WO2019080679A1 - Method and device for constructing structure map for mobile robot - Google Patents

Abstract

A method and device for constructing a structure map for a mobile robot. The method for constructing a structure map for a mobile robot comprises: obtaining sampling poses of a mobile robot (S11); generating nodes corresponding to the sampling poses in a map, based on the sampling poses (S12); and constructing a structure map, based on a connection relationship among the nodes (S13). The structure map constructed by using the method is more convenient for path planning.

Description

Method and device for constructing structural map of mobile robot Technical field

The present application relates to the field of computer technology, and in particular, to a technology for constructing a structure map of a mobile robot.

Background technique

At present, the use of mobile robots is more and more common, mainly including home service classes and shopping malls, and the construction of surrounding environment maps is the key to realizing mobile services. The existence and real situation of existing mobile robots Inconsistent problems, and the path planning is not convenient.

Summary of the invention

It is an object of the present application to provide a method and apparatus for a mobile robot to construct a structural map.

According to an aspect of the present application, a method for a mobile robot to construct a structure map is provided, wherein the method includes:

Obtaining the sampling pose of the mobile robot;

Generating a node corresponding to the sampled pose on the map based on the sampled pose;

A structural map is constructed based on the interconnection relationship between the nodes.

Further, wherein the constructing the structure map based on the interconnection relationship between the nodes comprises:

Detecting whether there is an interconnection relationship between the nodes, wherein the interconnection relationship refers to that the mobile robot performs linear motion between the nodes without blocking of an obstacle;

When the interconnection relationship exists, the interconnection relationship between the node and other nodes is stored in each node;

A structure map is constructed based on the interconnection relationship.

Further, the method further includes:

Obtaining a current pose and a target pose of the mobile robot;

And determining an optimal path to the target pose according to the current pose and the positional relationship between the target pose and the node on the structure map.

Further, the determining, according to the current pose and the positional relationship between the target pose and the node on the structure map, determining an optimal path to the target pose includes:

Determining a corresponding current node and a destination node on the structure map according to the current pose and the target pose;

Determining an optimal path to the target pose according to the interconnection relationship between the nodes on the structure map.

Further, wherein the acquiring the sample pose of the mobile robot comprises:

Obtaining a sampling pose of the mobile robot when the preset condition is met;

The preset condition includes at least one of the following:

The preset sampling time interval is reached;

The preset sampling distance threshold is reached.

According to another aspect of the present application, there is also provided an apparatus for a mobile robot to construct a structure map, wherein the apparatus comprises:

a first device, configured to acquire a sampling pose of the mobile robot;

a second device, configured to generate, on the map, a node corresponding to the sampled pose based on the sampled pose;

And a third device, configured to construct a structural map based on the interconnection relationship between the nodes.

Further, wherein the third device comprises:

a first unit, configured to detect whether there is an interconnection relationship between the nodes, where the interconnection relationship refers to that the mobile robot performs linear motion between the nodes without obstruction of an obstacle;

a second unit, configured to store, in each node, an interconnection relationship between the node and other nodes when the interconnection relationship exists;

The third unit is configured to construct a structure map based on the interconnection relationship.

Further, wherein the fifth device is used to:

Determining a corresponding current node and a destination node on the structure map according to the current pose and the target pose;

An optimal path to the target pose is determined according to the interconnection relationship between the nodes on the structure map.

Further, wherein the first device is used to:

Obtaining a sampling pose of the mobile robot when the preset condition is met;

The preset condition includes at least one of the following:

The preset sampling time interval is reached;

The preset sampling distance threshold is reached.

Compared with the prior art, the present application generates a sampling pose of a mobile robot, and then generates a node corresponding to the sampled pose on the map based on the sampled pose, and further based on the interconnection relationship between the nodes. Build a structure map. Structured maps constructed this way can be more easily used for path planning.

DRAWINGS

Other features, objects, and advantages of the present invention will become more apparent from the Detailed Description of Description

1 shows a flow chart of a method for a mobile robot to construct a structure map in accordance with an aspect of the present application;

2 is a schematic diagram showing a mobile robot construction structure map according to a preferred embodiment of the present application;

3 shows a schematic diagram of a path planning for a mobile robot in accordance with a preferred embodiment of the present application;

4 shows a schematic diagram of an apparatus for a mobile robot building structure map in accordance with another aspect of the present application.

