TW202127164A - Method for controlling robot to get out of trap, robot, electronic device and computer-readable storage medium - Google Patents

Abstract

The invention provides a method for controlling a robot to get out of a trap, a robot, an electronic device and a computer-readable storage medium. The method detects the moving state of the robot body, and determines the position of the force point of the multi joint manipulator on the support body when the robot body is detected to be in a trapped state; based on the determined position of the force point on the support body, the end of the multi joint manipulator far away from the robot body is controlled to contact the support body, and the multi joint manipulator is controlled to exert the target force on the robot body under the support of the support body, so as to make the robot body out of the trapped state.

Description

Method, robot, electronic device and computer readable storage medium for controlling robot to escape

The present invention relates to the field of robotics, in particular, to a method for controlling a robot to get out of trouble, a robot, an electronic device, and a computer-readable storage medium.

With the rapid development of robots, robots are becoming more and more important in life, learning and other scenarios. At present, during the working process of the robot, the robot may be trapped by obstacles, which makes the robot unable to work normally.

In view of this, the present invention provides at least a solution for controlling the robot to get out of trouble.

In a first aspect, the present invention provides a method for controlling the escape of a robot, the robot including a multi-joint manipulator and a robot body, and the method includes: Detect the traveling state of the robot body; In the case of detecting that the robot body is in a trapped state, determine the position of the force point of the multi-joint robot arm on the support body; Based on the determined position of the force point on the support body, the end of the multi-joint robot arm away from the robot body is controlled to contact the support body, and the multi-joint robot arm is controlled to contact the support body under the support of the support body. The robot body applies a target force to release the robot body from the trapped state.

In the above embodiment, the traveling state of the robot body can be detected; when it is detected that the robot body is in a trapped state, the force point position of the multi-joint manipulator on the support body is determined; based on the determined force point position on the support body, Control the end of the multi-joint robot arm away from the robot body to contact the support body, and control the multi-joint robot arm to apply the target force to the robot body under the support of the support body to make the robot body out of the trapped state, so that the robot can complete automatically Get out of trouble, ensure the normal work of the robot, and improve the working efficiency of the robot.

In a possible implementation manner, before the determining the position of the force point of the multi-joint manipulator on the support body, the method includes: Detecting at least one candidate support corresponding to the current position of the robot body and/or the attribute characteristics of the at least one candidate support based on a sensor provided on the robot body; Based on the attribute characteristics of each candidate support body and/or the priority order of the support bodies set, determine the support body corresponding to the multi-joint manipulator from at least one candidate support body; the attribute characteristics are used to characterize the support body The softness and hardness of the surface structure.

Here, according to the attributes and characteristics of the candidate supports, the harder objects can be preferentially selected as the support, so that the support of the material has a better support effect; in addition, the priority order of various supports that may appear in the surrounding environment can also be preset For example, hard objects have a higher priority, and objects that are not easily damaged have a higher priority. For example, the ground can have the highest priority, followed by walls, desktops, and glass objects.

In a possible implementation manner, based on the attribute characteristics of each candidate support and/or the set priority order of the support, determining the support corresponding to the multi-joint manipulator from at least one candidate support includes: Based on the attribute characteristics of each candidate support and/or the set priority order of the support, select an unselected candidate support from at least one candidate support; The determination is based on the position of the force point on the candidate support and the position of the end of the multi-joint manipulator arm away from the robot body, and it is determined that the end of the multi-joint manipulator arm away from the robot body reaches the position of the force point , The predicted pose information of the multi-joint manipulator; Controlling the end of the multi-joint robot arm away from the robot body to move to the position of the focus point, and detecting the current pose information of the multi-joint robot arm; In the case that the current pose information does not match the predicted pose information, return to the step of selecting an unselected candidate support from at least one candidate support until the current position of the multi-joint robot arm The pose information matches the predicted pose information, or until there is no unselected candidate support among the at least one candidate support.

Here, if the current pose information of the multi-joint manipulator does not match the predicted pose information, it indicates that there is a problem with the detection result of the attribute characteristics of the support (for example, the detected hardness of the support has a lower actual hardness). Reselect an unselected candidate support and continue to match the above-mentioned pose information to reduce the probability of problems in the selection of the support due to inaccurate detection results, and to ensure the support effect of the support. In this way, the multi-joint manipulator can exert more effective force on the robot body under the support of the rigid support body.

In a possible implementation manner, the determining the position of the force point of the multi-joint manipulator on the support includes: Divide the area corresponding to the detected support into multiple sub-areas, and determine the center point of each sub-area in the multiple sub-areas; The focus point of the multi-joint manipulator is selected from the center points of the multiple sub-regions.

In a possible implementation manner, the selecting the focus point of the multi-joint manipulator from the center points corresponding to the multiple sub-regions includes: Based on the direction and distance between each center point and the end of the multi-joint robot arm approaching the robot body, the focus point of the multi-joint robot arm is selected from the center points of the plurality of sub-regions.

In the above embodiment, by dividing the support body into multiple sub-regions, based on the direction and distance between each center point and the end of the multi-joint manipulator close to the robot body, the multi-joint manipulator arm is selected from the center points of the multiple sub-regions Compared with the method of randomly testing the focus point, in this way, the robot body has a higher efficiency in getting out of the trapped state.

In a possible implementation manner, controlling the end of the multi-joint manipulator away from the robot body to contact the support body based on the determined position of the force point on the support body includes: Determining the movement path of the multi-joint robot arm based on the position of the focus point and the current position of the end of the multi-joint robot arm away from the robot body; The multi-joint robot arm is controlled to move according to the movement path until the end of the multi-joint robot arm away from the robot body contacts the support body.

In a possible implementation manner, the controlling the multi-joint mechanical arm to apply a target force to the robot body under the support of the support body to make the robot body out of the trapped state includes: Determining the target direction for the robot body to escape the trapped state; The multi-joint mechanical arm is controlled to apply the target force in the target direction to the robot body under the support of the support body, so that the robot body is out of the trapped state.

In the above embodiment, the target direction is the direction of the target force applied by the multi-joint manipulator to the robot body. By clarifying the direction of the applied force, the efficiency of the robot body from the trapped state can be improved.

In a possible implementation manner, the determining the target direction that causes the robot body to leave the trapped state includes: Based on the pose data of the robot body, a target direction for the robot body to leave the trapped state is determined.

In a possible implementation manner, the determining the target direction for the robot body to leave the trapped state based on the pose data of the robot body includes: Determining the state of at least one wheel provided on the robot body based on the pose data of the robot body; Based on the state of the at least one wheel, a target direction for causing the robot body to leave the trapped state is determined.

In the above implementation manner, the direction of the target force can be determined more accurately based on the pose data of the robot body, thereby improving the efficiency of the robot body from the trapped state.

In a possible implementation manner, the determining the target direction that causes the robot body to leave the trapped state includes: Selecting a currently unselected direction from a plurality of preset directions as the target direction; Controlling the multi-joint manipulator arm to apply the target force in the target direction to the robot body, and detecting the state of the robot body; In the case that the robot body is not out of the trapped state, return to the step of selecting a currently unselected direction from the preset multiple directions as the target direction, until the robot body is out of the trapped state. Status, or until there is no unselected direction among the preset multiple directions.

In the foregoing embodiment, the target direction can be selected from multiple preset directions through continuous attempts. This method does not require calculation of the target direction, and saves processing resources.

In a possible implementation manner, the joint unit far from the robot body in the multi-joint manipulator is the first joint unit, and the joint unit close to the robot body is the second joint unit; Before controlling the multi-joint manipulator to apply a target force to the robot body, the method further includes: Based on the target direction, adjust the pose information of each joint unit in the multi-joint manipulator so that the adjusted angle between the second joint unit and the robot body matches the target direction ； Or, based on the target direction and the direction of action of the first joint unit, adjust the pose information of each joint unit in the robotic arm so that the adjusted second joint unit is between the robot body The included angle of is matched with the target direction; and the adjusted included angle between the first joint unit and the area where the force point position is located matches the direction of action of the first joint unit.

In the above embodiment, by setting the action direction for the first joint unit in the multi-joint robot arm, the support effect between the first joint unit and the support body in the multi-joint robot arm can be better; at the same time, the second joint unit is adjusted The position and posture of is matched with the above-mentioned target direction, so that the multi-joint manipulator can apply force in the target direction to the robot body, thereby making the robot body out of the trapped state.

In a possible implementation manner, the controlling the multi-joint manipulator arm to apply a target force to the robot body includes: By adjusting at least one of the following included angles, the multi-joint manipulator arm is controlled to apply a target force to the robot body: The included angle between adjacent joint units in the multi-joint manipulator; The included angle between the first joint unit in the multi-joint manipulator and the area where the focus point is located; The included angle between the second joint unit and the robot body.

In a possible implementation manner, in the case of detecting that the robot body is in a trapped state, determining the position of the force point of the multi-joint manipulator on the support body further includes: In the case of detecting that the robot body is in a trapped state, controlling the robot body to change the direction of movement and move; The determining the position of the force point of the multi-joint mechanical arm on the support includes: After detecting that the robot body changes the direction of movement and moves, and does not leave the trapped state, the position of the force point of the multi-joint manipulator on the support body is determined.

For the description of the effects of the following devices, electronic equipment, etc., please refer to the description of the above method, which will not be repeated here.

In a second aspect, the present invention provides a robot, the robot includes a multi-joint manipulator arm and a robot body, the multi-joint manipulator arm is movably connected to the robot body, the robot body is provided with a controller, and the control The robot controls the multi-joint robot arm by sending a control signal to a steering gear provided in each joint unit of the multi-joint robot arm, so as to implement the method for controlling the robot to escape as described in the first aspect.

