Path planning method and device for mechanical arm, readable storage medium and program product

Abstract

One or more embodiments of the present specification provide a path planning method and device for mechanical arms, a readable storage medium and a program product, the method comprising: acquiring a first planned path of a first mechanical arm and a second planned path of a second mechanical arm, the first planned path and the second planned path belonging to the same space-time area; dividing the space-time region into a plurality of sub-regions, and determining each first type of sub-region to which the first planning path belongs and each second type of sub-region to which the second planning path belongs; under the condition that the first type of sub-regions and the second type of sub-regions comprise the same overlapping sub-regions, the first planning path and / or the second planning path are / is adjusted according to the overlapping sub-regions, so that the adjusted first planning path and the adjusted second planning path do not conflict with each other.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to the field of robotic arm technology, and in particular, to a path planning method, device, readable storage medium, and program product for a robotic arm. Background Art

[0002] With the growing demand for robot operation efficiency and complex task processing capabilities, the collaborative work technology of robotic arms has emerged. Among them, the collaborative work mode represented by multiple robotic arms (such as dual robotic arms) can not only expand the operating space, but also significantly enhance the flexibility and accuracy of work. Accordingly, in the multi-robotic arm scenario, it is necessary to plan the action paths of different robotic arms and complete obstacle avoidance so that each robotic arm can perform business actions separately without collision.

[0003] In the related art, technicians usually plan the paths for each robot arm separately through pre-teaching, or plan the theoretically optimal or better path for each robot arm based on conventional obstacle avoidance algorithms and models. However, on the one hand, the above methods all plan their own paths based on the action logic of each robot arm, and there may be path overlaps, so different robots may collide when they move, affecting the stability and safety of the robot arm's working process; on the other hand, the calculation logic of the above conventional obstacle avoidance methods is complex and the amount of calculation is large, which requires a high overall computing power of the equipment, so the path planning efficiency is low and the equipment cost is high, which needs to be improved urgently. Summary of the invention

[0004] In view of this, one or more embodiments of this specification provide the following technical solutions:

[0005] According to a first aspect of one or more embodiments of this specification, a path planning method for a robot arm is proposed, the method comprising:

[0006] Acquire a first planned path of the first robotic arm and a second planned path of the second robotic arm, wherein the first planned path and the second planned path belong to the same space-time region;

[0007] Dividing the spatiotemporal region into a plurality of sub-regions, and determining each first-category sub-region to which the first planned path belongs and each second-category sub-region to which the second planned path belongs;

[0008] In the case where the first type of sub-area and the second type of sub-area include the same overlapping sub-area, the first planned path and / or the second planned path are adjusted according to the overlapping sub-area so that the adjusted first planned path and the second planned path do not conflict with each other.

[0009] Optionally, the spatiotemporal region includes a spatial range;

[0010] The dividing the spatiotemporal region into a plurality of sub-regions comprises: dividing the spatial range into a plurality of spatial sub-ranges;

[0011] The determining of each first-category sub-area to which the first planned path belongs and each second-category sub-area to which the second planned path belongs includes: determining each first-category spatial sub-range to which the first planned path belongs and each second-category spatial sub-range to which the second planned path belongs;

[0012] Among them, the first type of sub-area and the second type of sub-area contain the same overlapping sub-area, including: the first type of time sub-interval and the second type of time sub-interval contain the same spatial overlapping sub-range, and the spatial overlapping sub-range is the same spatial range occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths.

[0013] Optionally, the spatiotemporal region includes a time interval;

[0014] The dividing the spatiotemporal region into a plurality of sub-regions comprises: dividing the time interval into a plurality of time sub-intervals;

[0015] The determining of each first-type sub-area to which the first planned path belongs and each second-type sub-area to which the second planned path belongs includes: determining each first-type time sub-interval to which the first planned path belongs and each second-type time sub-interval to which the second planned path belongs;

[0016] Among them, the first type of sub-area and the second type of sub-area contain the same overlapping sub-area, including: the first type of time sub-interval and the second type of time sub-interval contain the same time overlapping sub-interval, and the time overlapping sub-interval is the same time interval occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths.