The same or similar reference numerals in the drawings denote the same or similar components.

Detailed ways

The invention is further described in detail below with reference to the accompanying drawings.

In a typical configuration of the present application, the terminal, the device of the service network, and the trusted party each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory, such as read only memory (ROM) or flash memory (flashRAM), in a computer readable medium. Memory is an example of a computer readable medium.

Computer readable media includes both permanent and non-persistent, removable and non-removable media. Information storage can be implemented by any method or technology. The information can be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, A magnetic tape cartridge, magnetic tape storage or other magnetic storage device or any other non-transportable medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media, such as modulated data signals and carrier waves.

The technical solutions of the present application will be clearly and completely described in the following with reference to the accompanying drawings and preferred embodiments.

1 illustrates a method for a mobile robot to construct a structure map, in accordance with an aspect of the present application, wherein the method includes:

S11 obtains a sampling pose of the mobile robot;

S12: generating, according to the sampled pose, a node corresponding to the sampled pose on a map;

S13 constructs a structure map based on the interconnection relationship between the nodes.

In this embodiment, in the step S11, the sampling pose of the mobile robot is acquired, where the pose is used to represent the position information of the mobile robot, and the sample pose is in the motion process of the mobile robot. In this way, the pose of the mobile robot is sampled, and in this way, a large number of sample poses of the mobile robot during the motion can be acquired, so as to form a basis for constructing the structure map.

Preferably, wherein the S11 comprises: acquiring a sampling pose of the mobile robot when a preset condition is met. Here, the preset condition includes at least one of the following: reaching a preset sampling time interval; reaching a preset sampling distance threshold.

That is, during the movement of the mobile robot, a sampling time interval may be set. After the sampling time interval is reached, the posture of the mobile robot is sampled to obtain a sampling pose, or a sampling distance threshold may be set, that is, After the mobile robot moves the preset distance, the pose of the mobile robot is sampled to obtain a sample pose. Here, the preset condition is only an example, and other existing or future preset conditions may be included in the scope of protection of the present application, and are hereby incorporated by reference. this.

Continuing in this embodiment, in the step S12, the node corresponding to the sample pose is generated on the map based on the sample pose. In this embodiment, after the sampling pose is acquired, the node corresponding to the sampled pose is generated on the map corresponding to the sampled pose, that is, there are many nodes on the structure map for corresponding to the mobile robot. The sampling pose generated during the movement can visually present the corresponding sampling pose on the map, which is convenient for path planning.

Continuing in this embodiment, in the step S13, a structure map is constructed based on the interconnection relationship between the nodes. Here, the interconnection relationship is used to indicate that nodes can be reached through a certain path, that is, if two nodes can be reached through a certain path, then there is an interconnection relationship between the two nodes. Thus, the certain path represents a path that can be reached directly or indirectly, in such a way as to form a map structure similar to a mesh.

Preferably, the step S13 includes: S131 (not shown) detecting whether there is an interconnection relationship between the nodes, wherein the interconnection relationship refers to the mobile robot performing a straight line between the nodes There is no obstacle blocking of the motion; S132 (not shown) stores the interconnection relationship between the node and other nodes in each node when the interconnection relationship exists; S133 (not shown) is based on the mutual Connect relationships and build structural maps.

In this embodiment, in the step S131, it is detected whether the nodes can directly arrive, that is, whether the nodes are free from obstacles between the nodes, and can be directly reached. Specifically, the map can be advanced in advance. The obstacles are identified, and then the nodes are connected by two or two. When the obstacles are not passed, it is determined that the two nodes have a mutual connection relationship.

Continuing in this embodiment, in the step S132, when the interconnection relationship exists, the interconnection relationship between the node and other nodes is stored in each node, for example, there are three nodes, and when the node 1 can If you reach node 2 and node 3 directly, node 2 and node 3 will be stored at node 1. Correspondingly, node 2 and node 3 will also store node 1. That is, this way stores the neighbor nodes of the node at each node to form a set of neighbor nodes.

