CN108607819A - Material sorting system and method - Google Patents

Abstract

The embodiment of the present invention provides a kind of Material Sorting system and method.The Material Sorting system includes：First imaging sensor and the second imaging sensor, the image data for obtaining the object；The image acquisition device being connect with described first image sensor and second imaging sensor, for acquiring described image data；The processing equipment being connect with described image collector, the processing equipment are used to be calculated the three-dimensional information of the object and the volume of the object according to described image data；The processing equipment is additionally operable to generate the movement instruction of control robot according to the three-dimensional information and volume；The robot being connect with the processing equipment, the robot are used to receive the movement instruction of the processing equipment, to adjust end according to the movement instruction to capture the object.

Description

Material sorting system and method

technical field

The invention relates to the technical field of control, in particular to a material sorting system and method.

Background technique

The current sorting technology uses a series of movements through teaching or offline programming. All actions and positions must be strictly set in advance. Once the working environment conditions change, sorting errors will occur. , low level of intelligence. Therefore, there is a need for a material sorting method capable of more accurately locating materials.

Contents of the invention

In view of this, the purpose of the embodiments of the present invention is to provide a material sorting system and method.

A material sorting system provided in an embodiment of the present invention, the material sorting system includes:

The first image sensor is used to acquire the first image data of the target;

a second image sensor, configured to acquire second image data of the target;

An image collector connected to the first image sensor and the second image sensor, configured to collect first image data obtained by the first image sensor and second image data obtained by the second image sensor;

A processing device connected to the image collector, the processing device is used to obtain the first image data and the second image data from the image collector, and calculate according to the first image data and the second image data Obtaining the three-dimensional information of the target object and the volume of the target object;

The processing device is also used to generate motion instructions for controlling the robot according to the three-dimensional information and volume;

A robot connected to the processing device, the robot is used to receive a motion command from the processing device, so as to adjust the end according to the motion command to grab the target.

The embodiment of the present invention also provides a material sorting method, including:

Acquiring first image data of the target collected by the first collection device and second image data of the target collected by the second collection device;

using the first image data and the second image data to locate the three-dimensional information and volume of the target;

Generate motion instructions for controlling the robot according to the three-dimensional information and volume;

Sending the motion command to the robot, so that the robot adjusts the end according to the motion command to grab the target.

Compared with the prior art, the material sorting system and method of the embodiment of the present invention obtains two image data of the target object, and uses the two image data to calculate the three-dimensional information and volume of the target object, so that the generated motion command can be The robot can be better positioned to the position of the target, thereby reducing the error of the robot grabbing the target.

In order to make the above objects, features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail in conjunction with the accompanying drawings.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and thus It should be regarded as a limitation on the scope, and those skilled in the art can also obtain other related drawings based on these drawings without creative work.

Fig. 1 is a schematic diagram of the operating environment of the material sorting system provided by the embodiment of the present invention.

Fig. 2 is a flowchart of a material sorting method provided by an embodiment of the present invention.

Fig. 3 is a partial flow chart of the material sorting method provided by the embodiment of the present invention.

Fig. 4 is a partial flowchart of the material sorting method provided by the embodiment of the present invention.

Icons: 10-material sorting system; 110-first image sensor; 120-second image sensor; 200-image collector; 300-processing equipment; 400-robot; 500-robot controller; 600-bracket; 610- Cross arm; 620-support arm; 700-conveyor belt; 800-trigger control device.

Detailed ways

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 are only some, not all, embodiments of the present invention. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.

It should be noted that like numerals and letters denote similar items in the following figures, therefore, once an item is defined in one figure, it does not require further definition and explanation in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

