Robot picking control method, device and equipment

Abstract

Embodiments of the present application provide a robot picking control method, device and equipment, the method comprising: obtaining the robot's goods placing pose when the goods to be picked is placed; determining the target robot's recognition pose and first travel path according to the goods placing pose; controlling the target robot to move to the recognition pose along the first travel path, and recognizing the goods to be picked pose at the recognition pose, and determining the target pose of the target robot according to the goods to be picked pose; determining the second travel path according to the target pose; and controlling the target robot to move to the target pose along the second travel path. Since the recognition pose is determined according to the goods placing pose, the robot can recognize the goods at a precise angle, and the travel path of the robot from the recognition pose to the target pose is determined according to the accurate recognition result, so the recognition accuracy is higher, the target picking pose can be determined more accurately, and a straight picking path is more likely to be planned, thereby improving the picking efficiency.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of robot control, and particularly relates to a robot goods taking control method, device and equipment. BACKGROUND

[0002] With the rapid development of mobile robot related technologies in recent years, the mobile robots are increasingly applied in logistics, warehousing, factory production and the like. A key application of the robot is goods carrying, which mainly includes three steps of goods taking, moving and goods placing. Due to limited space resources, storage spaces are usually arranged densely, and therefore the goods taking process has a relatively high precision requirement.

[0003] In the related art, when taking goods, the robot needs to be controlled to move to a preset fixed waiting pose, to perform goods recognition at the pose, and to move to a goods position to take goods according to the recognition result.

[0004] However, the prior art has the technical problems of low recognition precision and low goods taking efficiency. SUMMARY

[0005] The application relates to a robot goods taking control method, device and equipment, to solve the technical problems of low recognition precision and low goods taking efficiency in the prior art.

[0006] In a first aspect, the application provides a robot goods taking control method, comprising:

[0007] obtaining a goods placing pose of a robot when a to-be-taken goods is placed;

[0008] determining, according to the goods placing pose, a recognition pose and a first travel path of a target robot;

[0009] controlling the target robot to move along the first travel path to the recognition pose, and to recognize a to-be-taken goods pose at the recognition pose, and determining a target pose of the target robot according to the to-be-taken goods pose;

[0010] determining a second travel path according to the target pose;

[0011] controlling the target robot to move along the second travel path to the target pose.

[0012] The application provides a method capable of improving the efficiency and accuracy of a robot picking up goods. When the robot picks up goods, a goods placing pose of the robot is first acquired, and an identification pose of the robot identifying the goods and a path to the identification pose are determined according to the goods placing pose. Since the identification pose is determined according to the goods placing pose, the robot can identify the goods at a precise angle. Then, the path of the robot from the identification pose to the target pose is determined according to the accurate identification result. Compared with the traditional method of identifying goods at a fixed waiting point, the method has higher identification accuracy, can more accurately determine the target pose of picking up goods, and can plan a straight picking path with high probability, thereby improving the efficiency of picking up goods.

[0013] Optionally, the method further comprises:

[0014] acquiring a preset waiting pose and a preset topological path; determining the identification pose according to the goods placing pose; and correcting the preset topological path according to the identification pose and the preset waiting pose to obtain the first path.

[0015] Here, the application pre-acquires a fixed preset waiting pose and a preset topological path, and corrects the fixed waiting pose and the topological path according to the goods placing pose of the robot placing the goods to be picked up, so as to correct the pose of the robot identifying the goods. For example, the waiting pose is corrected to face the goods, thereby reducing the identification error, improving the identification accuracy, and further improving the efficiency of the robot picking up goods.

[0016] Optionally, the method further comprises:

[0017] establishing a coordinate system with a navigation control center of the goods to be picked up when the goods are placed, determining a straight line where the front and back movement directions of the goods placing pose in the coordinate system as a straight line where the identification pose is located; determining an identification distance according to a preset waiting distance and / or a distance between the preset waiting pose and the goods placing pose; and determining the identification pose according to the identification distance and the straight line where the identification pose is located.

[0018] In the application, a coordinate system is established with a navigation control center of the goods to be picked up when the goods are placed, a straight line where the x-axis of the goods placing pose is located, i.e., a straight line where the front direction of the goods when the goods are placed is located, is determined as a straight line where the identification pose is located. In order to ensure the identification accuracy, an identification distance is determined according to a preset waiting distance and / or a distance between the preset waiting pose and the goods placing pose, so as to ensure that the direction of the robot can basically face the goods or the target pose when the robot identifies the goods, and ensure the rationality of the identification distance, thereby further improving the identification accuracy.

[0019] Optionally, the first travel path is determined according to the first preset path and the second preset path after the correction.

[0020] According to a preset segmentation length threshold, the preset topological path is segmented to obtain a first preset path and a second preset path; the second preset path is corrected according to the identified pose and the preset waiting pose to obtain a second preset path after the correction; and the first travel path is determined according to the first preset path and the second preset path after the correction.

[0021] In the method, the preset topological path is segmented to obtain the second preset path that needs to be corrected and the first preset path that does not need to be corrected, and only part of the path needs to be corrected, thereby reducing the calculation amount of the path correction processing and further improving the path processing efficiency and the robot picking efficiency.

[0022] Optionally, the second preset path is corrected according to the identified pose and the preset waiting pose to obtain a second preset path after the correction.

[0023] According to the identified pose and the preset waiting pose, a deflection angle and a bias displacement of the second preset path are determined; and the second preset path is rotated and translated according to the deflection angle to move the preset waiting pose on the second preset path to the identified pose to obtain a second preset path after the correction.

[0024] Here, the method can directly perform rotation and translation processing on the preset fixed waiting pose, the identified pose and the second preset path, and quickly and efficiently correct the path.