Continuing in this embodiment, in the step S133, a structure map is constructed based on the interconnection relationship.

2, a preferred embodiment of a mobile robot building structure map is shown, in which, as shown, a corresponding node is first generated in the map by pose sampling, in this embodiment A is listed. , B, C, D, E five nodes, wherein there is a mutual connection between the A node and the B node, which can be directly reached, and there is a mutual connection between the C node and the B node, the D node, and the E node, and the D node There is an interconnection relationship with the E node, and the nodes having the interconnection relationship are connected to form a structure map as shown in FIG. 2. Among them, other nodes in which the interconnection relationship exists are stored correspondingly at each node.

Preferably, the method further includes: S14 (not shown) acquiring a current pose and a target pose of the mobile robot; S15 (not shown) according to the current pose and the target pose The positional relationship of the nodes on the structure map determines an optimal path to the target pose.

In this embodiment, after the structural map is constructed, the mobile robot can perform path planning according to the structural map. In the step S14, the current pose and the target pose of the mobile robot are acquired, so as to perform path planning according to the current pose and the target pose.

Continuing in this embodiment, in the step S15, the current pose and the target pose are mapped to corresponding positions in the structure map, and according to the position and the position of the node on the structure map. Relationship, determining the optimal path to the target pose.

Preferably, the step S15 includes: determining a corresponding current node and a destination node on the structure map according to the current pose and the target pose; and interconnecting nodes according to the structure map Relationship, determining the optimal path to the target pose.

If the current pose and the target pose correspond to the position of the node in the structure map, determine that the node where the current pose is located is the current node, and the node corresponding to the target pose is the destination node, and then according to each The connection relationship between the nodes determines the optimal path, for example, searching for the qualified path in the structure map by the shortest path search algorithm.

For example, in the map shown in FIG. 2, if the current pose is at the B node and the destination pose is at the E node, since the path from the Node B to the E node is: BCE and BCDE, it is possible to select For short paths, go to the C node and then to the E node.

In another embodiment, when the current pose and the target pose do not exactly correspond to the node position in the structure map, the current pose and the target pose are mapped to the node closest to them. Then, the optimal path is selected. As shown in FIG. 3, the current pose is closer to the node D, and the destination pose is closer to the node B, then the current node is determined to be the node D, and the destination node is the node B. The mobile robot can be controlled to correspond to the node D first, and the destination pose first corresponds to the node B, and then the optimal path is selected, for example, first to the node D and then to the node C, and then to the node B. Purpose pose.

Compared with the prior art, the present application generates a sampling pose of a mobile robot, and then generates a node corresponding to the sampled pose on the map based on the sampled pose, and further based on the interconnection relationship between the nodes. Build a structure map. Structured maps constructed this way can be more easily used for path planning.

4 shows an apparatus 1 for a mobile robot building structure map according to another aspect of the present application, wherein the apparatus 1 comprises:

a first device, configured to acquire a sampling pose of the mobile robot;

a second device, configured to generate, on the map, a node corresponding to the sampled pose based on the sampled pose;

And a third device, configured to construct a structural map based on the interconnection relationship between the nodes.

In this embodiment, the first device of the device 1 acquires a sampling pose of the mobile robot, where the pose is used to represent position information of the mobile robot, and the sample pose is motion of the mobile robot In the process, the pose of the mobile robot is sampled, and in this way, a large number of sample poses of the mobile robot during the motion can be acquired, so as to form a basis for constructing the structure map. Here, the device 1 comprises a device that controls the mobile robot or the mobile robot itself.

Preferably, wherein the first device is configured to acquire a sampling pose of the mobile robot when the preset condition is met. Here, the preset condition includes at least one of the following: reaching a preset sampling time interval; reaching a preset sampling distance threshold.