In a third aspect, the present invention provides a device for controlling the escape of a robot. The robot includes a multi-joint manipulator and a robot body, and the device includes: The state detection module is configured to detect the traveling state of the robot body; A force point position determining module, configured to determine the force point position of the multi-joint manipulator on the support body in the case of detecting that the robot body is in a trapped state; The control module is configured to control the end of the multi-joint robot arm away from the robot body to contact the support body based on the determined position of the force point on the support body, and control the multi-joint robot arm to contact the support body Under the support of, apply a target force to the robot body to make the robot body out of the trapped state.

In a possible implementation manner, the device further includes: The candidate support detection module is configured to detect at least one candidate support corresponding to the current position of the robot body and/or the attribute of the at least one candidate support based on a sensor provided on the robot body feature; The support body determination module is configured to determine the support body corresponding to the multi-joint robot arm from at least one candidate support body based on the attribute characteristics of each candidate support body and/or the set priority order of the support body; the attribute The feature is used to characterize the softness and hardness of the surface structure of the support.

In a possible implementation manner, the force point position determination module determines the support body corresponding to the multi-joint robot arm from at least one candidate support body according to the following steps: Based on the attribute characteristics of each candidate support and/or the set priority order of the support, select an unselected candidate support from at least one candidate support; The determination is based on the position of the force point on the candidate support and the position of the end of the multi-joint manipulator arm away from the robot body, and it is determined that the end of the multi-joint manipulator arm away from the robot body reaches the position of the force point , The predicted pose information of the multi-joint manipulator; After controlling the end of the multi-joint robot arm away from the robot body to move to the position of the focus point, detecting the current pose information of the multi-joint robot arm; In the case that the current pose information does not match the predicted pose information, return to the step of selecting an unselected candidate support from at least one candidate support until the current position of the multi-joint robot arm The pose information matches the predicted pose information, or until there is no unselected candidate support among the at least one candidate support.

In a possible implementation manner, the force point position determination module uses the following steps to determine the force point position of the multi-joint manipulator on the support: Divide the area corresponding to the detected support into multiple sub-areas, and determine the center point of each sub-area in the multiple sub-areas; The focus point of the multi-joint manipulator is selected from the center points of the multiple sub-regions.

In a possible implementation manner, the force point position determination module uses the following steps to select the force point of the multi-joint manipulator from the center points corresponding to the multiple sub-regions: Based on the direction and distance between each center point and the end of the multi-joint robot arm approaching the robot body, the focus point of the multi-joint robot arm is selected from the center points of the multiple sub-regions.

In a possible implementation manner, the control module uses the following steps to control the end of the multi-joint manipulator away from the robot body to contact the support body: Determining the movement path of the multi-joint robot arm based on the position of the focus point and the current position of the end of the multi-joint robot arm away from the robot body; The multi-joint robot arm is controlled to move according to the movement path until the end of the multi-joint robot arm away from the robot body contacts the support body.

In a possible implementation manner, the control module uses the following steps to apply a target force to the robot body: Determining the target direction for the robot body to escape the trapped state; The multi-joint mechanical arm is controlled to apply the target force in the target direction to the robot body under the support of the support body, so that the robot body is out of the trapped state.

In a possible implementation manner, the control module uses the following steps to determine the target direction for the robot body to leave the trapped state: Based on the pose data of the robot body, a target direction for the robot body to leave the trapped state is determined.

In a possible implementation manner, the control module uses the following steps to determine a target direction for the robot body to leave the trapped state based on the pose data of the robot body: Determining the state of at least one wheel provided on the robot body based on the pose data of the robot body; Based on the state of the at least one wheel, a target direction for causing the robot body to leave the trapped state is determined.

In a possible implementation manner, the control module uses the following steps to determine the target direction for the robot body to leave the trapped state: Selecting a currently unselected direction from a plurality of preset directions as the target direction; Controlling the multi-joint manipulator arm to apply the target force in the target direction to the robot body, and detecting the state of the robot body; In the case that the robot body is not out of the trapped state, return to the step of selecting a currently unselected direction from the preset multiple directions as the target direction, until the robot body leaves the trapped state , Or until there is no unselected direction among the preset multiple directions.

In a possible implementation manner, the joint unit far from the robot body in the multi-joint manipulator arm is the first joint unit, and the joint unit close to the robot body is the second joint unit; Before controlling the multi-joint mechanical arm to apply a target force to the robot body, the device further includes: The first adjustment module is configured to adjust the pose information of each joint unit in the multi-joint manipulator based on the target direction, so that the adjusted angle between the second joint unit and the robot body is , Which matches the target direction; Alternatively, the second adjustment module is configured to adjust the pose information of each joint unit in the robotic arm based on the target direction and the action direction of the first joint unit, so that the adjusted second joint The angle between the unit and the robot body matches the target direction; and the adjusted angle between the first joint unit and the area where the force point is located is the same as the first joint unit Match the direction of action.

In a possible implementation manner, the control module uses the following steps to control the multi-joint manipulator arm to apply a target force to the robot body: By adjusting at least one of the following included angles, the multi-joint manipulator arm is controlled to apply a target force to the robot body: The included angle between adjacent joint units in the multi-joint manipulator; The included angle between the first joint unit in the multi-joint manipulator and the area where the focus point is located; The included angle between the second joint unit and the robot body.

In a possible implementation manner, the module for determining the position of the focus point further includes: The moving direction changing unit is configured to control the robot body to change the moving direction to move when it is detected that the robot body is in a trapped state; The force point position determination module uses the following steps to determine the force point position of the multi-joint robot arm on the support body: After detecting that the robot body changes the direction of movement and moves, and does not leave the trapped state, determine the position of the force point of the multi-joint robot arm on the support body.

In a fourth aspect, the present invention provides an electronic device comprising: a processor and a memory connected to each other, the memory storing machine-readable instructions executable by the processor, and when the electronic device is running, the machine can When the read instruction is executed by the processor, the steps of the method for controlling the robot to get out of trouble as described in the first aspect or any one of the embodiments are executed.

In a fifth aspect, the present invention provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium, and the computer program executes the control robot described in the first aspect or any one of the above-mentioned embodiments when the computer program is run by a processor Steps of the method of getting out of trouble.

In a sixth aspect, the present invention provides a computer program that, when executed by a processor, implements the steps of any one of the above-mentioned methods for controlling a robot to get out of trouble.

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, preferred embodiments are described in detail below in conjunction with the accompanying drawings.

In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is only a part of the embodiments of the present invention, rather than all the embodiments. The elements of the embodiments of the present invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the protection scope of the present invention.

In order to solve the problem of the robot being trapped by obstacles and ensure the normal operation of the robot, an embodiment of the present invention provides a method for controlling the robot to escape from the trap. By controlling the multi-joint manipulator under the support of the support body, the target force is applied to the robot body. , So that the robot body is out of the trapped state, ensuring the normal operation of the robot.

In order to facilitate the understanding of the embodiments of the present invention, a method for controlling the escape of a robot disclosed in the embodiments of the present invention is first introduced in detail.

The method for controlling the escape of a robot provided by the embodiment of the present invention can be applied to a user terminal, a server, or a controller (such as a processor) provided on the robot body. When the robot body is in a trapped state, the user or server or controller can execute the computer instructions to implement the method for controlling the robot to escape from the trap provided by the embodiments of the present invention, and control the multi-joint manipulator to apply the target force to the robot body, so that the robot The body is out of the trapped state, so that the robot can work normally, and the working efficiency of the robot is improved.

Exemplarily, the robot may be a sweeping robot, where the sweeping robot absorbs ground debris into a built-in garbage storage box through a built-in vacuum cleaner. In order to improve the absorption efficiency of the sweeping robot, the gap between the main body of the sweeping robot and the ground is small. Therefore, when the sweeping robot is actually used, for example, when the sweeping robot cleans the user's room, it may be wire or rolled up. The carpet etc. are trapped, making the sweeping robot unable to work normally, that is, the sweeping robot is in a trapped state. In order to solve the problem that the sweeping robot cannot work normally, a multi-joint manipulator can be provided on the sweeping robot. The multi-joint manipulator arm is connected to the robot body. When the robot body is trapped, the controller provided on the robot body can pass the invention The method for controlling the escape of a robot provided by the embodiment controls the multi-joint manipulator to apply a target force to the robot body, so that the robot body is released from the trapped state, thereby enabling the robot to work normally and improving the working efficiency of the robot.

1 is a schematic flowchart of a method for controlling a robot to get out of trouble according to an embodiment of the present invention. The method can be applied to a controller set on a user terminal, a server, and a robot body, wherein the method is applied to Take the sweeping robot as an example.

A method for controlling a robot to escape from the trap shown in Figure 1 includes the following steps: S101, detecting the traveling state of the robot body; S102, in the case of detecting that the robot body is in a trapped state, determine the position of the force point of the multi-joint manipulator on the support body; S103: Based on the determined force point position on the support body, control the end of the multi-joint manipulator arm away from the robot body to contact the support body, and control the multi-joint manipulator arm to apply a target force to the robot body under the support of the support body, so that The robot body is out of the trapped state.

Based on the above steps, the traveling state of the robot body can be detected; when it is detected that the robot body is in a trapped state, the force point position of the multi-joint manipulator on the support body is determined; based on the determined force point position on the support body, control The end of the multi-joint manipulator arm away from the robot body contacts the support body, and controls the multi-joint manipulator arm to apply a target force to the robot body under the support of the support body to free the robot body from the trapped state, so that the robot can automatically complete the escape , To ensure the normal work of the robot and improve the work efficiency of the robot.