[0025] Optionally, the preset topological path includes a preset main road path, a preset turning arc path and a preset storage site straight line path; and correspondingly, the first preset path includes the preset main road path and the preset turning arc path, and the second preset path is the preset storage site straight line path.

[0026] In the method, the part of the path that needs to be corrected can be directly determined according to the original division of the path, that is, the preset main road path, the preset turning arc path and the preset storage site straight line path, without performing redundant splitting processing, thereby further simplifying the path processing steps and improving the goods identification and robot picking efficiency.

[0027] Optionally, the first travel path is determined according to the first preset path and the second preset path after the correction.

[0028] The first preset path and the second preset path after the correction are connected by a convergence error to obtain a first travel path.

[0029] Here, the application can connect and convert the first preset path and the second preset path after the correction according to the convergence error algorithm, reduce the influence of discontinuity during path switching, plan a smooth path for the robot, and further improve the picking efficiency of the robot.

[0030] Optionally, the robot's goods placement pose when the goods are placed is obtained, comprising:

[0031] According to the identification information of the goods to be picked and the correspondence between the pre-stored identification information and the goods placement pose, the goods placement pose of the goods to be picked is obtained.

[0032] Optionally, before the goods placement pose of the goods to be picked is obtained according to the correspondence between the identification information of the goods to be picked and the pre-stored identification information and the goods placement pose, the method further comprises:

[0033] The robot is controlled to place the goods at a preset pose; the identification information of the goods and the goods placement pose of the robot when the goods are placed are obtained; and the correspondence between the identification information and the goods placement pose is stored.

[0034] Since the goods are placed by the robot, the current pose of the robot is obtained and uploaded when the goods are placed, and the picking task parameters are corrected by the prior information when the goods are picked, thereby improving the safety, efficiency and accuracy of picking.

[0035] In a second aspect, the application provides a robot picking control device, which comprises:

[0036] The acquisition module is configured to obtain the goods placement pose of the robot when the goods to be picked are placed;

[0037] The first determination module is configured to determine the identification pose of the target robot and the first travel path according to the goods placement pose;

[0038] The first control module is configured to control the target robot to move to the identification pose along the first travel path, identify the goods to be picked at the identification pose, determine the target pose of the target robot according to the goods to be picked, and determine the target pose of the target robot according to the goods to be picked.

[0039] The second determination module is configured to determine the second travel path according to the target pose.

[0040] The second control module is configured to control the target robot to move to the target pose along the second travel path.

[0041] Optionally, the first determining module comprises:

[0042] an acquiring sub-module, configured to acquire a preset waiting pose and a preset topological path;

[0043] a determining sub-module, configured to determine an identification pose according to the put-away pose;

[0044] a correcting sub-module, configured to correct the preset topological path according to the identification pose and the preset waiting pose, to obtain a first travel path.

[0045] Optionally, the determining sub-module is specifically configured to:

[0046] establish a coordinate system with a navigation control center of the to-be-taken goods when placed, and determine a straight line where a front-back movement direction of the put-away pose in the coordinate system as a straight line where the identification pose is located;

[0047] determine an identification distance according to a preset waiting distance and / or a distance between the preset waiting pose and the put-away pose;

[0048] determine the identification pose according to the identification distance and the straight line where the identification pose is located.

[0049] Optionally, the correcting sub-module is specifically configured to:

[0050] perform segmentation processing on the preset topological path according to a preset segmentation length threshold, to obtain a first preset path and a second preset path; correct the second preset path according to the identification pose and the preset waiting pose, to obtain a corrected second preset path; and determine the first travel path according to the first preset path and the corrected second preset path.

[0051] Optionally, the correcting sub-module is further specifically configured to:

[0052] determine a deflection angle and a bias displacement of the second preset path according to the identification pose and the preset waiting pose; perform rotation processing and translation processing on the second preset path according to the deflection angle, to move the preset waiting pose on the second preset path to the identification pose, to obtain the corrected second preset path.

[0053] Optionally, the preset topological path comprises a preset main road path, a preset turning arc path and a preset in-storage position straight line path; correspondingly, the first preset path comprises the preset main road path and the preset turning arc path, and the second preset path is the preset in-storage position straight line path.

[0054] Optionally, the correcting sub-module is further specifically configured to:

[0055] The first preset path and the second preset path after the correction are connected by means of convergence error to obtain a first travel path.

[0056] Optionally, the acquisition module is specifically configured to:

[0057] According to the correspondence relationship between the identification information of the to-be-taken goods and the pre-stored identification information and the goods placement pose, the goods placement pose of the to-be-taken goods is acquired.

[0058] Optionally, before the acquisition module is configured to acquire the goods placement pose of the to-be-taken goods according to the correspondence relationship between the identification information of the to-be-taken goods and the pre-stored identification information and the goods placement pose, the device further comprises a placement control module configured to:

[0059] control the robot to place the goods at a preset pose; acquire the identification information of the goods and the goods placement pose of the robot when the goods are placed; and store the correspondence relationship between the identification information and the goods placement pose.

[0060] In a third aspect, the present application provides a robot goods taking control device, comprising a memory and a processor.

[0061] The memory stores computer program instructions.

[0062] The processor executes the computer program instructions stored in the memory to implement the method according to any one of the first aspect.

[0063] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer program instructions, and the computer program instructions are executed by a processor to implement the method according to any one of the first aspect.

[0064] In a fifth aspect, the present application provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the method according to any one of the first aspect.