That is, during the movement of the mobile robot, a sampling time interval may be set. After the sampling time interval is reached, the first device samples the posture of the mobile robot to obtain a sampling pose, or may also set a sampling distance. The threshold, that is, after the mobile robot moves a preset distance, samples the pose of the mobile robot to obtain a sample pose. Here, the preset condition is only an example, and other existing or future preset conditions may be included in the scope of protection of the present application, and are hereby incorporated by reference. this.

Continuing in this embodiment, the second device generates a node corresponding to the sample pose based on the sample pose based on the sample pose. In this embodiment, after acquiring the sampled pose, the first device generates a node corresponding to the sampled pose in a position corresponding to the sampled pose on the map, that is, there are many nodes on the structure map. It is used to correspond to the sampling pose generated by the mobile robot during the movement process, so that the corresponding sampling pose can be visually presented on the map, which is convenient for path planning.

Continuing in this embodiment, the third device constructs a structural map based on the interconnection relationship between the nodes. Here, the interconnection relationship is used to indicate that nodes can be reached through a certain path, that is, if two nodes can be reached through a certain path, then there is an interconnection relationship between the two nodes. Thus, the certain path represents a path that can be reached directly or indirectly, in such a way as to form a map structure similar to a mesh.

Preferably, wherein the third device comprises: a first unit (not shown) for detecting whether there is an interconnection relationship between the nodes, wherein the interconnection relationship refers to the mobile robot in the The linear motion between the nodes does not block the obstacle; the second unit (not shown) is used to store the interconnection relationship between the node and other nodes in each node when the interconnection relationship exists. a third unit (not shown) for constructing a structural map based on the interconnection relationship.

In this embodiment, the first unit of the third device detects whether the nodes can reach directly, that is, whether the nodes are free from obstacles between the nodes, and can arrive directly, specifically, in the map. The obstacles can be identified in advance, and then the nodes are connected in pairs. When the obstacles are not passed, it is determined that the two nodes have a mutual connection relationship.

Continuing in this embodiment, the second unit stores the interconnection relationship between the node and other nodes in each node when there is the interconnection relationship, for example, there are three nodes, and when the node 1 can directly reach Nodes 2 and 3 will store nodes 2 and 3 at node 1, and correspondingly nodes 2 and 3 will also store node 1. That is, this way stores the neighbor nodes of the node at each node to form a set of neighbor nodes.

Continuing in this embodiment, the third unit constructs a structural map based on the interconnection relationship.

2, a preferred embodiment of a mobile robot building structure map is shown, in which, as shown, a corresponding node is first generated in the map by pose sampling, in this embodiment A is listed. , B, C, D, E five nodes, wherein there is a mutual connection between the A node and the B node, which can be directly reached, and there is a mutual connection between the C node and the B node, the D node, and the E node, and the D node There is an interconnection relationship with the E node, and the nodes having the interconnection relationship are connected to form a structure map as shown in FIG. 2. Among them, other nodes in which the interconnection relationship exists are stored correspondingly at each node.

Preferably, the method further includes: a fourth device (not shown) for acquiring a current pose and a target pose of the mobile robot; and a fifth device (not shown) for The current pose and the positional relationship between the target pose and the nodes on the structure map determine an optimal path to the target pose.

In this embodiment, after the structural map is constructed, the mobile robot can perform path planning according to the structural map. The fourth device acquires a current pose and a target pose of the mobile robot, so as to perform path planning according to the current pose and the target pose.

Continuing in this embodiment, the fifth device maps the current pose and the target pose to corresponding positions in the structure map, and according to the positional relationship with the node on the structure map, Determine the optimal path to the target pose.

Preferably, the fifth device is configured to: determine, according to the current pose and the target pose, a corresponding current node and a destination node on the structure map; according to the structure between the nodes on the map The interconnection relationship determines an optimal path to the target pose.

If the current pose and the target pose correspond to the position of the node in the structure map, determine that the node where the current pose is located is the current node, and the node corresponding to the target pose is the destination node, and then according to each The connection relationship between the nodes determines the optimal path, for example, searching for the qualified path in the structure map by the shortest path search algorithm.

For example, in the map shown in FIG. 2, if the current pose is at the B node and the destination pose is at the E node, since the path from the Node B to the E node is: BCE and BCDE, it is possible to select For short paths, go to the C node and then to the E node.