Regarding S101: In the embodiment of the present invention, the traveling state includes a trapped state and a non-trapped state. In specific implementation, the traveling state of the robot body can be detected by the visual sensor and wheel encoder provided on the robot body, or the robot body can be detected by the inertial measurement unit (IMU) provided on the robot body The state of travel. In specific implementation, the method for detecting the traveling state of the robot body can be determined according to the type of the sensor provided on the robot body, which is not specifically limited in the embodiment of the present invention.

In the embodiment of the present invention, the visual sensor detects the surrounding environment where the robot body is located, the wheel encoder detects the rotation state of the wheels set on the robot body, and the IMU detects the three-axis attitude angle and acceleration of the robot body. Perform detection, that is, detect the travel data of the robot body. Exemplarily, the process of detecting the traveling state of the robot body through the vision sensor and wheel encoder provided on the robot body may be: if the vision sensor provided on the robot body detects that the surrounding environment where the robot body is located is not When the change occurs and the wheel sensor detects that the wheels on the robot body are always rotating, it is determined that the robot is in a trapped state; if the vision sensor on the robot body detects the surroundings of the robot body When the environment has not changed, and the wheel sensor detects that the wheels on the robot body are not rotating, or the vision sensor on the robot body detects that the surrounding environment where the robot body is located has changed, and the wheels at the same time When the type sensor detects that the wheels provided on the robot body are in a rotating state, it is determined that the robot is in a non-trapped state.

Exemplarily, detecting the traveling state of the robot body through the IMU set on the robot body may be: the IMU detects the traveling data of the robot body, and based on the traveling data obtained by the IMU detection, the traveling state of the robot body is performed according to the prior knowledge and experience. judge. Exemplarily, the prior knowledge experience includes: if the robot body is trapped, and due to the action of obstacles, the first driving wheel provided on the robot body does not contact the ground, and the second driving wheel is in contact with the ground. The acceleration of the robot body has an acceleration component perpendicular to the ground. Therefore, if the IMU detects that the acceleration of the robot body has an acceleration component perpendicular to the ground, it will determine that the robot body is in a trapped state.

Regarding S102: In the embodiment of the present invention, the supporting body may be a ground or a wall, or any object with a surface structure that the robot can touch in actual use, such as a refrigerator, a washing machine, and the like. Among them, objects with a surface structure that meet the requirements refer to objects with a hard surface structure, such as refrigerators, wooden wardrobes, etc.; objects with a surface structure that do not meet the requirements refer to objects with a soft surface structure, such as carpets, leather sofas, etc. .

In the embodiment of the present invention, when it is detected that the robot body is in a trapped state, the support body can be determined by the visual sensor provided on the robot body. After the support body is determined, the focus of the multi-joint manipulator arm can be determined from the support body , So that the multi-joint manipulator can apply the target force to the robot body based on the focus point.

In a possible implementation manner, before determining the position of the force point of the multi-joint manipulator on the support, the method includes: Based on a sensor set on the robot body, detecting at least one candidate support body corresponding to the current position of the robot body, and/or attribute characteristics of the at least one candidate support body; Based on the attribute characteristics of each candidate support and/or the priority order of the support set, determine the support corresponding to the multi-joint manipulator from at least one candidate support; the attribute characteristics are used to characterize the hardness of the surface structure of the support Degree characteristics.

In this specific implementation, the image corresponding to the current position of the robot body can be obtained through the visual sensor, the image can be recognized, the candidate support body existing in the image can be determined, and the attribute characteristics of the candidate support body can be judged , Where the attribute characteristics include hardness and softness, or include different identifications of softness and hardness. Exemplarily, a deep learning model can be used to determine the candidate support body and the attribute characteristics of the candidate support body that exist in the image. Specifically, the image is input into a trained deep learning model for processing, and the image includes The candidate support and the attribute characteristics of the candidate support. For example, the image A corresponding to the current position of the robot body A obtained by the vision sensor is input into the deep learning model for processing, and the candidate supports in the obtained image A include: sofa and ground, then the detected The attribute characteristic of the sofa is softness, and the attribute characteristic of the ground is rigidity.

In this specific implementation, other sensors can also be used to detect the attribute characteristics of the candidate support. For example, a tactile sensor is provided on the end of the multi-joint robot arm away from the robot body. The specific method used to detect the above attribute characteristics can be based on The actual needs to be determined, and the embodiment of the present invention does not specifically limit this.

In specific implementation, the support body corresponding to the multi-joint manipulator can be determined from at least one candidate support body based on the attribute characteristics of each candidate support body. Specifically, harder objects can be selected according to the attribute characteristics of the candidate support body As a support. Continuing with the above example, if it is detected that the candidate support body corresponding to the current position of the robot body A includes a sofa and the ground, based on the attribute characteristics of the candidate support body, it can be determined that the support body corresponding to the multi-joint manipulator is the ground; if it is detected The candidate support body corresponding to the current position of the robot body F includes the sofa, the ground, and the table top. Since the hardness of the ground is higher than that of the table top, and the hardness of the table top is higher than that of the sofa, the ground can be determined as the supporting body.

Exemplarily, the priority order of the support body may be determined according to the target direction range of the multi-joint manipulator under the support of the support body to apply the target force to the robot body. For example, if the end of the multi-joint manipulator that is far away from the robot body is a manipulator, the multi-joint manipulator arm is supported by the ground, and the target direction range for applying the target force to the robot body can be from 0 degrees to 90 degrees ( Including 0 degree direction and 90 degree direction); under the support of the wall, the multi-joint manipulator can apply the target force to the robot body in the target direction range of 0 degree direction, but not 90 degree direction, where 0 degree direction is Refers to the direction parallel to the ground, and the 90-degree direction refers to the upward direction perpendicular to the ground; therefore, the target direction range corresponding to the ground is larger than the target direction range of the wall. Therefore, the priority of the ground can be set higher than the priority of the wall. And/or, the priority of the support can be determined according to the vulnerability of the surface of the support, for example, the vulnerability of the wall is higher than that of the ground, and the vulnerability of furniture (refrigerator, sofa, etc.) is higher than that of the wall. Therefore, the priority of the ground can be set higher than the priority of the wall, and the priority of the wall is higher than the priority of the furniture. And/or, the priority of the support can be determined according to the hardness of the surface of the support. For example, the hardness of the ground is higher than that of the wall, the hardness of the wall is higher than that of the desktop, the hardness of the desktop is higher than that of the sofa, and the priority of the support is from high to low. It can be ground, wall, table top, sofa. Among them, the vulnerability and hardness of each support body can be determined based on prior knowledge and experience.

In specific implementation, the support body corresponding to the multi-joint manipulator can be determined from at least one candidate support body based on the set priority order of the support body. For example, if the candidate support body corresponding to the current position of the robot body B is detected When it includes sofas, floors, and walls, based on the priority order of the supports set, it can be determined that the support corresponding to the multi-joint manipulator is the ground.

In a specific implementation, the support body corresponding to the multi-joint robot arm may be determined from at least one candidate support body based on the attribute characteristics of each candidate support body and the set priority order of the support body. For example, if it is detected that the candidate support body corresponding to the current position of the robot body B includes a sofa, a floor, and a wall, since the attribute characteristic of the sofa is soft, it is determined that the sofa cannot be used as a support body, so the sofa is excluded; because the ground has priority The level is higher than the wall, so the ground is determined as the supporting body corresponding to the multi-shutdown mechanical arm. The priority order of the support body may be specifically determined according to the use scenario of the robot, which is not specifically limited in the embodiment of the present invention.

Exemplarily, multiple support bodies may also be determined for the multi-joint robot arm, and the priority of the multiple support bodies may be determined according to the priority order of the support bodies. Continuing the description from the above embodiment, if the priority order of the support body is that the ground is greater than the wall, and it is detected that the candidate support body corresponding to the current position of the robot body C includes the ground and the wall, the ground can be used as the first support body, and the wall As a second support. In a specific implementation, the end of the multi-joint robot arm away from the robot body is first controlled to contact the first support body, and the multi-joint robot arm is controlled to apply a target force to the robot body under the support of the first support body. When controlling the multi-joint manipulator arm under the support of the first support body and cannot make the robot body out of the trapped state, you can control the end of the multi-joint manipulator arm away from the robot body to contact the second support body, and control the multi-joint manipulator arm to be in contact with the second support body. Under the support of the second support body, a target force is applied to the robot body to make the robot body out of the trapped state. By providing multiple support bodies for the multi-joint mechanical arm, the flexibility of the robot body from the trapped state is improved, and the efficiency of the robot body from the trapped state is improved.

In the embodiment of the present invention, the sensor provided on the robot body may be a vision sensor. When determining the support body through the visual sensor set on the robot body, the initial image corresponding to the robot body can be obtained based on the pose information of the robot body in the trapped state; whether there is support in the initial image If there is no support body, you can judge whether the robot body can rotate, that is, whether the robot body can rotate clockwise and/or counterclockwise; after confirming that the robot body can rotate, control the robot body to rotate, and in the process of rotation , Acquire the image corresponding to the robot body, and determine the support body corresponding to the robot body based on the image obtained during the rotation process.