[0017] Optionally, the space-time region includes a spatial range and a time interval;

[0018] The dividing the spatiotemporal region into a plurality of sub-regions comprises: dividing the spatial range into a plurality of spatial sub-ranges and a plurality of temporal sub-ranges respectively;

[0019] The determining of each first-class sub-area to which the first planned path belongs and each second-class sub-area to which the second planned path belongs includes: determining each first-class spatial sub-range and each first-class time sub-interval to which the first planned path belongs, and each second-class spatial sub-range and each second-class time sub-interval to which the second planned path belongs;

[0020] Among them, the first type of sub-area and the second type of sub-area contain the same overlapping sub-area, including: the first type of time sub-interval and the second type of time sub-interval contain the same spatial overlapping sub-range, the first type of time sub-interval and the second type of time sub-interval contain the same time overlapping sub-interval, the spatial overlapping sub-range is the same spatial range occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths, and the time overlapping sub-interval is the same time interval occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths.

[0021] Optionally, adjusting the first planned path according to the overlapping sub-area includes: acquiring a motion posture of the second robotic arm in the overlapping sub-area as a dynamic obstacle for the first robotic arm, and adjusting the first planned path according to a fast exploration random tree algorithm and the dynamic obstacle; or,

[0022] The adjusting the second planned path according to the overlapping sub-area includes: obtaining the motion posture of the first robotic arm in the overlapping sub-area as a dynamic obstacle for the second robotic arm, and adjusting the second planned path according to the fast exploration random tree algorithm and the dynamic obstacle; or,

[0023] The adjusting the first planned path and the second planned path according to the overlapping sub-area includes: adjusting the first planned path and the second planned path simultaneously according to an optimization algorithm or a machine learning technique.

[0024] Optionally, obtaining a first planned path of the first robotic arm includes:

[0025] Acquire an operation process of a target operation to be performed by the first robotic arm, and determine the first planned path according to the operation process;

[0026] Alternatively, multiple target operations matching the first robotic arm are selected from a set of candidate operations associated with the first robotic arm, and the first planned path is determined according to the multiple target operations and their execution order.

[0027] Optionally, the method further includes:

[0028] The first planned path and / or the second planned path are adjusted according to environmental obstacles other than any one of the robotic arms.

[0029] According to a second aspect of one or more embodiments of this specification, an electronic device is proposed, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor implements the steps of the method described in the first aspect by running the executable instructions.

[0030] According to a third aspect of one or more embodiments of the present specification, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0031] According to a fourth aspect of one or more embodiments of the present specification, a computer program product is provided, comprising a computer program / instruction, which implements the steps of the method described in the first aspect when executed by a processor.

[0032] In the technical solution provided in this specification, after obtaining the first planned path of the first robotic arm and the second planned path of the second robotic arm, which belong to the same space-time region, the space-time region can be divided into multiple sub-regions, so as to determine the first-class sub-regions to which the first planned path belongs and the second-class sub-regions to which the second planned path belongs in the space-time region. In the case where the first-class sub-region and the second-class sub-region include the same overlapping sub-region, there is a risk of accidental collision between the first robotic arm and the second robotic arm. At this time, the first planned path and / or the second planned path can be adjusted according to the above-mentioned overlapping sub-regions so that the adjusted first planned path and the second planned path do not conflict with each other.

[0033] It can be seen that, on the one hand, this scheme takes into account the sub-areas corresponding to the first planned path and the second planned path respectively, and therefore can plan the paths of the first robotic arm and the second robotic arm as a whole. Compared with the method of independently planning the path for a single robotic arm, the path planned by this scheme has higher stability and security; on the other hand, this scheme only adjusts the first planned path and / or the second planned path in the special case where the first type of sub-area and the second type of sub-area include the same overlapping sub-area, instead of adjusting all the areas corresponding to each path respectively, which effectively reduces the amount of calculation in the path planning process, thereby reducing the computing power requirements of the computing equipment, and improving the overall efficiency of path planning, achieving cost reduction and efficiency improvement in the path planning process in the robotic arm scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 It is a schematic diagram of the architecture of a path planning system for a robotic arm provided by an exemplary embodiment;

[0036] Figure 2It is a flowchart of a path planning method for a robot arm provided by an exemplary embodiment;

[0037] Figure 3 is a schematic diagram of dividing a plurality of spatial sub-ranges provided by an exemplary embodiment;

[0038] Figure 4 is a schematic diagram of dividing multiple time sub-intervals provided by an exemplary embodiment;

[0039] Figure 5 is a schematic diagram of a time-sharing operation based on time subintervals provided by an exemplary embodiment;

[0040] Figure 6 is a schematic diagram of a path planning method for a first robotic arm and a second robotic arm in a spatial overlapping sub-range and a temporal overlapping sub-interval provided by an exemplary embodiment;

[0041] Figure 7 is a schematic structural diagram of an electronic device provided by an exemplary embodiment;

[0042] Figure 8 It is a schematic structural diagram of a path planning device for a robotic arm provided by an exemplary embodiment. DETAILED DESCRIPTION

[0043] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are only examples of devices and methods consistent with some aspects of the present invention.