[0065] The present application provides a robot goods taking control method, device and equipment. When the robot takes goods, the goods placement pose of the robot when placing the to-be-taken goods is first acquired, the identification pose of the robot for identifying the goods and the path to the identification pose are determined according to the goods placement pose. Since the identification pose is determined according to the goods placement pose, the robot can accurately identify the goods at a precise angle. According to the accurate identification result, the travel path of the robot from the identification pose to the target pose is determined. Compared with the traditional method of walking to a fixed waiting point to identify the goods, the identification accuracy is higher, the target goods taking pose can be more accurately determined, and a straight line taking path is more likely to be planned, thereby improving the goods taking efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the present application, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0067] Figure 1 An application scenario schematic diagram provided for the embodiments of the present application;

[0068] Figure 2 A conventional fork picking pallet process schematic diagram of related technology provided for the embodiments of the present application;

[0069] Figure 3 A robot picking control system architecture schematic diagram provided for the embodiments of the present application;

[0070] Figure 4 A robot picking control method flowchart schematic diagram provided for the embodiments of the present application;

[0071] Figure 5 Another robot picking control method flowchart schematic diagram provided for the embodiments of the present application;

[0072] Figure 6 A robot picking process schematic diagram provided for the embodiments of the present application;

[0073] Figure 7 Another robot picking process schematic diagram provided for the embodiments of the present application;

[0074] Figure 8 Still another robot picking process schematic diagram provided for the embodiments of the present application;

[0075] Figure 9 Still another robot picking process schematic diagram provided for the embodiments of the present application;

[0076] Figure 10 Still another robot picking control method flowchart schematic diagram provided for the embodiments of the present application;

[0077] Figure 11 A robot picking control device structure schematic diagram provided for the embodiments of the present application;

[0078] Figure 12 A robot picking control device structure schematic diagram provided for the embodiments of the present application.

[0079] The specific embodiments of the present application have been described in detail above with reference to the accompanying drawings. The above description and drawings are not intended to limit the scope of the present application in any way, but merely to illustrate the concept of the present application to those skilled in the art. DETAILED DESCRIPTION

[0080] To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in a clear and complete manner with reference to the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of the present application.

[0081] It should be noted that although the terms "first", "second", and the like are used to describe various information in the embodiments of the present application, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. Alternatively, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information without departing from the scope of the present application.

[0082] It should be understood that the terms "comprising", "including", indicate the presence of the previously mentioned features, steps, operations, but do not exclude the presence, occurrence or addition of one or at least one other feature, step, operation. The terms "and / or" and the like used in the present application can be interpreted as inclusive or mean any one or any combination. Alternatively, "A and / or B" means "any of the following: A; B; A and B". In addition, the character " / " in this paper generally indicates that the associated objects before and after are in an "or" relationship.

[0083] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards, and provide corresponding operation portal for user to choose authorization or refusal.

[0084] First, the terms involved in the present application are explained:

[0085] Pose: position and attitude, in a two-dimensional coordinate system, position is usually represented as (x, y), and attitude (also called angle, heading or yaw) is usually represented as θ.

[0086] Incomplete constraint robot: a robot equipped with wheels fixed relative to the chassis (the chassis cannot rotate), whose moving direction can only be forward or backward along the rolling direction of the fixed wheels, such as differential, standard fork (standard forklift) robots, if lateral deviation is to be eliminated, the moving direction can only be changed by generating a rotating motion, therefore it is called an incomplete constraint robot.

[0087] Waiting point / waiting pose: due to the limited recognition range of the perception sensor, and the recognition accuracy is usually closer, the robot will first move to a certain distance in front of the target position along the topological path before recognizing the docking machine, goods, storage location, to ensure the accuracy of the docking, picking, and placing tasks. The position is called the waiting point, and the expected pose of the robot at this position is called the waiting pose, which is represented by W in the embodiments of the present application.

[0088] Target pose: the pose that the robot is expected to reach, in this paper, it refers to the expected pose of the robot when it starts to pick goods, which is represented by T.

[0089] Recognition pose: the current pose of the robot when placing goods, which is represented by D.

[0090] One of the key applications of the robot is the handling of goods, which mainly includes three steps: picking, moving, and placing. Due to the limited space resources in most factories, the storage locations are usually arranged densely, so the picking process requires high accuracy. If the accuracy is poor during picking, it may cause problems such as picking skew, not picking goods, etc. If the goods are skewed relative to the robot after picking, it is easy to drop the goods. In addition, due to the dense shelves and goods near the storage locations, if the picking accuracy is poor or there is a rotating motion component (such as an arc, in-place rotation) during picking, it is easy to cause interference and collision due to the occupation of more space.

[0091] Figure 1 An application scenario provided by the embodiments of the present application is shown in the following figure. Figure 1 The application scenario of the embodiments of the present application includes a standard fork and a pallet, Figure 1 The standard fork top view, pallet top view, and pallet side view are shown in the figure, where the arrow in the figure represents the forward direction of the standard fork, and the coordinate in the figure represents the navigation control center of the standard fork, that is, the center moves along the path. In Figure 1 In the application scenario, the robot is a standard fork, and the goods are usually placed on a pallet. Picking means picking a pallet. The standard fork picking process is: lowering the tines to the bottom, then moving backward to insert the tines into the pallet hole, and lifting the goods by lifting the tines to complete the picking task.