For robots working in a structured or unstructured environment, the visual system is very important. Robot visual servoing that combines vision and robot control is an important research direction and a research hotspot for improving the level of robot intelligence. one. In the past, sorting was not equipped with a vision system, and the materials needed to be mechanically positioned during sorting, which was inefficient, long and slow. Therefore, the combination of binocular stereo vision and visual servo control technology of industrial robots plays an important role in improving the real-time guidance of sorting. At present, sorting technology presents a trend of intelligent and high-efficiency development in the logistics industry, palletizing and assembly line operations and other industries. The dynamic guidance method for sorting mixed materials composed of industrial robots and binocular stereo vision has high efficiency and strong environmental adaptability, and can obtain three-dimensional information of materials in real time. On the other hand, using binocular stereo vision for positioning has high efficiency. , The accuracy is appropriate, and it is very suitable for the control of real-time operations. For the positioning of moving objects, the acquisition of images is completed in an instant, and the system can identify materials in a non-contact manner, with broad application prospects. However, in the currently used sorting technology, a series of movements are taught or offline programming. All actions and placements must be strictly set in advance. Once the working environment conditions change, there will be separation Picking mistakes, the level of intelligence is low. The specific possible problems are as follows: 1) Usually, the materials on the conveyor belt are assisted by manual or auxiliary robots. Therefore, three-dimensional space errors will occur when the workpiece is positioned; including translation errors and rotation errors. Therefore, when the robot is performing real-time sorting guidance, it is necessary to correct the posture of the end effector to adapt to the sorting operation. When the size of the material is inconsistent, if the robot’s terminal posture is not adjusted, the sorting quality will inevitably be reduced.

Practice has shown that the random placement of material errors on the conveyor belt is objective and inevitable. Compared with traditional manual teaching sorting, how to improve the intelligence level and sorting efficiency of the sorting system is the key to solving the problem. Aiming at the above problems, the position-based visual servo control is adopted, which is characterized by comparing the end pose of the robot with the expected pose, and calculating the end pose deviation of the robot. The error is defined in the working space of the servo system. Therefore, its advantage lies in the use of spatial pose information to describe robot tasks, and the design of control laws is easy and robust.

Therefore, to develop a control and processing system with low cost, simple structure and high sorting efficiency, which can satisfy the three-dimensional information extraction of mixed materials based on position visual servo control, and provide technical support for real-time guidance of visual sorting, the market potential is huge. In view of the above-mentioned technical research, the present application is described in detail through the following examples.

An embodiment of the present invention provides a material sorting system 10. As shown in FIG. 1, the material sorting system 10 in this embodiment includes: a first image sensor 110, a second image sensor 120, an image collector 200, and a processing device 300 and 400 for robots.

The first image sensor 110 is used to acquire first image data of the target object. The second image sensor 120 is configured to acquire second image data of the target. In one embodiment, the first image sensor 110 and the second image sensor 120 are at the same distance from the conveyor belt 620 shown in FIG. 1 , relative to the first image sensor 110 and the second image sensor The rotation angles of the carriers of 120 are the same or close. For example, the first image sensor 110 and the second image sensor 120 are installed on a horizontal bar parallel to the conveyor belt 620, and the first image sensor 110 and the second image sensor 120 are relatively The angles of the crossbars are the same or similar, and the angles of the first image sensor 110 and the second image sensor 120 relative to the conveyor belt 620 are the same or similar.

The image collector 200 is connected with the first image sensor 110 and the second image sensor 120 . The image collector 200 is used to collect the first image data obtained by the first image sensor 110 and the second image data obtained by the second image sensor 120 .

The processing device 300 is connected to the image collector 200, and the processing device 300 is used to acquire the first image data and the second image data from the image collector 200, and according to the first image data and the The second image data is calculated to obtain the three-dimensional information of the target object and the volume of the target object.

The processing device 300 is further configured to generate motion commands for controlling the robot 400 according to the three-dimensional information and volume.

The robot 400 is connected with the processing device 300, and the robot 400 is configured to receive a motion command from the processing device 300, so as to adjust the end according to the motion command to grab the target.

In this embodiment, by acquiring the volume of the target, when the movement command is generated, the end of the robot can be opened or closed within the range of the volume along the plane where the target is located, so as to enabling the end of the robot to better grasp the target. Further, the processing device may also calculate the length and width of the upper surface of the target.

For example, the width of the upper surface of the target is 20cm, and the length is 50cm. The degree of opening and closing of the end of the robot can be opened in the range of 17-60cm according to the width and length of the target, so that the robot The target can be successfully grasped.

In this embodiment, the three-dimensional information of the target is obtained by calculating the position deviation between the corresponding points of the first image data and the second image data.