In the embodiment of the present invention, when the robot body is close to a wall or a refrigerator or other support that is perpendicular to the ground, when the support is detected by a vision sensor, there may be situations in which the support cannot be determined within the visual range, and/or, When the robot body cannot rotate, at least one ultrasonic sensor can be used to determine whether there is a support body perpendicular to the ground. The ultrasonic sensor transmits and receives ultrasonic waves to determine whether there is a support body at the position of the robot body, and when there is a support body, it determines the distance between the support body and the robot body. Among them, the number of ultrasonic sensors set on the robot body can be determined according to the range of the ultrasonic wave emitted by the ultrasonic sensor. For example, if the ultrasonic sensor emits the ultrasonic wave in a 60-degree fan-shaped area, it can be set by 6 An ultrasonic sensor realizes a 360-degree omni-directional detection of the area around the robot body.

In the embodiment of the present invention, according to the attribute characteristics of the candidate support, a harder object can be preferentially selected as the support, so that the support of the material has a better support effect; in addition, various supports that may appear in the surrounding environment can also be preset For example, hard objects have a higher priority, and objects that are not easily damaged have a higher priority. For example, the priority of the ground can be set to the highest, followed by walls, desktops, glass objects, etc. .

In a possible implementation manner, based on the attribute characteristics of each candidate support and/or the set priority order of the support, determining the support corresponding to the multi-joint manipulator from at least one candidate support includes: Based on the attribute characteristics of each candidate support and/or the set priority order of the support, select an unselected candidate support from at least one candidate support; The determination is based on the position of the force point on the candidate support and the position of the end of the multi-joint manipulator away from the robot body, and determines the predicted pose of the multi-joint manipulator when the end of the multi-joint manipulator arm away from the robot body reaches the position of the force point News; Control the end of the multi-joint robot arm away from the robot body to move to the position of the focus point, and detect the current pose information of the multi-joint robot arm; In the case that the current pose information does not match the predicted pose information, return to the step of selecting an unselected candidate support from at least one candidate support until the current pose information of the multi-joint manipulator and the predicted pose The information matches, or until there is no unselected candidate support in at least one candidate support.

In the embodiment of the present invention, the predicted pose information is estimated by the multi-joint manipulator. In the case where the end of the multi-joint manipulator away from the robot body touches the position of the force point, the estimated pose information is corresponding to the multi-joint manipulator. In specific implementation, the movement path of the multi-joint robot arm can be determined, and when the movement path of the multi-joint robot arm is determined, the predicted pose information of the multi-joint robot arm can be estimated. Exemplarily, by determining the movement path of the multi-joint manipulator based on the position of the force point and the current position of the end of the multi-joint manipulator away from the robot body, and the predicted pose information of the multi-joint manipulator, the control of the multi-joint manipulator arm away from After one end of the robot body moves to the position of the focus point according to the determined movement path, the current pose information of the multi-joint manipulator is detected. Based on the detected current pose information and the matching of the predicted pose information, the multi-joint manipulator's position is determined Support body.

In the embodiment of the present invention, in the process of determining the support body, when detecting the attribute characteristics of the candidate support body, there may be a situation that the attribute characteristic detection error occurs. For example, the attribute feature of the soft candidate support is determined to be rigid, which in turn causes the candidate support with the soft attribute feature to be determined as the support. Therefore, it is possible to select an unselected candidate support from at least one candidate support based on the attribute characteristics of each candidate support and/or the set priority order of the support; after selecting a candidate support, control After the end of the multi-joint manipulator moves away from the robot body to the position of the force point on the candidate support, it is detected whether the current pose information of the multi-joint manipulator matches the predicted pose information, and if it does not match, the candidate support is reselected; If it matches, the candidate support is used as the support corresponding to the multi-joint robot arm.

In specific implementation, if the attribute feature of the support body is soft, the posture information of the multi-joint robot arm will change after the multi-joint robot arm touches the force point on the support body, resulting in the posture of the multi-joint robot arm The difference between the information and the preset pose information exceeds the set range, making the current pose information of the multi-joint robot arm mismatch the predicted pose information; conversely, if the attribute characteristics of the support body are rigid, the multi-joint robot After the arm touches the force point on the support, the pose information of the multi-joint robotic arm will basically not change, or the difference between the pose information of the multi-joint robotic arm and the predicted pose information is within the set range, that is, The current pose information of the multi-joint manipulator matches the predicted pose information. Therefore, the candidate supports can be detected based on the current pose information and the predicted pose information of the multi-joint manipulator.

In the embodiment of the present invention, if the current pose information of the multi-joint robot arm does not match the predicted pose information, it indicates that there is a problem with the detection result of the attribute characteristics of the support (for example, the detected support with a high hardness has a lower actual hardness) At this time, an unselected candidate support can be reselected, and the matching of the above-mentioned pose information can be continued to reduce the probability of problems in the selection of the support due to the inaccurate detection result, and to ensure the support effect of the support. In this way, the multi-joint manipulator can exert more effective force on the robot body under the support of the rigid support body.

In a possible implementation manner, determining the position of the force point of the multi-joint manipulator on the support includes: Divide the area corresponding to the detected support into multiple sub-areas, and determine the center point of each sub-area in the multiple sub-areas; From the center points of multiple sub-regions, select the focus point of the multi-joint manipulator.

In the embodiment of the present invention, the area corresponding to the support refers to the area of the corresponding support in the image obtained by the vision sensor, where the area corresponding to the support is a partial area of the surface of the support, for example, if When the support is a wall, the area corresponding to the support is the area corresponding to the wall image captured by the vision sensor. After the support body is determined, the region corresponding to the support body can be divided into multiple sub-regions, wherein the number of the divided sub-regions can be determined according to the area of the support body, or the number of the divided sub-regions can be a preset number. For example, if the supporting body is a wall, the wall is divided into multiple sub-regions, the center point of each sub-region is determined, and the force point of the multi-joint robot arm is selected from the multiple center points.

In a possible implementation manner, selecting the focus point of the multi-joint manipulator from the center points corresponding to the multiple sub-regions includes: Based on the direction and distance between each center point and the end of the multi-joint robot arm approaching the robot body, the focus point of the multi-joint robot arm is selected from the center points of multiple sub-regions.

In the embodiment of the present invention, since the length of the multi-joint manipulator is determined, if the distance between the center point and the end of the multi-joint manipulator close to the robot body is greater than the length of the multi-joint manipulator, the center point cannot be used as a focus Point, so you can refer to the length of the multi-joint manipulator to determine the best distance value. At the same time, an optimal direction can be set for the robot body based on prior knowledge and experience. In the specific implementation, based on the optimal distance value and the optimal direction, the focus point of the multi-joint manipulator is selected from the center points of the multiple sub-regions.

For example, if a multi-joint robot arm includes 5 joint units, and the length of each joint unit is 10 cm, considering that the multi-joint robot arm needs to bend when performing an escape action, the optimal distance value can be set to less than 50 cm The value can be set according to the actual use scenario, for example, set to 20 cm. At the same time, the best direction for the robot body based on prior knowledge and experience can be the multi-joint manipulator approaching the end of the robot body and any setting on the robot body. The direction in which the position of a driving wheel is connected, or the optimal direction may be a direction perpendicular to the line connecting the positions of the two driving wheels. Wherein, the optimal direction can be determined according to the pose data of the robot body, or the scene of the robot body in actual use, which is not specifically limited in the embodiment of the present invention. Figure 2 shows a schematic diagram of the upper surface of a robot body. The position A in the figure is the position where the multi-joint manipulator is connected to the robot body (that is, the multi-joint manipulator is close to the end of the robot body), and the positions B and C are Where the driving wheel is located, the best direction can be the connection direction between position A and position B, that is, the direction indicated by ray 21, or the best direction can be the connection direction between position A and position C, that is, the direction indicated by ray 22 , Or the direction perpendicular to the line connecting position B and position C, that is, the direction indicated by the ray 23.

In the specific implementation, if there is no corresponding center point in the optimal distance and/or optimal direction, the point closest to the optimal distance can be selected from the center points of multiple sub-regions, and/or the optimal distance can be selected. The point in the direction closest to the direction. If the point on the best distance is inconsistent with the point on the best direction, the point on the best distance can be preferentially selected as the focus point. After selecting the point on the best distance as the focus point and controlling the end of the multi-joint manipulator away from the robot body to contact the focus point, the angle between the multi-joint manipulator arms can be made the best angle value, and then adjusted to the best angle The multi-joint manipulator arm with a high value can more accurately control the multi-joint manipulator arm to apply the target force to the robot body.

In the embodiment of the present invention, by dividing the support body into a plurality of sub-regions, based on the direction and distance between each center point and the end of the multi-joint manipulator close to the robot body, the multi-joint machine is selected from the center points of the multiple sub-regions. Compared with the method of randomly testing the force point of the arm, in this way, the robot body has a higher efficiency in getting out of the trapped state.

For S103: in the embodiment of the present invention, after determining the position of the force point, control the end of the multi-joint manipulator away from the robot body to contact the force point, and control the multi-joint manipulator arm to apply the target to the robot body under the support of the support body Force to get the robot body out of the trapped state. In actual use, the optimal value of the target force can be determined based on the weight of the robot body.

Exemplarily, if the target direction of the target force is a direction perpendicular to the ground, the target force is a force that enables the robot body to move upwards. For example, the size of the target force is set to be greater than the gravity of the robot body (the gravity can be based on the robot body The body weight is calculated); if the target direction of the target force is parallel to the ground, the target force is the force that enables the robot body to move horizontally. For example, set the target force to be greater than the frictional resistance exerted on the robot body (The frictional resistance is also related to the weight of the robot body). In summary, it can be seen that the value of the target force is related to the weight of the robot body. For example, if the weight of the robot body is larger, the corresponding optimal value of the target force is larger; if the weight of the robot body is smaller, the corresponding optimal value of the target force is smaller. In specific implementation, according to the application place of the robot body, at least one scene in which the robot body is in a trapped state can be counted, and the minimum target force for making the robot body out of the trapped state in each scene can be determined. From the minimum value corresponding to at least one scene, the largest value is selected as the best value of the target force. Wherein, the value of the target force can be determined according to the actual application site, which is not specifically limited in the embodiment of the present invention.