[0092] Figure 2 A conventional standard fork picking pallet process of a related technology provided by the embodiments of the present application is shown in the following figure. Figure 2As shown, the conventional fork picking pallet process is as follows: first step, control the fork to move along the topological map path to the waiting pose W before picking the pallet. Usually, the topological map path includes three types: main road path P1, turning arc path P2, and storage site straight path P3. Second step, start the perception sensor to identify the pallet at the waiting pose, search and identify the pallet within a certain range, determine the pallet pose, and determine the robot target pose T for picking the pallet according to the pallet pose. Further, path planning is performed according to the current pose and target pose of the robot to obtain the planning path P0 for picking the pallet. Third step, control the robot to move along the planning path P0 to the target pose T. Fourth step, perform the picking operation after reaching the target pose T. The related art mainly controls the robot to move to a fixed waiting pose in the topological map, then identifies the pose of the goods to be picked by the perception sensor, further obtains the target pose of the robot for picking the goods, finally plans the path and controls the robot to move to the target pose for picking the goods. In addition, the relative pose between the goods and the robot can also be continuously identified by the perception sensor, and then the deviation between the current pose and the target pose of the robot is continuously obtained, and the robot is continuously guided according to the pose deviation to complete the picking.

[0093] However, the related art has the following problems: since the waiting pose is fixed, there are errors in storage site identification and navigation control when goods are placed, so there will be a certain lateral deviation Ay and angle deviation Atheta between the waiting pose W and the target pose T. However, when Ay or Atheta is large, an arc or a rotation + straight line path needs to be planned to enable the nonholonomic robot to reach the target pose T for picking the goods. However, the arc or rotation + straight line motion will occupy more space and has lower efficiency than the straight line. The perception sensor usually has high accuracy when facing the object to be identified, but if there is a large Ay or Atheta, it will easily lead to inaccurate identification, so it cannot reach the accurate picking pose at one time and needs to be adjusted repeatedly, which is low in efficiency. Since the arc motion has both rotation and movement components, it will affect the estimation accuracy of the odometer and also have adverse effects on the navigation control accuracy, which will easily lead to failure to reach the target pose at one time and needs to be identified again after returning to the waiting point. In summary, the existing technology has the technical problems of low identification accuracy and low picking efficiency.

[0094] To solve the above technical problems, the embodiment of the present application provides a robot picking control method, which obtains the placing pose of the robot when placing the goods to be picked, determines the identification pose of the robot for identifying the goods and the path to the identification pose according to the placing pose, and determines the travel path according to the accurate identification result after identifying the goods at the identification pose.

[0095] Since the goods are placed by the robot itself, the situation when placing the goods is clear, and the waiting pose and path in the picking task are corrected according to the information when placing the goods, so as to ensure that the robot is basically opposite to the goods (or the target pose) when reaching the waiting pose, that is, Δy and Δθ are small. In this way, it can be ensured that the planned path is a straight line, and the picking efficiency and accuracy are improved.

[0096] Optionally, Figure 3 A schematic diagram of a robot picking control system architecture is provided for the embodiments of the present application. In Figure 3 In the above-mentioned architecture, the above-mentioned architecture includes at least one of a data acquisition device 301, a processing device 302 and a display device 303.

[0097] Optionally, the robot picking control system can be in communication connection with the robot, so as to control the robot.

[0098] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the architecture of the robot picking control system. In other possible embodiments of the present application, the above-mentioned architecture can include more or fewer components than the illustrated, or combine certain components, or split certain components, or different component arrangement, which can be determined according to the actual application scene, and is not limited herein. Figure 1 The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0099] In the specific implementation process, the data acquisition device 301 can include an input / output interface, and can also include a communication interface. The data acquisition device 301 can be connected with the processing device through the input / output interface or the communication interface.

[0100] The processing device 302 can obtain the placing pose of the robot when placing the goods to be picked, determine the recognition pose of the robot for recognizing the goods and the path to the recognition pose according to the placing pose, and determine the travel path according to the accurate recognition result after recognizing the goods at the recognition pose.

[0101] The display device 303 can also be a touch display screen or a screen of a terminal device, which is used to receive user instructions while displaying the above-mentioned content, so as to realize the interaction with the user.

[0102] It should be understood that the above-mentioned processing device can be realized by reading the instructions in the memory by the processor and executing the instructions.

[0103] In addition, the network architecture and service scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0104] It can be understood that the embodiments of the present application take the forklift taking pallets and the differential latent forklift taking shelves as examples for illustration, but the application of the embodiments of the present application is not limited to the forklift taking pallets and the differential taking shelves, other vehicle types taking goods or docking machine tables, etc. can be similarly processed. Even, all other methods of correcting the current task parameters by prior information in the previous task to improve the quality of task completion also belong to the protection scope of the embodiments of the present application.

[0105] In the following, the technical solutions shown in the present application are described in detail through specific embodiments. It should be noted that the following embodiments can exist independently, or can be combined with each other. For the same or similar content, it is not repeated in different embodiments.

[0106] Optionally, Figure 4 A flowchart of a robot taking goods control method provided by the embodiments of the present application. The execution subject of the embodiments of the present application can be the processing device 302 in the Figure 3 , or the processor of the robot, and the specific execution subject can be determined according to the actual application scene. As shown in Figure 4 , the method comprises the following steps:

[0107] S401: Obtain the goods placing pose of the robot when the goods to be taken are placed.

[0108] Optionally, when the robot is placed, the placing pose of the robot can be obtained, or the robot is controlled to upload the placing pose to a preset storage location after placing, and the placing pose is obtained from the preset storage location when the goods need to be taken.

[0109] Optionally, obtaining the goods placing pose of the robot when the goods to be taken are placed comprises:

[0110] According to the correspondence between the identification information of the goods to be taken and the pre-stored identification information and the placing pose, the placing pose of the goods to be taken is obtained.

[0111] Optionally, the identification information can be information such as the goods label, the goods type, the quantity of each goods, etc.

[0112] S402: According to the placing pose, determine the recognition pose and the first travel path of the target robot.

[0113] The first travel path herein refers to a travel path of the target robot from the starting pose to the recognition pose.