In this embodiment, the three-dimensional information of the target can be converted from the camera coordinate system to the robot end coordinate system through the hand-eye system.

In this embodiment, the first image sensor 110 may be a CMOS image sensor (CMOS ImageSensor, CIS for short). The CMOS image sensor is a contact photosensitive device. The material used in the CMOS image sensor may be cadmium sulfide used to manufacture photoresistors. The first image sensor 110 may also be a CCD (charge coupled device) scanner. Described CCD scanner is a kind of semiconductor chip that utilizes microelectronics technology to make, and there are many photosensitive units on the chip of CCD scanner, and image is transmitted to the CCD chip through the optical system that is made up of a series of lenses, mirrors etc. , realize the photoelectric conversion function. In this embodiment, the second image sensor 120 may also be a CMOS image sensor or a CCD scanner.

In this embodiment, the processing device 300 may be a network server, a database server, etc., or may be a personal computer (personal computer, PC), a tablet computer, a smart phone, a personal digital assistant (personal digital assistant, PDA), etc.

The image collector 200 in this embodiment may be a multi-channel image acquisition card, and the multi-channel image acquisition card collects image signals into the processing device 300 in real time.

In one embodiment, a multi-channel image acquisition card is used to acquire image signals into the processing device 300 and save them in the hard disk in the form of data files. The multi-channel image acquisition card can transfer the video signals captured by the first image sensor 110 and the second image sensor 120 from the first image sensor 110 and the second image sensor 120 to the In the processing device 300, and use the image processing algorithm in the processing device 300 to complete the positioning and recognition of the target object, and then convert it into a motion command of the robot 400 to control the end effector of the robot 400 to reach the actual position of the target object.

In this embodiment, the binocular stereo vision technology is used to realize the accurate detection of the position of the calculation target in the three-dimensional Cartesian space, a high-quality image is obtained through a high-precision image sensor, and the image is processed by the processing device 300 and can be output for the robot. The plane coordinates of the terminal pose translation adjustment, and at the same time, the calculation of the rotation coordinates can be performed and the result can be sent to the robot controller 500 to correct the terminal rotation posture. This part realizes the dynamic guidance of the robot 400 for sorting objects through the binocular stereo vision system and visual servo fusion processing.

The embodiment of the present application adopts the binocular stereo vision technology, which is based on the parallax of the imaging points. The characteristics of the target object in the three-dimensional space captured by the binocular first image sensor 110 and the second image sensor 120 are imaged in two The plane is used for stereo matching, that is, the imaging coordinates of the same feature point are found on two different imaging planes. Once the correct stereo matching relationship is obtained, the parallax image of the corresponding matching area can be obtained, and the object in the three-dimensional space can be obtained. The three-dimensional information of the object, in order to move the end effector of the robot 400 to the set desired position (the position of the target object) and realize the online adjustment of the end posture, it is necessary to calculate the current pose of the end effector of the robot 400 The relative position to the desired position or the relative position to the base coordinates of the robot 400, the robot 400 uses these relative position quantities to solve the control quantities of each joint according to the inverse kinematics relationship, and then realizes the online adjustment of the terminal posture of the robot 400, realizing Real-time positioning and sorting of mixed materials.

The first image sensor 110 and the second sensor observe two images of the same target through two viewpoints above the target, calculate the parallax between corresponding pixels of different images according to the principle of triangulation, and obtain depth information, thereby realizing three-dimensional and reconstructing to obtain the three-dimensional information of the target. On this basis, it is necessary to perform binocular stereo vision calibration, the purpose is to calculate the distance between the first image sensor 110 and the second sensor in the binocular system formed by the first image sensor 110 and the second sensor. The relative positional relationship between the first image sensor 110 and the second sensor is to obtain the rotation matrix R and the translation matrix T. In trigonometry and geometry, triangulation is a method of measuring the distance to a target by measuring the angle between the target point and a known endpoint of a fixed datum line.

In this embodiment, as shown in FIG. 1 , the material sorting system 10 further includes a robot controller 500, and the robot controller 500 is configured to receive motion instructions produced by the processing equipment 300 to control the robot 400 sports.