In a possible implementation manner, based on the determined position of the force point on the support body, controlling the end of the multi-joint manipulator away from the robot body to contact the support body includes: Determine the movement path of the multi-joint manipulator based on the position of the focus point and the current position of the end of the multi-joint manipulator away from the robot body; The multi-joint robot arm is controlled to move according to the movement path until the end of the multi-joint robot arm away from the robot body contacts the support body.

In the embodiment of the present invention, the position of the focus point and the current position of the end of the multi-joint robot arm away from the robot body are located in the same coordinate system. For example, the position of the focus point may be the coordinates of the focus point in the geodetic coordinate system, and the multi-joint robot arm The current position of the end away from the robot body is also the position of the end of the multi-joint robot arm in the geodetic coordinate system. In other embodiments, when the position of the focus point and the current position of the end of the multi-joint manipulator away from the robot body are not in the same coordinate system, the two can be converted to the same coordinate system through coordinate conversion. Among them, the coordinate system can be selected according to the actual situation. In specific implementation, the movement path of the multi-joint manipulator can be planned based on the position of the force point and the current position of the end of the multi-joint manipulator away from the robot body through inverse kinematics; it can also be based on the position of the force point and the multi-joint manipulator through a deep learning algorithm. The current position of the end of the articulated manipulator arm away from the robot body determines the movement path of the multi-joint manipulator arm.

In a possible implementation manner, controlling the multi-joint mechanical arm to apply a target force to the robot body under the support of the support body to make the robot body out of the trapped state includes: Determine the target direction to make the robot body out of the trapped state; The multi-joint manipulator is controlled to apply a target force in the target direction to the robot body under the support of the support body, so that the robot body is out of the trapped state.

In the embodiment of the present invention, when the robot arm supports the support body, it generates a force on the support body, and at the same time, the support body generates a reaction force on the robot arm. The reaction force is transmitted to the robot body (ie the target force) through the robot arm. The target direction is the direction of the target force applied by the multi-joint manipulator to the robot body. By clarifying the direction of the applied force, the efficiency of the robot body from the trapped state can be improved.

In a possible implementation manner, determining the target direction for the robot body to escape from the trapped state includes: Based on the pose data of the robot body, determine the target direction to make the robot body out of the trapped state.

In an implementation manner, the target direction for the robot body to escape from the trapped state can be determined based on the prior knowledge and experience based on the pose data of the robot body. For example, in a certain application site, determine at least one scene where the robot body is trapped, count the sample pose data of the robot body in the trapped state in each scene, and determine that the robot body in the scene is out of the trapped state The sample target direction of the robot body is stored in association with the corresponding sample target direction, so that when the robot body is detected in a trapped state, it can be based on the robot body’s pose data from the stored sample of the robot body. From the pose data and the corresponding target direction of the sample, determine the target direction that makes the robot body out of the trapped state.

In the embodiment of the present invention, the pose data of the robot body is the position data and the posture data of the robot body in a preset coordinate system. Exemplarily, the pose data of the robot body can be detected through an inertial measurement unit (IMU) provided on the robot body.

In a possible implementation manner, based on the pose data of the robot body, determining the target direction to make the robot body out of the trapped state includes: Determine the state of at least one wheel set on the robot body based on the pose data of the robot body; Based on the state of at least one wheel, a target direction for the robot body to escape from the trapped state is determined.

In the embodiment of the present invention, the state of the wheel can be ground contact or non-contact ground, that is, if the wheel is in contact with the ground, the state of the wheel is ground contact; if the wheel is not in contact with the ground, the state of the wheel is non-contact ground . Based on the pose data of the robot body, the state of at least one wheel set on the robot body is determined, that is, it is determined whether each wheel is in contact with the ground or not in contact with the ground. For example, you can determine whether the robot body is tilted according to the pose data of the robot body. If so, determine the direction in which the robot body is tilted based on the pose data of the robot body. The status of each wheel. After the status of each wheel is determined, the target direction for making the robot body out of the trapped state can be determined based on the status of at least one wheel. Exemplarily, if there are at least one wheel that does not touch the ground, the direction perpendicular to the plane of the ground may be determined as the target direction, or the direction perpendicular to the upper surface of the robot body may be determined as the target direction; If the state of each of the at least one wheel is in contact with the ground, the direction parallel to the plane of the ground can be determined as the target direction, that is, the direction parallel to the upper surface of the robot body can be determined as the target direction.

In the embodiment of the present invention, the action direction of the target force can be determined more accurately based on the pose data of the robot body, thereby improving the efficiency of the robot body from the trapped state.

In a possible implementation manner, determining the target direction for the robot body to escape from the trapped state includes: Choose a direction that is not currently selected from the preset multiple directions as the target direction; Control the multi-joint manipulator to apply the target force in the target direction to the robot body, and detect the state of the robot body; When the robot body is not out of the trapped state, return to the step of selecting a currently unselected direction from the preset multiple directions as the target direction, until the robot body is out of the trapped state, or until the preset multiple directions There is no unselected direction in the direction.

In the embodiment of the present invention, a currently unselected direction can also be selected from a plurality of preset directions as the target direction. The preset multiple directions may include: a direction parallel to the robot body (0 degrees to the robot body) ), the direction perpendicular to the robot body (90 degrees to the robot body), the direction of 30 degrees to the robot body, the direction of 60 degrees to the robot body, etc. For example, the direction parallel to the robot body may be the target direction, or the direction perpendicular to the robot body may be the target direction. Among them, the preset multiple directions can be set according to actual needs. Refer to Figure 3 which shows a schematic side view of a robot body. The figure includes the robot body 31, ray 301, ray 302, ray 303, and ray 304. The position A is the position where the multi-joint manipulator is connected to the robot body. The direction indicated by the ray 301 is parallel to the robot body, the direction indicated by the ray 302 is 30 degrees to the robot body, the direction indicated by the ray 303 is 60 degrees to the robot body, and the ray 304 indicates The direction is perpendicular to the robot body.

In the embodiment of the present invention, based on the angle with the robot body, one direction can be selected as the target direction from large to small in sequence from the preset multiple directions, or it can be based on the angle with the robot body, from small to large in sequence from small to large. One of the preset multiple directions is selected as the target direction. For example, the direction parallel to the robot body can be selected as the target direction from a plurality of preset directions. If the robot body is not separated and trapped after controlling the multi-joint manipulator to apply the target force in the target direction to the robot body. In the state, you can select a direction that is 30 degrees to the robot body from the preset multiple directions as the target direction, until the robot body is out of the trapped state, or until there is no unselected direction in the preset multiple directions Direction.

In the embodiment of the present invention, if there is no unselected direction among the preset multiple directions, or after replacing the support body and/or the force point and re-applying the target force to the robot body, it is detected that the robot body is still When in a trapped state, an alarm signal can be generated to control the alarm device provided on the robot body to issue an alarm instruction, so that the user can control the robot body to release the trapped state based on the alarm instruction.

In the embodiment of the present invention, the target direction can be selected from a plurality of preset directions through continuous attempts. In this way, calculation of the target direction is not required, and processing resources are saved.

In a possible implementation manner, the joint unit far from the robot body in the multi-joint manipulator is the first joint unit, and the joint unit close to the robot body is the second joint unit; Before controlling the multi-joint manipulator to apply the target force to the robot body, the method further includes: Based on the target direction, adjust the pose information of each joint unit in the multi-joint manipulator so that the adjusted angle between the second joint unit and the robot body matches the target direction; Or, adjust the pose information of each joint unit in the robot arm based on the target direction and the direction of action of the first joint unit, so that the adjusted angle between the second joint unit and the robot body matches the target direction; and The adjusted angle between the first joint unit and the area where the force point is located matches the direction of action of the first joint unit.

In the embodiment of the present invention, by adjusting the posture information of each joint unit in the mechanical arm, the adjusted angle between the second joint unit and the robot body matches the target direction; thus, the multi-joint mechanical arm can be positioned at Under the support of the supporting body, a target force in the target direction is applied to the robot body, so that the robot body is out of the trapped state. Among them, if each wheel of the robot body is in contact with the ground and the target direction is perpendicular to the ground, and the angle between the second joint unit and the robot body is equal to 90 degrees, then the second joint unit and the robot body are The included angle matches the target direction.

In the embodiment of the present invention, the direction of action of the first joint unit can be determined through multiple tests according to the application of the robot body, so that the angle between the first joint unit and the area where the force point is located is the same as that of the first joint After the action directions of the units are matched, by controlling the multi-joint manipulator, the target force can be applied to the robot body more accurately, even if the support effect between the first joint unit and the support body in the multi-joint manipulator is better. For example, the direction of action of the first joint unit can be perpendicular to the surface of the support body, and the posture information of each joint unit can be adjusted so that the adjusted first joint unit is perpendicular to the area where the force point is located, even if The adjusted angle between the first joint unit and the area where the force point is located matches the direction of action of the first joint unit.