[0114] The storage pose is prior information, and the purpose of obtaining is to adjust the topological path according to the prior information, so as to ensure that the lateral and angle deviations are small when the goods are recognized, thereby improving the recognition accuracy and planning a straight line path.

[0115] S403: controlling the target robot to move along the first travel path to the recognition pose, and recognizing the to-be-taken goods pose at the recognition pose, and determining the target pose of the target robot according to the to-be-taken goods pose.

[0116] Optionally, the target pose of the target robot is determined according to the to-be-taken goods pose, including: determining the target pose of the target robot according to the to-be-taken goods pose and a preset robot-to-goods taking pose difference or a preset robot-to-goods taking distance.

[0117] Since the recognition pose is determined according to the storage pose, the lateral and angle deviations of the current pose of the robot and the target pose should be small, and a straight taking path can be planned, the recognition pose can be accurately recognized and obtained, and the recognition error is reduced. Further, the straight taking reduces the difficulty of taking goods by the robot, and reduces the taking error caused by the angle adjustment of the robot.

[0118] S404: determining a second travel path according to the target pose.

[0119] The second travel path refers to a travel path of the target robot from the recognition pose to the target pose.

[0120] S405: controlling the target robot to move along the second travel path to the target pose.

[0121] The embodiments of the present application provide a method capable of improving the taking efficiency and accuracy of the robot. When the robot takes goods, the storage pose of the robot when the to-be-taken goods is placed is first obtained, the recognition pose of the robot for recognizing the goods and the path to the recognition pose are determined according to the storage pose. Since the recognition pose is determined according to the storage pose of the goods, the robot can recognize the goods at a precise angle, and the travel path of the robot from the recognition pose to the target pose is determined according to the accurate recognition result. Compared with the traditional method of walking to a fixed waiting point to recognize the goods, the recognition accuracy is higher, the target taking pose can be more accurately determined, and a straight taking path is more likely to be planned, thereby improving the taking efficiency.

[0122] Optionally, the embodiments of the present application can first determine the recognition pose according to the storage pose, correct the travel path of the robot based on the recognition pose, and correspondingly, Figure 5A flowchart illustrating another robot picking control method provided in this application embodiment is shown below. Figure 5 As shown, the method includes:

[0123] S501: Obtain the robot's placement posture when the goods to be picked up are placed.

[0124] S502: Obtain the preset waiting pose and preset topology path.

[0125] Optionally, a preset waiting pose and a preset topology path can be obtained through the robot's preset control information. Alternatively, pre-stored preset waiting poses and preset topology paths can be obtained, where the preset waiting pose and preset topology path refer to the robot's fixed preset waiting pose and preset topology path before correction.

[0126] Exemplary, Figure 6 This application provides a schematic diagram of a robot picking up goods, as shown in the embodiment of the present application. Figure 6 As shown, the preset topology path is a travel path consisting of the main road path P1, the turning arc path P2, and the straight path to the storage position P3, with the preset waiting pose being W.

[0127] S503: Determine the recognition pose based on the placement pose.

[0128] like Figure 6 As shown, the identified pose is W'.

[0129] Optionally, the identification pose is determined based on the placement pose, including:

[0130] A coordinate system is established with the navigation control center when the goods to be picked up are placed. The straight line of the forward and backward movement direction of the goods placement posture in the coordinate system is determined as the straight line where the recognition posture is located. The recognition distance is determined according to the preset waiting distance and / or the distance between the preset waiting posture and the goods placement posture. The recognition posture is determined according to the recognition distance and the straight line where the recognition posture is located.

[0131] like Figure 6 As shown, a coordinate system is established with the cargo placement pose D, and the recognition pose W' is on the same straight line as the X-axis of D, which reduces the angular deviation of the robot when recognizing the cargo.

[0132] Optionally, such as Figure 6 As shown, the straight line containing the x-axis of the cargo placement pose is determined as the straight line containing the recognition pose.

[0133] It is understood that the preset waiting distance here can be determined according to the actual situation, and this application embodiment does not impose specific restrictions on it.

[0134] Optionally, the recognition distance can be equal to the distance between the preset waiting position and the delivery position.

[0135] In the embodiment of the present application, a coordinate system is established at the navigation control center of the to-be-taken goods when placed, a straight line where the x-axis of the goods placement pose is located, i.e., a straight line where the front face of the goods when placed is located, is determined as a straight line where the identified pose is located, and in order to ensure the identification accuracy, the identification distance is determined according to the preset waiting distance and / or the distance between the preset waiting pose and the goods placement pose, so that the robot direction can basically face the goods or the target pose when the robot identifies the goods, and the identification distance is reasonable, and the identification accuracy is further improved.

[0136] S504: correcting the preset topological path according to the identified pose and the preset waiting pose to obtain a first travel path.

[0137] Since the connection between the corrected path P3' and the original topological path cannot be guaranteed, but the deviation is usually small (related to the goods placement deviation), the corrected path P3' can be directly switched to by controlling the convergence. The corrected path needs to have a certain length, otherwise it is difficult to guarantee the deviation when reaching the corrected waiting pose W'.

[0138] Optionally, the preset topological path is corrected according to the identified pose and the preset waiting pose to obtain a first travel path, including:

[0139] The preset topological path is segmented according to a preset segmentation length threshold to obtain a first preset path and a second preset path; the second preset path is corrected according to the identified pose and the preset waiting pose to obtain a corrected second preset path; and the first travel path is determined according to the first preset path and the corrected second preset path.

[0140] It can be understood that the preset segmentation length threshold can be determined according to actual conditions, and the embodiment of the present application does not make specific limitations.