In this embodiment, the robot 400 is also used to grab and place the target object in a set area. The processing device 300 is further configured to calculate the remaining space of the set area every time the device is placed. The processing device 300 is further configured to calculate whether the set area can accommodate the target object according to the volume of the target object and the remaining space, and generate a prompt message when the target object cannot be accommodated.

In this embodiment, the disappearance of the prompt can be a text message displayed on the processing device 300, or a voice message played by the audio device of the processing device 300, or a message sent to a designated electronic terminal information.

In one embodiment, the three-dimensional coordinates of the edge of the target are calculated through the first image data and the second image data, and the volume of the target is calculated according to the plurality of three-dimensional edge coordinates.

In this embodiment, the material sorting system 10 further includes: a trigger control device 800 arranged at a designated position, and the trigger control device 800 is used to send a detection message to the processing equipment 300 when the target object is detected. Signal.

After receiving the detection signal, the processing device 300 is configured to send a trigger command to the first image sensor 110 and the second image sensor to trigger the first image sensor 110 and the second image sensor 120 to work.

The processing device 300 is further configured to send a startup instruction to other devices connected to the processing device 300, so that the other devices are turned on.

In one embodiment, the trigger control device 800 is installed at one end of the conveyor belt 620 . For example, it is installed at one end of the conveyor belt 620 to receive objects. Only the trigger control device 800 is shown in the figure, and it can be understood that the trigger control device 800 can be installed on a mounting bracket.

When the trigger control device 800 detects that there is material, the detection signal is transmitted to the processing device 300, and the processing device 300 issues a control command to trigger the first image sensor 110 and the second image sensor 120 to perform image acquisition. And make other devices open at the same time, so as to ensure the scanning speed of the system and improve work efficiency. The other devices may include an image collector 200, a robot 400, a robot controller 500, and the like.

In this embodiment, the material sorting system 10 further includes: a bracket 600 , and the bracket 600 includes a cross arm 610 and a support arm 620 .

The first image sensor 110 and the second image sensor 120 are installed on the cross arm 610 of the bracket 600 .

In this embodiment, the support arm 620 is provided with a plurality of first installation positions, and the cross arm 610 is installed in any one of the plurality of first installation positions.

The first installation position may be an installation hole provided on the support arm 620, and the cross arm 610 is installed in the installation hole through a fixing member.

At least three second installation positions are provided on the cross arm 610 , and the first image sensor 110 and the second image sensor 120 are installed on two second installation positions of the at least three second installation positions.

In this embodiment, the second installation position may be a groove provided on the cross arm 610, the groove is provided with installation holes, the first image sensor 110 and the second image sensor 120 A mounting sheet is connected to the top, and the mounting sheet has a through hole corresponding to the mounting hole. When the first image sensor 110 or the second image sensor 120 needs to be installed, the through hole can be placed corresponding to the installation hole, and then fixed by a fixing piece.

In this embodiment, as shown in FIG. 1 , the cross arm 610 may be arranged directly above the conveyor belt 620 . The first image sensor 110 and the second sensor can rotate relative to the cross arm 610 .

The distance between the cross arm 610 and the conveyor belt 620 can be adjusted by adjusting the cross arm 610 to be installed at different first installation positions.

Through the above settings within the allowable imaging range, the first image sensor 110 and the second image sensor 120 can be adjusted in height and lateral directions to adapt to installation in different environments, and at the same time

The binocular stereo vision system collects the three-dimensional depth image of the material on the conveyor belt 620, and then calculates the direction, coordinates and grabbing point of the mixed material from the obtained image through the processing system. Considering the size information of the material, within the allowable range of measurement accuracy, a height-adjustable bracket 600 and a binocular angle- and lateral-direction adjustable structure are designed. The use of the cantilever bracket 600 can avoid the working space of the robot 400 and improve the safety of the robot 400 working.

In this embodiment, a first filter is installed at the lens of the first image sensor 110 ; a second filter is installed at the lens of the second image sensor 120 .

In this embodiment, the first image sensor 110 and the second image sensor 120 are perpendicular to each other or at a certain angle and directly illuminate the materials on the conveyor belt 620 .