In the embodiment of the present invention, by setting the action direction for the first joint unit in the multi-joint manipulator, the angle between the first joint unit and the area where the force point is located can be controlled after adjusting the pose of each joint unit, and The action direction of the first joint unit is matched, so that the support effect between the first joint unit and the support body in the multi-joint manipulator is better; at the same time, the second joint can be controlled after adjusting the posture of each joint unit The included angle between the unit and the robot body is matched with the target direction, so that the multi-joint manipulator can apply force in the target direction to the robot body, thereby making the robot body out of the trapped state.

In a possible implementation manner, controlling the multi-joint manipulator to apply a target force to the robot body includes: By adjusting at least one of the following included angles, the multi-joint manipulator is controlled to exert a target force on the robot body: The included angle between adjacent joint units in a multi-joint manipulator; The included angle between the first joint unit of the multi-joint manipulator and the area where the force point is located; The included angle between the second joint unit and the robot body.

In the embodiment of the present invention, by adjusting the included angle between adjacent joint units in the multi-joint robotic arm; and/or, adjusting the included angle between the first joint unit in the multi-joint robotic arm and the area where the force point is located; and/or, The angle between the second joint unit and the robot body is adjusted to achieve the target force applied to the robot body.

Exemplarily, if the target direction is a direction parallel to the plane on which the ground is located, the target force in the target direction can be applied to the robot body by adjusting the angle between adjacent joint units in the multi-joint manipulator. For example, by controlling the angle between some adjacent joint units in a multi-joint manipulator arm to increase, it is possible to apply a target force in a target direction to the robot body.

Exemplarily, if the target direction is a direction perpendicular to the plane on which the ground is located, the angle between adjacent joint units in the multi-joint manipulator can be adjusted, and/or the angle between the second joint unit and the robot body, Apply the target force in the target direction to the robot body. For example, by controlling the multi-joint manipulator arm, the angle between some adjacent joint units becomes smaller and the angle between some adjacent joint units becomes larger, so that the target force in the target direction can be applied to the robot body. Or, by controlling the multi-joint manipulator, the angle between some adjacent joint units becomes smaller, the angle between some adjacent joint units becomes larger, and the angle between the second joint unit and the robot body becomes smaller. , To achieve the target force applied to the robot body in the target direction.

Exemplarily, the target direction is the direction perpendicular to the plane of the ground as an example for description. As shown in FIG. 4A, a schematic side view of a robot includes a robot body 31 and a multi-joint robot arm 32. In a sleepy state, the robot body is located on the ground 47. Due to the obstacle 40, the first driving wheel 41 provided on the robot body is in contact with the ground 47, and the second driving wheel 42 is not in contact with the ground 47. The universal wheel 45 is not in contact with the ground 47. The multi-joint robotic arm includes 5 joint units. The direction of action of the first joint unit 43 is perpendicular to the support body. The support body is the ground 47. The second joint unit 44 is connected to the ground 47. The included angle between the robot bodies matches the target direction; position A is the position where the multi-joint manipulator is connected to the robot body, and position D is the determined focus position. Among them, by adjusting the angle between adjacent joint units in the multi-joint manipulator, and the angle between the first joint unit in the multi-joint manipulator and the area where the force point is located, the multi-joint manipulator can be controlled to exert a target effect on the robot body. Force, the target direction corresponding to the target force is a direction perpendicular to the plane on which the ground is located, and a schematic side view of the adjusted robot is shown in Fig. 4B.

Illustrative description, taking the target direction as the direction parallel to the robot body as an example, as shown in FIG. 5A is a schematic side view of a robot. A universal wheel 45 set on the robot body, the robot body is in a trapped state, and the first driving wheel 41 and the second driving wheel set on the robot body are in contact with the ground 47, the multi-joint manipulator includes 4 joint units , The direction of action of the first joint unit 43 is the direction perpendicular to the support body, the support body is the wall 46, the angle between the second joint unit 44 and the robot body 31 matches the target direction; the position A is a multi-joint machine The position where the arm is connected to the robot body, and the position D is the determined force point position. Among them, by adjusting the angle between adjacent joint units in the multi-joint manipulator, and the angle between the first joint unit in the multi-joint manipulator and the area where the force point is located, the multi-joint manipulator can be controlled to exert a target effect on the robot body. Force, the target direction corresponding to the target force is a direction parallel to the robot body, that is, the target direction corresponding to the target force is a direction parallel to the plane of the ground. The side view of the adjusted robot is shown in FIG. 5B.

In a possible implementation, in the case of detecting that the robot body is in a trapped state, determining the position of the force point of the multi-joint manipulator on the support body further includes: In the case of detecting that the robot body is in a trapped state, control the robot body to change the direction of movement and move; Determine the position of the force point of the multi-joint manipulator on the support, including: After detecting that the robot body changes the direction of movement and moves, and does not leave the trapped state, determine the position of the force point of the multi-joint robot arm on the support body.

In the embodiment of the present invention, when it is detected that the robot body is in a trapped state, the robot body can be controlled to change the moving direction and move, so as to make the robot body out of the trapped state. Exemplarily, the transformed movement direction may be detected based on a visual sensor set on the robot body; or, it may also be determined based on the location information of the robot body and a stored map of the application site. Wherein, the manner of determining the moving direction of the robot body after the transformation may be determined according to actual needs, which is not specifically limited in the embodiment of the present invention.

In the specific implementation, after detecting that the robot body has changed the direction of movement and moved, and has not escaped from the trapped state, determine the position of the force point of the multi-joint manipulator on the support, based on the determined position of the force point on the support, Control the end of the multi-joint manipulator arm away from the robot body to contact the support body, and control the multi-joint manipulator arm to apply a target force to the robot body under the support of the support body to make the robot body out of the trapped state, so that it can be in the robot In the case that the traditional way of changing the direction of movement cannot be used to escape the trap, the robot arm is used to assist in the escape, which improves the success rate of the robot.

Take the sweeping robot as an example to explain the method of controlling the robot to escape. During the working process of the sweeping robot, the traveling state of the sweeping robot is detected in real time. When the sweeping robot is detected to be trapped, it can be based on the settings on the sweeping robot. The vision sensor acquires an image of the location of the sweeping robot; judges whether there is a candidate support based on the acquired image, and selects at least one candidate support based on the set priority order and the attribute characteristics of the candidate support Support; after determining the support, determine the position of the force point from the support, and control the multi-joint manipulator to contact the force point on the support; the current after detecting that the multi-joint manipulator touches the force point When the pose information matches the predicted pose information, the target direction corresponding to the sweeping robot is determined, and based on the target direction, the pose information of the multi-joint manipulator is adjusted, and the multi-joint manipulator after the adjusted pose information is controlled to be on the support. Under the support of, apply the target force in the target direction to the main body of the cleaning robot, so that the main body of the cleaning robot is out of the trapped state.

The present invention provides a method for controlling the escape of a robot by detecting the traveling state of the robot body; when detecting that the robot body is in a trapped state, determining the position of the force point of the multi-joint manipulator on the support body; based on the determined support body Control the end of the multi-joint robot arm away from the robot body to contact the support body, and control the multi-joint robot arm to apply a target force to the robot body under the support of the support body to make the robot body out of the trapped state. It can make the robot automatically complete the escape, ensure the normal work of the robot, and improve the working efficiency of the robot.

Those skilled in the art can understand that in the above-mentioned methods of the specific implementation, the writing order of the steps does not mean a strict execution order but constitutes any limitation on the implementation process. The specific execution order of each step should be based on its function and possibility. The inner logic is determined.

Based on the same concept, the embodiment of the present invention also provides a device for controlling the escape of a robot. See FIG. 6, which is a schematic structural diagram of the device for controlling the escape of a robot provided by an embodiment of the present invention, including a state detection module 601 and a focus Point position determination module 602, control module 603, specifically: The state detection module 601 is configured to detect the traveling state of the robot body; The force point position determination module 602 is configured to determine the force point position of the multi-joint manipulator on the support body when it is detected that the robot body is in a trapped state; The control module 603 is configured to control the end of the multi-joint robot arm away from the robot body to contact the support body based on the determined position of the force point on the support body, and control the multi-joint robot arm to contact the support body at the support body. Under the support of the body, a target force is applied to the robot body to release the robot body from the trapped state.

In a possible implementation manner, the device further includes: The candidate support detection module is configured to detect at least one candidate support corresponding to the current position of the robot body and/or the attribute of the at least one candidate support based on a sensor provided on the robot body feature; The support body determination module is configured to determine the support body corresponding to the multi-joint robot arm from at least one candidate support body based on the attribute characteristics of each candidate support body and/or the set priority order of the support body; the attribute The feature is used to characterize the softness and hardness of the surface structure of the support.

In a possible implementation manner, the force point position determination module 602 determines the support body corresponding to the multi-joint manipulator from at least one candidate support body according to the following steps: Based on the attribute characteristics of each candidate support and/or the set priority order of the support, select an unselected candidate support from at least one candidate support; The determination is based on the position of the force point on the candidate support and the position of the end of the multi-joint manipulator arm away from the robot body, and it is determined that the end of the multi-joint manipulator arm away from the robot body reaches the position of the force point , The predicted pose information of the multi-joint manipulator; After controlling the end of the multi-joint robot arm away from the robot body to move to the position of the focus point, detecting the current pose information of the multi-joint robot arm; In the case that the current pose information does not match the predicted pose information, return to the step of selecting an unselected candidate support from at least one candidate support until the current position of the multi-joint robot arm The pose information matches the predicted pose information, or until there is no unselected candidate support among the at least one candidate support.