[0141] Optionally, the first travel path is determined according to the first preset path and the corrected second preset path, including:

[0142] The first preset path and the corrected second preset path are connected by a convergence error to obtain the first travel path.

[0143] Optionally, the convergence error is connected by a convergence error algorithm, and the error caused by the discontinuity at the connection is automatically eliminated by controlling the convergence deviation of the algorithm.

[0144] Here, the embodiment of the present application can connect and convert the first preset path and the corrected second preset path according to the convergence error algorithm, reduce the influence caused by the discontinuity when switching paths, plan a smooth path for the robot, and further improve the efficiency of the robot in taking goods.

[0145] Exemplarily, Figure 7Another schematic diagram of the robot taking the goods is provided in the embodiments of the present application, based on Figure 6 , Figure 7 In the control robot moves to the identification pose, and automatically moves along the first travel path to the identification pose.

[0146] Optionally, the preset topology path includes a preset main path, a preset turning arc path, and a preset storage position straight path; correspondingly, the first preset path includes the preset main path and the preset turning arc path, and the second preset path is the preset storage position straight path. That is, the first preset path can be a combination of the main path P1 and the turning arc path P2 in Figure 6 or Figure 7 As shown in Figure 6 or Figure 7 , the second preset path can be P3' in Figure 6 .

[0147] In the embodiments of the present application, the part of the path that needs to be corrected can be determined directly according to the original division of the path, that is, the preset main path, the preset turning arc path, and the preset storage position straight path, without the need for redundant splitting processing, further simplifying the path processing steps, and improving the efficiency of goods identification and robot taking goods.

[0148] Optionally, according to the identification pose and the preset waiting pose, the second preset path is corrected to obtain a corrected second preset path, including:

[0149] According to the identification pose and the preset waiting pose, the deflection angle and the offset displacement of the second preset path are determined; according to the deflection angle, the second preset path is rotated and translated to move the preset waiting pose on the second preset path to the identification pose, to obtain the corrected second preset path.

[0150] Optionally, taking Figure 6 for example, Figure 6 , the angle between P3 and P3' is the deflection angle.

[0151] Here, the embodiments of the present application can directly perform rotation and translation processing on the preset fixed waiting pose, the identification pose, and the second preset path, to quickly and efficiently correct the path.

[0152] Specifically: a distance L is extended along the x-axis direction of the goods placing pose D to obtain a corrected waiting pose W', the angle of W' is consistent with the goods placing pose D. Wherein L can be a fixed value (the distance between the original designed waiting point and the target pose), or directly use the distance value between D and W. A segment of the original topological path is intercepted in the last segment of the original topological path, and the length of the segment is greater than a certain value (to ensure the accuracy when reaching the pose W'), and the segment is usually a straight path P3 from the storage position. The original path P3 and the waiting pose W are rotated and translated together so that W coincides with W', and the path P3 is corrected to P3'.

[0153] In the embodiment of the present application, the preset topological path is segmented in advance during the correction process, so as to obtain a second preset path that needs to be corrected and a first preset path that does not need to be corrected. Only part of the path needs to be corrected, thereby reducing the calculation amount of the path correction process and further improving the path processing efficiency and the robot picking efficiency.

[0154] S505: controlling the target robot to move along the first advancing path to the recognition pose, recognizing the to-be-picked goods pose at the recognition pose, and determining the target pose of the target robot according to the to-be-picked goods pose.

[0155] Exemplarily, Figure 8 Another robot picking process schematic diagram provided by the embodiment of the present application is based on the above, Figure 6 and the robot reaches the target pose along the path.

[0156] Since W' is corrected according to the goods placing pose D, the robot should be exactly opposite the pallet (Δy, Δθ is small) at the pose W. ′ Then the pallet is identified and confirmed through sensing, the target pose T is further determined, and the planning path P0 is obtained according to the current pose of the robot and the target pose T. Since the robot is basically opposite the pallet during planning, the robot can enter the pallet through a straight line to improve the efficiency of picking the pallet.

[0157] S506: determining a second advancing path according to the target pose.

[0158] Optionally, the second advancing path is a straight line connecting the recognition pose and the target pose.

[0159] S507: controlling the target robot to move along the second advancing path to the target pose.

[0160] Exemplarily, Figure 9 Another robot picking process schematic diagram provided by the embodiment of the present application is based on the above, Figure 8 and the robot reaches the target pose along the path and realizes picking.

[0161] It can be understood that, Figure 6- Figure 9 The embodiments of the present application are also applicable to other application scenarios such as differential latency robots, which are only exemplary.

[0162] The embodiments of the present application pre-acquire fixed preset waiting poses and preset topological paths, and correct the fixed waiting poses and topological paths in combination with the goods placing poses of the robot when placing the goods to be taken, so as to correct the poses of the robot when identifying the goods, for example, correct the waiting poses to face the goods, thereby reducing the identification error, improving the identification accuracy, and further improving the efficiency of the robot taking goods.

[0163] Optionally, in order to more conveniently and quickly realize taking goods, the embodiments of the present application acquire the goods placing pose of the robot each time the goods are placed, and correspondingly, Figure 10 Another flowchart of a robot taking goods control method provided by the embodiments of the present application is shown in FIG. 10. Figure 10 The method comprises the following steps:

[0164] S1001: Control the robot to place the goods at a preset pose.

[0165] S1002: Acquire the identification information of the goods and the goods placing pose of the robot when placing the goods.

[0166] S1003: Store the correspondence between the identification information and the goods placing pose.

[0167] S1004: Acquire the goods placing pose of the robot when placing the goods to be taken.

[0168] S1005: According to the goods placing pose, determine the identification pose and the first travel path of the target robot.