Filters with specific wavelengths are installed in front of the lenses of the first image sensor 110 and the second image sensor 120 to ensure the high quality of image collection and prevent interference from external strong light.

Further, the material sorting system 10 in this embodiment mainly includes two parts, one of which includes a binocular stereo vision imaging system, which mainly includes the first image sensor 110 and the second image sensor installed in parallel 120. A bracket 600 is formed. The main positioning is to complete the extraction of the coordinates, direction and grabbing point of the mixed material on the conveyor belt 620 . The second is the processing device 300, the image collector 200, and the method for correcting the attitude of the robot end by combining the position visual servo control, which mainly combines the three-dimensional information of the material obtained by the binocular stereo vision with the position visual servo control to realize the real-time monitoring of the mixed material. sorting.

The embodiment of the present invention adopts a control method combining binocular stereo vision technology and visual servo control technology, which has accurate positioning, high precision, and easy control and realization. Through a single vision system, the three-dimensional contour of any material can be extracted, and the three-dimensional information of any point on the contour can be obtained. At the same time, the control method based on processing equipment is realized, and a new visual servo control method is proposed by combining the binocular stereo vision system on the basis of complementary advantages. The first image sensor and the second image sensor installed parallel to each other are used as the image acquisition equipment, which are not affected by the interference and temperature of the industrial site environment, and can provide reliable signal input for the real-time sorting of the robot, which is conducive to improving the intelligence of the robot sorting level. Specifically reflected in the following points:

①The imaging unit adopts binocular stereo vision, which has the advantages of high efficiency, appropriate precision, simple system structure, and low cost. It is very suitable for the manufacturing site. It uses a trigger control device to transmit the signal when the material on the conveyor belt is detected To the processing equipment, the computer sends instructions to enable other systems to open at the same time, improving work efficiency, and using high-performance processing equipment to efficiently perform image processing and information processing.

②Binocular stereo vision technology and position-based visual servo control method are used to realize real-time sorting of mixed materials. On the one hand, binocular stereo vision technology is used to reconstruct the three-dimensional information of materials, including the direction, coordinates and grabbing points of mixed materials, and then Through the position-based visual servo control method, the terminal posture and related parameters of the robot are adjusted in real time to perform precise sorting tasks. The method proposed by the embodiment of the present invention has higher accuracy and real-time performance.

③The material sorting system provided by the embodiment of the present invention can carry out visual reconstruction of the three-dimensional shape of the mixed material. In addition to being used for material positioning and grabbing, it can also be used for volume measurement of the target object, and accurate data analysis can reduce warehouse explosion. Phenomenon.

④In addition to being used for sorting and guiding mixed materials on the production line, the embodiment of the present invention can also be used for laser cutting path guidance, welding, palletizing, handling and other operations, as well as other real-time production and processing based on robotics and visual servo control .

In the material sorting system of the embodiment of the present invention, by obtaining two image data of the target object, and using the two image data to calculate the three-dimensional information and volume of the target object, the generated motion command can better position the robot to the desired location. The position of the target object is described, thereby reducing the error of the robot grabbing the target object.

Please refer to FIG. 2 , which is a flowchart of a material sorting method applied to the processing equipment shown in FIG. 1 provided by an embodiment of the present invention. The specific process shown in FIG. 2 will be described in detail below.

Step S101 , acquiring first image data of a target collected by a first collection device and second image data of a target collected by a second collection device.

Step S102, using the first image data and the second image data to locate the 3D information and volume of the target.

Step S103, generating motion commands for controlling the robot according to the three-dimensional information and volume.

In this embodiment, the step S103 includes: calculating the relative position of the three-dimensional information and the current pose of the terminal of the robot, and using the relative position as a motion track to generate the motion instruction.

In this embodiment, the position where the end of the robot needs to move can be calculated by using the hand-eye calibration method.

Step S104, sending the motion command to the robot, so that the robot adjusts the end according to the motion command to grab the target.

In this embodiment, the robot grabs and places the target object in a set area, as shown in FIG. 3 , the method further includes: step S105 to step S107.

Step S105, calculating the remaining space of the set area every time the device is placed.

Step S106 , calculating whether the set area can accommodate the target object according to the volume of the target object and the remaining space.