In a possible implementation manner, the force point position determination module 602 uses the following steps to determine the force point position of the multi-joint manipulator on the support: Divide the area corresponding to the detected support into multiple sub-areas, and determine the center point of each sub-area in the multiple sub-areas; The focus point of the multi-joint manipulator is selected from the center points of the multiple sub-regions.

In a possible implementation manner, the force point position determination module 602 uses the following steps to select the force point of the multi-joint manipulator from the center points corresponding to the multiple sub-regions: Based on the direction and distance between each center point and the end of the multi-joint robot arm approaching the robot body, the focus point of the multi-joint robot arm is selected from the center points of the multiple sub-regions.

In a possible implementation manner, the control module 603 uses the following steps to control the end of the multi-joint manipulator away from the robot body to contact the support body: Determining the movement path of the multi-joint robot arm based on the position of the focus point and the current position of the end of the multi-joint robot arm away from the robot body; The multi-joint robot arm is controlled to move according to the movement path until the end of the multi-joint robot arm away from the robot body contacts the support body.

In a possible implementation manner, the control module 603 uses the following steps to apply a target force to the robot body: Determine the target direction that causes the robot body to escape from the trapped state; The multi-joint manipulator is controlled to apply the target force in the target direction to the robot body under the support of the support body, so that the robot body is out of the trapped state.

In a possible implementation manner, the control module 603 uses the following steps to determine the target direction for the robot body to leave the trapped state: Based on the pose data of the robot body, a target direction for the robot body to leave the trapped state is determined.

In a possible implementation manner, the control module 603 uses the following steps to determine a target direction for the robot body to leave the trapped state based on the pose data of the robot body: Determining the state of at least one wheel provided on the robot body based on the pose data of the robot body; Based on the state of the at least one wheel, a target direction for causing the robot body to leave the trapped state is determined.

In a possible implementation manner, the control module 603 uses the following steps to determine the target direction for the robot body to leave the trapped state: Selecting a currently unselected direction from a plurality of preset directions as the target direction; Controlling the multi-joint manipulator arm to apply the target force in the target direction to the robot body, and detecting the state of the robot body; In the case that the robot body is not out of the trapped state, return to the step of selecting a currently unselected direction from the preset multiple directions as the target direction, until the robot body leaves the trapped state , Or until there is no unselected direction among the preset multiple directions.

In a possible implementation manner, the joint unit far from the robot body in the multi-joint manipulator is the first joint unit, and the joint unit close to the robot body is the second joint unit; Before controlling the multi-joint mechanical arm to apply a target force to the robot body, the device further includes: The first adjustment module is configured to adjust the pose information of each joint unit in the multi-joint manipulator based on the target direction, so that the adjusted angle between the second joint unit and the robot body is , Which matches the target direction; Alternatively, the second adjustment module is configured to adjust the pose information of each joint unit in the robotic arm based on the target direction and the action direction of the first joint unit, so that the adjusted second joint The angle between the unit and the robot body matches the target direction; and the adjusted angle between the first joint unit and the area where the force point is located is the same as the first joint unit Match the direction of action.

In a possible implementation manner, the control module 603 uses the following steps to control the multi-joint manipulator to apply a target force to the robot body: By adjusting at least one of the following included angles, the multi-joint manipulator arm is controlled to apply a target force to the robot body: The included angle between adjacent joint units in the multi-joint manipulator; The included angle between the first joint unit in the multi-joint manipulator and the area where the focus point is located; The included angle between the second joint unit and the robot body.

In a possible implementation manner, the module for determining the position of the focus point includes: The moving direction changing unit is configured to control the robot body to change the moving direction to move when it is detected that the robot body is in a trapped state; The force point position determination module uses the following steps to determine the force point position of the multi-joint robot arm on the support body: After detecting that the robot body changes the direction of movement and moves, and does not leave the trapped state, determine the position of the force point of the multi-joint robot arm on the support body.

In some embodiments, the functions or templates contained in the device provided in the embodiments of the present invention can be used to execute the methods described in the above method embodiments. For specific implementation, refer to the description of the above method embodiments. For brevity, here No longer.

Based on the same concept, an embodiment of the present invention also provides a robot. See FIG. 7, which is a schematic diagram of the architecture of a robot provided by an embodiment of the present invention. The robot includes a multi-joint manipulator 701 and a robot body 702. It is movably connected with the robot body 702. The robot body 702 is provided with a controller 7022. The controller 7022 controls the multi-joint robot arm by sending a control signal to the steering gear set in each joint unit of the multi-joint robot arm. 7022 is configured to execute the method for controlling the escape of a robot described in the above method embodiment. For specific implementation, please refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

Based on the same technical concept, the embodiment of the present invention also provides an electronic device. Referring to FIG. 8, it is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, which includes a processor 801, a memory 802, and a bus 803. Among them, the memory 802 is configured to store execution instructions, including internal memory 8021 and external memory 8022; the internal memory 8021 here is configured to temporarily store calculation data in the processor 801, as well as external memory 8022 such as a hard disk. For data exchanged, the processor 801 exchanges data with the external memory 8022 through the internal memory 8021. When the electronic device 800 is running, the processor 801 and the memory 802 communicate through the bus 803, so that the processor 801 performs the following instruction: Detect the traveling state of the robot body; In the case of detecting that the robot body is in a trapped state, determine the position of the force point of the multi-joint robot arm on the support body; Based on the determined position of the force point on the support body, the end of the multi-joint robot arm away from the robot body is controlled to contact the support body, and the multi-joint robot arm is controlled to contact the support body under the support of the support body. The robot body applies a target force to release the robot body from the trapped state.

In a possible design, the instructions executed by the processor 801 further include: Detecting at least one candidate support corresponding to the current position of the robot body and/or the attribute characteristics of the at least one candidate support based on a sensor provided on the robot body; Based on the attribute characteristics of each candidate support body and the set priority order, determine the support body corresponding to the multi-joint manipulator from at least one candidate support body; the attribute characteristics are used to characterize the surface structure of the support body The characteristics of the degree of softness and hardness.

In a possible design, the instructions executed by the processor 801 further include: Based on the attribute characteristics of each candidate support and/or the set priority order of the support, select an unselected candidate support from at least one candidate support; The determination is based on the position of the force point on the candidate support and the position of the end of the multi-joint manipulator arm away from the robot body, and it is determined that the end of the multi-joint manipulator arm away from the robot body reaches the position of the force point , The predicted pose information of the multi-joint manipulator; Controlling the end of the multi-joint robot arm away from the robot body to move to the position of the focus point, and detecting the current pose information of the multi-joint robot arm; In the case that the current pose information does not match the predicted pose information, return to the step of selecting an unselected candidate support from at least one candidate support until the current position of the multi-joint robot arm The pose information matches the predicted pose information, or until there is no unselected candidate support among the at least one candidate support.

In a possible design, the instructions executed by the processor 801 further include: Divide the area corresponding to the detected support into multiple sub-areas, and determine the center point of each sub-area in the multiple sub-areas; The focus point of the multi-joint manipulator is selected from the center points of the multiple sub-regions.

In a possible design, the instructions executed by the processor 801 further include: Based on the direction and distance between each center point and the end of the multi-joint robot arm approaching the robot body, the focus point of the multi-joint robot arm is selected from the center points of the plurality of sub-regions.

In a possible design, the instructions executed by the processor 801 further include: Determining the movement path of the multi-joint robot arm based on the position of the focus point and the current position of the end of the multi-joint robot arm away from the robot body; The multi-joint robot arm is controlled to move according to the movement path until the end of the multi-joint robot arm away from the robot body contacts the support body.

In a possible design, the instructions executed by the processor 801 further include: Determine the target direction that causes the robot body to escape from the trapped state; The multi-joint manipulator is controlled to apply the target force in the target direction to the robot body under the support of the support body, so that the robot body is out of the trapped state.

In a possible design, the instructions executed by the processor 801 further include: Based on the pose data of the robot body, a target direction for the robot body to leave the trapped state is determined.

In a possible design, the instructions executed by the processor 801 further include: Determining the state of at least one wheel provided on the robot body based on the pose data of the robot body; Based on the state of the at least one wheel, a target direction for causing the robot body to leave the trapped state is determined.

In a possible design, the instructions executed by the processor 801 further include: Selecting a currently unselected direction from a plurality of preset directions as the target direction; Controlling the multi-joint manipulator arm to apply the target force in the target direction to the robot body, and detecting the state of the robot body; In the case that the robot body is not out of the trapped state, return to the step of selecting a currently unselected direction from the preset multiple directions as the target direction, until the robot body leaves the trapped state, Or until there is no unselected direction among the preset multiple directions.

In a possible design, the instructions executed by the processor 801 further include: In the multi-joint manipulator arm, a joint unit far from the robot body is a first joint unit, and a joint unit close to the robot body is a second joint unit; Before controlling the multi-joint manipulator to apply a target force to the robot body, the method further includes: Based on the target direction, adjust the pose information of each joint unit in the multi-joint manipulator so that the adjusted angle between the second joint unit and the robot body matches the target direction ； Or, based on the target direction and the direction of action of the first joint unit, adjust the pose information of each joint unit in the robotic arm so that the adjusted second joint unit is between the robot body The included angle of is matched with the target direction; and the adjusted included angle between the first joint unit and the area where the force point position is located matches the direction of action of the first joint unit.

In a possible design, the instructions executed by the processor 801 further include: By adjusting at least one of the following included angles, the multi-joint manipulator arm is controlled to apply a target force to the robot body: The included angle between adjacent joint units in the multi-joint manipulator; The included angle between the first joint unit in the multi-joint manipulator and the area where the focus point is located; The included angle between the second joint unit and the robot body.