[0169] S1006: Control the target robot to move to the identification pose along the first travel path, and identify the pose of the goods to be taken at the identification pose, and determine the target pose of the target robot according to the pose of the goods to be taken.

[0170] S1007: Determine the second travel path according to the target pose.

[0171] S1008: Control the target robot to move to the target pose along the second travel path.

[0172] The implementation manners of steps S1004-S1008 are similar to those of steps S401-S405, and are not described herein.

[0173] Since the goods are placed by the robot, the embodiments of the present application acquire and bind the current pose of the robot when placing the goods, and correct the taking task parameters by the prior information when taking the goods, thereby improving the safety, efficiency and accuracy of taking goods.

[0174] Figure 11 This is a schematic diagram of the structure of a robot picking control device provided in an embodiment of this application, as shown below. Figure 11 As shown, the apparatus in this embodiment includes: an acquisition module 1101, a first determination module 1102, a first control module 1103, a second determination module 1104, and a second control module 1105. The robot picking control device here can be the aforementioned processing device, the processor itself, or an integrated circuit that implements the processor's functions. It should be noted that the division of the acquisition module 1101, the first determination module 1102, the first control module 1103, the second determination module 1104, and the second control module 1105 is only a logical functional division; physically, they can be integrated or independent.

[0175] The acquisition module is used to acquire the robot's placement posture when the goods to be picked up are placed.

[0176] The first determining module is used to determine the target robot's recognition pose and first travel path based on the delivery pose.

[0177] The first control module is used to control the target robot to move along the first travel path to the recognition pose, and to recognize the pose of the goods to be picked up at the recognition pose, and to determine the target pose of the target robot based on the pose of the goods to be picked up.

[0178] The second determining module is used to determine the second travel path based on the target pose.

[0179] The second control module is used to control the target robot to move along the second travel path to the target pose.

[0180] Optionally, the first determining module includes:

[0181] The acquisition submodule is used to acquire the preset waiting pose and the preset topology path;

[0182] The determination submodule is used to determine the recognition pose based on the placement pose;

[0183] The correction submodule is used to correct the preset topology path based on the recognized pose and the preset waiting pose to obtain the first travel path.

[0184] Optionally, determine the specific use of the submodule for:

[0185] A coordinate system is established using the navigation control center when the goods to be picked are placed, and the straight line in which the forward and backward movement of the placement posture in the coordinate system is determined as the straight line where the identification posture is located.

[0186] The recognition distance is determined based on the preset waiting distance and / or the distance between the preset waiting position and the delivery position;

[0187] According to the identified distance and the straight line where the identified pose is located, the identified pose is determined.

[0188] Optionally, the correction sub-module is specifically configured to:

[0189] According to the preset segmentation length threshold, the preset topological path is segmented to obtain a first preset path and a second preset path; according to the identified pose and the preset waiting pose, the second preset path is corrected to obtain a corrected second preset path; and according to the first preset path and the corrected second preset path, the first travel path is determined.

[0190] Optionally, the correction sub-module is further configured to:

[0191] According to the identified pose and the preset waiting pose, a deflection angle and a bias displacement of the second preset path are determined; and according to the deflection angle, the second preset path is rotated and translated to move the preset waiting pose on the second preset path to the identified pose, to obtain the corrected second preset path.

[0192] Optionally, the preset topological path includes a preset main road path, a preset turning arc path, and a preset storage position straight line path; correspondingly, the first preset path includes the preset main road path and the preset turning arc path, and the second preset path is the preset storage position straight line path.

[0193] Optionally, the correction sub-module is further configured to:

[0194] The first preset path and the corrected second preset path are connected in a convergent error manner to obtain the first travel path.

[0195] Optionally, the acquisition module is specifically configured to:

[0196] According to the identification information of the to-be-taken goods and a correspondence relationship between the pre-stored identification information and the storage pose, the storage pose of the to-be-taken goods is acquired.

[0197] Optionally, before the acquisition module is configured to acquire the storage pose of the to-be-taken goods according to the identification information of the to-be-taken goods and the correspondence relationship between the pre-stored identification information and the storage pose, the device further includes a placement control module configured to:

[0198] Control the robot to place the goods at a preset pose; acquire the identification information of the goods and a storage pose of the robot when the goods are placed; and store the correspondence relationship between the identification information and the storage pose.

[0199] Reference Figure 12The diagram illustrates a structural schematic of a robot pickup control device 1200 suitable for implementing embodiments of the present disclosure. This robot pickup control device 1200 can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, personal digital assistants (PDAs), portable Android devices (PADs), portable media players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 12 The robot pickup control device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0200] like Figure 12 As shown, the robot picking control device 1200 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 1201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1202 or a program loaded from a storage device 1208 into a random access memory (RAM) 1203. The RAM 1203 also stores various programs and data required for the operation of the robot picking control device 1200. The processing unit 1201, ROM 1202, and RAM 1203 are interconnected via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0201] Typically, the following devices can be connected to the I / O interface 1205: input devices 1206 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 1207 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1208 including, for example, magnetic tape, hard disk, etc.; and communication devices 1209. Communication device 1209 allows the robot picking control device 1200 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 12 A robotic picking control device 1200 with various devices is shown; however, it should be understood that implementation or possession of all the devices shown is not required. More or fewer devices may be implemented alternatively.

[0202] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication device 1209, or installed from the storage device 1208, or installed from the ROM 1202. When the computer program is executed by the processing device 1201, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

[0203] It should be noted that the computer readable medium described above in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium may, for example, be, but is not limited to, an electronic, magnetic, optical, electromagnetic, or infrared system, device or apparatus, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, device or apparatus. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, in which a computer readable program code is carried. Such a propagated data signal can take a variety of forms, including, but not limited to, an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can be used to carry or transmit a program for use by or in connection with an instruction execution system, device or apparatus. The program code contained in the computer readable medium can be transmitted by any suitable medium, including, but not limited to, a wire, an optical fiber, an RF (radio frequency) or the like, or any suitable combination thereof.