Step S107, when the target cannot be accommodated, a prompt message will be generated.

In this embodiment, as shown in FIG. 4 , the method further includes: Step S108 to Step S109.

Step S108 , after receiving the detection signal sent by the trigger control device, sending a trigger command to the first image sensor and the second image sensor to trigger the first image sensor and the second image sensor to work.

Step S109, sending an activation instruction to other devices connected to the processing device, so as to enable the other devices to be turned on.

Further, the method further includes performing hand-eye calibration on the robot. In this embodiment, the material sorting system further includes an end effector optical target arranged at the end of the robot and an optical target of a target moving body installed at other positions (not shown in FIG. 1 ). For example, the target moving body optical target can be installed on the edge of the conveyor belt shown in FIG. 1 . In one embodiment, the robot can be calibrated by hand and eye through the following steps:

Step 1: Obtain the position information images of the optical target of the end effector and the optical target of the target moving body in the initialization state collected by the first image sensor and the second image sensor, and calculate the optical target of the end effector of the robot according to the camera model The pose homogeneous matrix expression M _2V in the camera coordinate system and the pose homogeneous matrix expression M _1V of the target moving body optical target in the camera coordinate system, then go to step 2;

Step 2: Measure the pose homogeneous matrix expression M _2T of the optical target of the end effector in the coordinate system of the end effector of the robot through the measuring tool; obtain the six joint angles of the robot through the joint angle sensor to determine the initial position of the end effector of the robot The pose homogeneous matrix at the position, and then M _TB is obtained through the forward solution of robot kinematics; according to the coordinate transformation relationship, the homogeneous matrix of the optical target of the end effector under the robot base frame B is calculated as M _2B = M _TB · M _2T , then go to step 3;

Step 3: Determine the transformation matrix of the robot base frame, and calculate the transformation matrix from the camera coordinate system to the robot base frame according to the homogeneous matrix of the robot end effector optical target in the camera coordinate system and the robot base frame Transformation matrix M _map =M _2B ·M _2V ^-1 , then enter step 4;

Step 4: Calculate the positional relationship M _bind between the target moving body and the robot end effector. During the target tracking process, the robot always maintains a fixed offset relationship between the robot end effector and the target moving body. According to the After the first image sensor and the second image sensor acquire the homogeneous matrix M _2V of the optical target of the end effector and the homogeneous matrix M _1V of the optical target of the target moving body, the offset relationship is calculated: M _bind = M _2V ⁻¹ · M _1V , then go to step 5;

Step 5: Calculate the position error of the optical target of the end effector and the optical target of the target moving body in the camera coordinate system V, and the first image sensor and the second image sensor continuously calculate a new M _1V at a certain frequency and M _2V , the position error M _errV in the camera visual coordinate system V is calculated by M _errV ＝ M _1V -M _2V · M _bind ; and then calculated by the formula M _errB = M _map · M _errV The position error M _errB , then go to step 6;

Step 6: Determine the error value. The homogeneous matrix M _errB contains the position errors ΔX, ΔY, and ΔZ of the robot end effector and the target moving body in the three-dimensional space in the _X , _Y , and _Z directions. If the error value is in If it is within the allowable range ε, go to step 1, otherwise go to step 7;

Step 7: Calculate the speed control variables V _X , V _Y , and V _Z in the robot end effector coordinate system T by using the error value according to the PID algorithm, and send them to the robot controller to make the robot end effector move at a given speed. Then enter step 1 to achieve the goal of the robot tracking motion quickly and accurately within a certain space range.

For other details of this embodiment, reference may be made to the descriptions in the foregoing system embodiments, which will not be repeated here.

In the material sorting method of the embodiment of the present invention, by obtaining two image data of the target object, and using the two image data to calculate the three-dimensional information and volume of the target object, the generated motion instructions can better position the robot to the desired location. The position of the target object is described, thereby reducing the error of the robot grabbing the target object.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods may also be implemented in other ways. The device embodiments described above are only illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functions and possible implementations of devices, methods and computer program products according to multiple embodiments of the present invention. operate. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code that includes one or more Executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or action , or may be implemented by a combination of dedicated hardware and computer instructions.