In a possible design, the instructions executed by the processor 801 further include: In the case of detecting that the robot body is in a trapped state, controlling the robot body to change the direction of movement and move; The determining the position of the force point of the multi-joint mechanical arm on the support includes: After detecting that the robot body changes the direction of movement and moves, and does not leave the trapped state, the position of the force point of the multi-joint manipulator on the support body is determined.

In addition, an embodiment of the present invention also provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium. step.

The computer program product of the method for controlling the escape of a robot provided by the embodiment of the present invention includes a program code, and the instructions included in the program code can be used to execute the steps of the method for controlling the escape of a robot described in the above method embodiment. For details, see The above method embodiments will not be repeated here.

Those skilled in the art can clearly understand that, for the convenience and conciseness of the description, the specific working process of the system and device described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here. In the several embodiments provided by the present invention, it should be understood that the disclosed system, device, and method can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other divisions in actual implementation. For example, multiple units or elements may be combined or may be Integrate into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some communication interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. . Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.

If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a volatile or non-volatile computer-readable storage medium executable by a processor. Based on this understanding, the technical solution of the present invention essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several The instructions are used to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage media include: U disk, removable hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disks or optical disks, etc., which can store program codes Medium.

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, and they shall be covered Within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the patent application.

21~23: Ray 31: Robot body 32: Multi-joint robotic arm 40: Obstacles 41: first drive wheel 42: second drive wheel 43: second drive wheel 44: Second joint unit 45: universal wheel 46: Wall 47: Ground 301~304: Ray 601: Status detection module 602: Focusing point position determination module 603: Control Module 701: Multi-joint robotic arm 702: Robot body 7022: Controller 800: electronic equipment 801: processor 802: memory 8021: internal memory 8022: External memory 803: Bus A~D: location S101~S103: steps

In order to more clearly describe the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings needed in the embodiments. The drawings here are incorporated into the specification and constitute a part of the specification. These attachments The figure shows an embodiment in accordance with the present invention, and is used together with the description to explain the technical solution of the present invention. It should be understood that the following drawings only show certain embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, they can also Obtain other related drawings based on these drawings. FIG. 1 shows a schematic flowchart of a method for controlling a robot to escape from a trap provided by an embodiment of the present invention; Figure 2 shows a schematic diagram of the upper surface of a robot body provided by an embodiment of the present invention; Figure 3 shows a schematic side view of a robot body provided by an embodiment of the present invention; Fig. 4A shows a schematic side view of a robot provided by an embodiment of the present invention; 4B shows a schematic side view of another robot provided by an embodiment of the present invention; Fig. 5A shows a schematic side view of a robot provided by an embodiment of the present invention; Figure 5B shows a schematic side view of another robot provided by an embodiment of the present invention; Fig. 6 shows a schematic structural diagram of a device for controlling a robot to escape from a trap provided by an embodiment of the present invention; FIG. 7 shows a schematic diagram of the architecture of a robot provided by an embodiment of the present invention; FIG. 8 shows a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

S101~S103: steps

Claims (16)

A method for controlling the escape of a robot, wherein the robot includes a multi-joint manipulator and a robot body, and the method includes: Detect the traveling state of the robot body; In the case of detecting that the robot body is in a trapped state, determine the position of the force point of the multi-joint robot arm on the support body; Based on the determined position of the force point on the support body, the end of the multi-joint robot arm away from the robot body is controlled to contact the support body, and the multi-joint robot arm is controlled to contact the support body under the support of the support body. The robot body applies a target force to release the robot body from the trapped state. The method according to claim 1, wherein, before the determining the position of the force point of the multi-joint robot arm on the support body, the method includes: Detecting at least one candidate support corresponding to the current position of the robot body and/or the attribute characteristics of the at least one candidate support based on a sensor provided on the robot body; Based on the attribute characteristics of each candidate support body and/or the priority order of the support bodies set, determine the support body corresponding to the multi-joint manipulator from at least one candidate support body; the attribute characteristics are used to characterize the support body The softness and hardness of the surface structure. The method according to claim 2, wherein the support corresponding to the multi-joint manipulator is determined from at least one candidate support based on the attribute characteristics of each candidate support and/or the priority order of the support set Body, including: Based on the attribute characteristics of each candidate support and/or the set priority order of the support, select an unselected candidate support from at least one candidate support; The determination is based on the position of the force point on the candidate support and the position of the end of the multi-joint manipulator arm away from the robot body, and it is determined that the end of the multi-joint manipulator arm away from the robot body reaches the position of the force point , The predicted pose information of the multi-joint manipulator; Controlling the end of the multi-joint robot arm away from the robot body to move to the position of the focus point, and detecting the current pose information of the multi-joint robot arm; In the case that the current pose information does not match the predicted pose information, return to the step of selecting an unselected candidate support from at least one candidate support until the current position of the multi-joint robot arm The pose information matches the predicted pose information, or until there is no unselected candidate support among the at least one candidate support. The method according to any one of claims 1 to 3, wherein the determining the position of the force point of the multi-joint manipulator on the support includes: Divide the area corresponding to the detected support into multiple sub-areas, and determine the center point of each sub-area in the multiple sub-areas; The focus point of the multi-joint manipulator is selected from the center points of the multiple sub-regions. The method according to claim 4, wherein the selecting the focus point of the multi-joint manipulator from the center points corresponding to the multiple sub-regions includes: Based on the direction and distance between each center point and the end of the multi-joint robot arm approaching the robot body, the focus point of the multi-joint robot arm is selected from the center points of the plurality of sub-regions. The method according to any one of claims 1 to 3, wherein the controlling the end of the multi-joint manipulator away from the robot body to contact the support body based on the determined position of the force point on the support body includes : Determining the movement path of the multi-joint robot arm based on the position of the focus point and the current position of the end of the multi-joint robot arm away from the robot body; The multi-joint robot arm is controlled to move according to the movement path until the end of the multi-joint robot arm away from the robot body contacts the support body. The method according to any one of claims 1 to 3, wherein the control of the multi-joint manipulator is supported by the support body to apply a target force to the robot body, so that the robot body Get out of the trapped state, including: Determine the target direction that causes the robot body to escape from the trapped state; The multi-joint manipulator is controlled to apply the target force in the target direction to the robot body under the support of the support body, so that the robot body is out of the trapped state. The method according to claim 7, wherein the determining the target direction that causes the robot body to escape from the trapped state includes: Based on the pose data of the robot body, a target direction for the robot body to leave the trapped state is determined. The method according to claim 8, wherein the determining, based on the pose data of the robot body, a target direction that causes the robot body to leave the trapped state includes: Determining the state of at least one wheel provided on the robot body based on the pose data of the robot body; Based on the state of the at least one wheel, a target direction for causing the robot body to leave the trapped state is determined. The method according to claim 7, wherein the determining the target direction that causes the robot body to escape from the trapped state includes: Selecting a currently unselected direction from a plurality of preset directions as the target direction; Controlling the multi-joint manipulator arm to apply the target force in the target direction to the robot body, and detecting the state of the robot body; In the case that the robot body is not out of the trapped state, return to the step of selecting a currently unselected direction from the preset multiple directions as the target direction, until the robot body leaves the trapped state , Or until there is no unselected direction among the preset multiple directions. The method according to any one of claims 1 to 3, wherein the joint unit far from the robot body in the multi-joint manipulator is a first joint unit, and the joint unit close to the robot body is a second joint unit ； Before controlling the multi-joint manipulator to apply a target force to the robot body, the method further includes: Based on the target direction, adjust the pose information of each joint unit in the multi-joint manipulator so that the adjusted angle between the second joint unit and the robot body matches the target direction ； Or, based on the target direction and the direction of action of the first joint unit, adjust the pose information of each joint unit in the robotic arm so that the adjusted second joint unit is between the robot body The included angle of is matched with the target direction; and the adjusted included angle between the first joint unit and the area where the force point position is located matches the direction of action of the first joint unit. The method according to claim 11, wherein the controlling the multi-joint manipulator to apply a target force to the robot body includes: By adjusting at least one of the following included angles, the multi-joint manipulator arm is controlled to apply a target force to the robot body: The included angle between adjacent joint units in the multi-joint manipulator; The included angle between the first joint unit in the multi-joint manipulator and the area where the focus point is located; The included angle between the second joint unit and the robot body. The method according to any one of claims 1 to 3, wherein, in the case of detecting that the robot body is in a trapped state, determining the position of the force point of the multi-joint manipulator on the support body, and include: In the case of detecting that the robot body is in a trapped state, controlling the robot body to change the direction of movement and move; The determining the position of the force point of the multi-joint mechanical arm on the support includes: After detecting that the robot body changes the direction of movement and moves, and does not leave the trapped state, the position of the force point of the multi-joint manipulator on the support body is determined. A robot, wherein the robot includes a multi-joint manipulator arm and a robot body, the multi-joint manipulator arm is movably connected to the robot body, and a controller is provided in the robot body, and the controller passes to the multi-joint manipulator. The steering gear provided in each joint unit of the articulated manipulator sends a control signal to control the multi-joint manipulator to execute the method for controlling the robot to get out of trouble according to any one of the request items 1 to 13. An electronic device, comprising: a processor and a memory connected to each other, the memory storing machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are used by the processor During execution, the steps of the method for controlling the robot to get out of trouble as described in any one of the claim items 1 to 13 are executed. A computer-readable storage medium has a computer program stored on the computer-readable storage medium, and when the computer program is run by a processor, it executes the steps of the method for controlling a robot to escape from sleep according to any one of claim items 1 to 13.

Images