In another embodiment, when the current pose and the target pose do not exactly correspond to the node position in the structure map, the current pose and the target pose are mapped to the node closest to them. Then, the optimal path is selected. As shown in FIG. 3, the current pose is closer to the node D, and the destination pose is closer to the node B, then the current node is determined to be the node D, and the destination node is the node B. The mobile robot can be controlled to correspond to the node D first, and the destination pose first corresponds to the node B, and then the optimal path is selected, for example, first to the node D and then to the node C, and then to the node B. Purpose pose.

Compared with the prior art, the present application generates a sampling pose of a mobile robot, and then generates a node corresponding to the sampled pose on the map based on the sampled pose, and further based on the interconnection relationship between the nodes. Build a structure map. Structured maps constructed this way can be more easily used for path planning.

It is apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the invention is defined by the appended claims instead All changes in the meaning and scope of equivalent elements are included in the present invention. Any reference signs in the claims should not be construed as limiting the claim. In addition, it is to be understood that the word "comprising" does not exclude other elements or steps. A plurality of units or devices recited in the device claims may also be implemented by a unit or device by software or hardware. The first, second, etc. words are used to denote names and do not denote any particular order.

Claims (10)

A method for a mobile robot to construct a structural map, wherein the method comprises: Obtaining the sampling pose of the mobile robot; Generating a node corresponding to the sampled pose on the map based on the sampled pose; A structural map is constructed based on the interconnection relationship between the nodes. The method of claim 1, wherein the constructing the structure map based on the interconnection relationship between the nodes comprises: Detecting whether there is an interconnection relationship between the nodes, wherein the interconnection relationship refers to that the mobile robot performs linear motion between the nodes without blocking of an obstacle; When the interconnection relationship exists, the interconnection relationship between the node and other nodes is stored in each node; A structure map is constructed based on the interconnection relationship. The method of claim 1 or 2, wherein the method further comprises: Obtaining a current pose and a target pose of the mobile robot; And determining an optimal path to the target pose according to the current pose and the positional relationship between the target pose and the node on the structure map. The method according to claim 3, wherein the determining the optimal path to the target pose according to the current pose and the positional relationship between the target pose and the node on the structure map comprises: Determining a corresponding current node and a destination node on the structure map according to the current pose and the target pose; Determining an optimal path to the target pose according to the interconnection relationship between the nodes on the structure map. The method according to any one of claims 1 to 4, wherein the acquiring the sample pose of the mobile robot comprises: Obtaining a sampling pose of the mobile robot when the preset condition is met; The preset condition includes at least one of the following: The preset sampling time interval is reached; The preset sampling distance threshold is reached. An apparatus for a mobile robot to construct a structural map, wherein the apparatus comprises: a first device, configured to acquire a sampling pose of the mobile robot; a second device, configured to generate, on the map, a node corresponding to the sampled pose based on the sampled pose; And a third device, configured to construct a structural map based on the interconnection relationship between the nodes. The apparatus of claim 6 wherein said third means comprises: a first unit, configured to detect whether there is an interconnection relationship between the nodes, where the interconnection relationship refers to that the mobile robot performs linear motion between the nodes without obstruction of an obstacle; a second unit, configured to store, in each node, an interconnection relationship between the node and other nodes when the interconnection relationship exists; The third unit is configured to construct a structure map based on the interconnection relationship. The device according to claim 6 or 7, wherein the device further comprises: a fourth device, configured to acquire a current pose and a target pose of the mobile robot; And a fifth device, configured to determine an optimal path to the target pose according to the current pose and the positional relationship between the target pose and the node on the structure map. The apparatus of claim 8 wherein said fifth means is for: Determining a corresponding current node and a destination node on the structure map according to the current pose and the target pose; Determining an optimal path to the target pose according to the interconnection relationship between the nodes on the structure map. Apparatus according to any one of claims 6 to 9 wherein said first means is for: Obtaining a sampling pose of the mobile robot when the preset condition is met; The preset condition includes at least one of the following: The preset sampling time interval is reached; The preset sampling distance threshold is reached.

Images