In addition, each functional module in each embodiment of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art 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 instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. . It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is a relationship between these entities or operations. any such actual relationship or order exists between them. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention. It should be noted that like numerals and letters denote similar items in the following figures, therefore, once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention. Should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims (10)

1. a kind of Material Sorting system, which is characterized in that the Material Sorting system includes：

First imaging sensor, the first image data for obtaining object；

Second imaging sensor, the second image data for obtaining the object；

The image acquisition device being connect with described first image sensor and second imaging sensor, for acquiring described first The second image data that the first image data and the second imaging sensor that imaging sensor obtains obtain；

The processing equipment being connect with described image collector, the processing equipment are used to obtain described the from described image collector One image data and the second image data, and the target is calculated according to described first image data and the second image data The volume of the three-dimensional information of object and the object；

The processing equipment is additionally operable to generate the movement instruction of control robot according to the three-dimensional information and volume；

The robot being connect with the processing equipment, the robot is used to receive the movement instruction of the processing equipment, with root End is adjusted to capture the object according to the movement instruction.

2. Material Sorting system as described in claim 1, which is characterized in that the robot is additionally operable to grab the object It takes and is placed on setting regions；

The processing equipment is additionally operable to every remaining space placed and once calculate the setting regions；

The processing equipment is additionally operable to whether calculate the setting regions according to the volume of the object and the remaining space The object can be accommodated, when the object cannot be accommodated, prompting message will be generated.

3. Material Sorting system as described in claim 1, which is characterized in that the Material Sorting system further includes：

Trigger control device in designated position is set, the trigger control device, for when detecting the object, to institute It states processing equipment and sends detection signal；

The processing equipment sends triggering after receiving the detection signal, to described first image sensor and the second image Instruction triggers described first image sensor and the work of the second imaging sensor；

The processing equipment is additionally operable to send enabled instruction to the miscellaneous equipment connecting with the processing equipment, so that described other Opening of device.

4. Material Sorting system as claimed in claim 3, which is characterized in that the Material Sorting system further includes：

Holder, the holder include transverse arm and support arm；

Described first image sensor and the second imaging sensor are mounted on the transverse arm of the holder.

5. Material Sorting system as claimed in claim 4, which is characterized in that multiple first installations are arranged on the support arm Position, the transverse arm are mounted at any installation position in the multiple first installation position；

At least three second installation positions, described first image sensor and second imaging sensor peace are set on the transverse arm On two the second installation positions of described at least three second installation positions.

6. Material Sorting system as described in claim 1, which is characterized in that installed at the camera lens of described first image sensor There is the first filter plate；The second filter plate is installed at the camera lens of second imaging sensor.

7. a kind of Material Sorting method, which is characterized in that including：

Obtain the of the first image data of the object of the first collecting device acquisition and the object of the second collecting device acquisition Two image datas；

The three-dimensional information and volume of the object are positioned using described first image data and the second image data；

The movement instruction of control robot is generated according to the three-dimensional information and volume；

The movement instruction is sent to robot, so that the robot adjusts end to capture according to the movement instruction State object.

8. Material Sorting method as claimed in claim 7, which is characterized in that the object is captured and placed by the robot In setting regions, the method further includes：

Often place the remaining space for once calculating the setting regions；

Calculate whether the setting regions can accommodate the object according to the volume of the object and the remaining space；

When the object cannot be accommodated, prompting message will be generated.

9. Material Sorting method as claimed in claim 7, which is characterized in that be applied to processing equipment, the processing equipment with Trigger control device connects, and the method further includes：

After receiving the detection signal that the trigger control device is sent, sent to described first image sensor and the second image Triggering command triggers described first image sensor and the work of the second imaging sensor；

Enabled instruction is sent to the miscellaneous equipment being connect with the processing equipment, so that the miscellaneous equipment is opened.

10. Material Sorting method as claimed in claim 7, which is characterized in that described to be given birth to according to the three-dimensional information and volume Include at the step of movement instruction for controlling robot：

Calculate the relative position of the end current pose of the three-dimensional information and the robot；

Using the relative position as movement instruction described in trace generator.