[0204] The computer readable medium described above can be included in the robot picking control device; or can exist separately and not be assembled into the robot picking control device.

[0205] The computer readable medium described above carries one or more programs, which, when executed by the robot picking control device, cause the robot picking control device to execute the methods illustrated by the embodiments described above.

[0206] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0207] The flow diagrams and the block diagrams in the drawings are meant as possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams and the block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0208] The units described in the embodiments of the present disclosure can be implemented by software, or by hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself. For example, the first obtaining unit can also be described as a unit for obtaining at least two Internet protocol addresses.

[0209] The functions described above in the specification of the present disclosure can be performed by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Program-specific Integrated Circuits (ASICs), Program-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0210] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium can include, but not limited to, an electronic, magnetic, optical, electromagnetic, or infrared system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0211] The robot taking goods control device of the embodiments of the present application can be used to execute the technical solutions in the method embodiments of the present application, and the implementation principles and technical effects are similar, which will not be described here.

[0212] The embodiments of the present application also provide a computer readable storage medium, which stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the robot taking goods control method of any one of the above.

[0213] The embodiments of the present application also provide a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the robot taking goods control method of any one of the above.

[0214] In the several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0215] In addition, each functional unit in the embodiments of the present application can be integrated into one processing unit, or each unit can exist alone physically, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware, or in the form of software functional units.

[0216] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

[0217] It is to be understood that the application is not limited to the precise construction herein disclosed and shown in the drawings, and that various changes in shape, size and arrangements of parts can be made without departing from the scope of the application. The scope of the application is limited only by the claims that follow.

Claims

1. A robot picking control method, characterized in that, include: Obtain the robot's placement posture when the goods to be picked up are placed; Based on the loading pose, determine the target robot's recognition pose and first travel path; The target robot is controlled to move along the first travel path to the recognition pose, and the pose of the goods to be picked up is recognized at the recognition pose. The target pose of the target robot is determined based on the pose of the goods to be picked up. Determine the second travel path based on the target pose; Control the target robot to move along the second travel path to the target pose.

2. The method according to claim 1, characterized in that, The step of determining the target robot's recognition pose and first travel path based on the delivery pose includes: Obtain the preset waiting pose and preset topology path; Determine the identification pose based on the described placement pose; Based on the identified pose and the preset waiting pose, the preset topology path is corrected to obtain the first travel path.

3. The method according to claim 2, characterized in that, The step of determining the identification pose based on the placement pose includes: A coordinate system is established with the navigation control center of the goods to be picked up when they are placed, and the straight line in the coordinate system where the goods placement posture moves forward and backward is determined as the straight line where the identification posture is located. The identification distance is determined based on the preset waiting distance and / or the distance between the preset waiting pose and the delivery pose; The recognition pose is determined based on the recognition distance and the line where the recognition pose is located.

4. The method according to claim 2, characterized in that, The step of correcting the preset topology path based on the identified pose and the preset waiting pose to obtain the first travel path includes: The preset topology path is segmented according to a preset segmentation length threshold to obtain a first preset path and a second preset path. Based on the identified pose and the preset waiting pose, the second preset path is corrected to obtain the corrected second preset path; A first travel path is determined based on the first preset path and the modified second preset path.

5. The method according to claim 4, characterized in that, The step of correcting the second preset path based on the identified pose and the preset waiting pose to obtain the corrected second preset path includes: Based on the identified pose and the preset waiting pose, determine the deflection angle and offset displacement of the second preset path; Based on the deflection angle, the second preset path is rotated and translated to move the preset waiting pose on the second preset path to the recognized pose, thus obtaining the corrected second preset path.

6. The method according to claim 5, characterized in that, The preset topology path includes the preset main road path, the preset turning arc path, and the preset straight path to the storage location. Accordingly, the first preset path includes the preset main road path and the preset turning arc path, and the second preset path is the preset straight path to the storage location.

7. The method according to any one of claims 4 to 6, characterized in that, Determining the first travel path based on the first preset path and the modified second preset path includes: The first preset path and the corrected second preset path are connected by using a convergence error method to obtain the first travel path.

8. The method according to any one of claims 1 to 6, characterized in that, The process of obtaining the robot's placement pose when the goods to be picked up are placed includes: Based on the identification information of the goods to be picked up and the correspondence between the pre-stored identification information and the placement position, the placement position of the goods to be picked up is obtained.

9. The method according to claim 8, characterized in that, Before obtaining the placement position of the goods to be picked up based on the identification information of the goods to be picked up and the pre-stored correspondence between identification information and placement position, the method further includes: Control the robot to place the goods in a preset position; Obtain the identification information of the goods and the placement posture of the robot when placing the goods; Store the correspondence between the identification information and the placement position.

10. A robot picking control device, characterized in that, The device includes: The acquisition module is used to acquire the robot's placement posture when the goods to be picked up are placed. The first determining module is used to determine the target robot's recognition pose and first travel path based on the delivery pose. The first control module is used to control the target robot to move along the first travel path to the recognition pose, and to recognize the pose of the goods to be picked up in the recognition pose, and to determine the target pose of the target robot based on the pose of the goods to be picked up. The second determining module is used to determine the second travel path based on the target pose. The second control module is used to control the target robot to move along the second travel path to the target pose.

11. A robot picking control device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, are used to implement the method as described in any one of claims 1 to 9.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 9.

Images