[0044] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0045] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0046] Figure 1 FIG. 1 is a schematic diagram of the architecture of a path planning system for a robotic arm provided by an exemplary embodiment. Figure 1 As shown, the system may include at least a first robotic arm 11 and a second robotic arm 12 .

[0047] The first robot arm 11 and the second robot arm 12 are respectively a multi-degree-of-freedom mechanical device. They can be composed of a base, a connecting rod and a joint. Specifically, the base is usually installed on a workbench or the ground as the fixed part of the robot arm; the connecting rod is a rigid component connecting each joint, which determines the range of motion and flexibility of the robot arm; the joint is a moving part of the robot arm, usually including a rotating joint and a moving joint, and the number of joints determines the degree of freedom of the robot arm. Each robot arm can be driven based on a motor, gear, belt and other devices, so that the end or joint of the robot arm forms a motion trajectory in space, and the planned path refers to an optimal or feasible motion trajectory designed for the robot arm from the starting position to the target position, so that the robot arm can avoid accidental collisions during the movement according to the planned path. The first robot arm corresponds to a first planned path, and the second robot arm corresponds to a second planned path, and the first planned path and the second planned path belong to the same space-time region.

[0048] Depending on the end effector, that is, the tool installed at the end of each robotic arm, the corresponding functions can be realized in application scenarios such as manufacturing, medical, logistics storage, agriculture, and construction. Taking the catering production field as an example, assuming that an intelligent coffee machine is equipped with a first robotic arm 11 and a second robotic arm 12, and the first robotic arm 11 uses a coffee bean gripper based on a gripper design as an end effector, and the second robotic arm 12 uses a coffee cup placer based on a suction cup design as an end effector, then the two robotic arms can work together, the first robotic arm 11 is responsible for the processing of coffee beans, and the second robotic arm 12 is responsible for the placement and movement of coffee cups, thereby improving the level of automation in coffee making.

[0049] It should be noted that the solution of the present application can be applicable to multi-robot arm scenarios, and the first robot arm and the second robot arm described in the embodiments of this specification can be any two robot arms in this scenario. The following embodiments mainly illustrate the path planning / adjustment process of the first robot arm and the second robot arm as an example.

[0050] Figure 2 is a flow chart of a path planning method for a robot arm provided by an exemplary embodiment, such as Figure 2 As shown, the above method includes:

[0051] Step S202: acquiring a first planned path of the first robotic arm and a second planned path of the second robotic arm, wherein the first planned path and the second planned path belong to the same space-time region.

[0052] When the first robotic arm and the second robotic arm are required to work together, the planned path of each robotic arm can be obtained first, so as to adjust the first planned path of the first robotic arm and / or the second planned path of the second robotic arm in subsequent steps, thereby avoiding conflicts between the first planned path and the second planned path, resulting in accidental collisions between the first robotic arm and the second robotic arm.

[0053] Taking the first planned path of the first robotic arm as an example, first, the preliminary path corresponding to the movement of the robotic arm can be determined according to the specific task that the first robotic arm needs to perform. Specifically, each task can be subdivided into multiple operations to be performed continuously, and each operation can instruct the first robotic arm to perform a corresponding action. Each action is preset with a corresponding motion path. Therefore, the process of determining the preliminary path of the first robotic arm is equivalent to clarifying the specific task to be performed by the first robotic arm, and then generating a rough path that meets the task sequence requirements according to the operation steps in the task and the kinematic model of the first robotic arm, that is, the above-mentioned preliminary path. The generation of the preliminary path can be achieved through simple geometric calculations or rule-based methods. For example, for the task of grabbing an object from point A and moving it to point B for placement, the preliminary path may be a straight line or a simple curve connecting points A and B. Of course, the preliminary path at this time only considers the task requirements and does not consider obstacles in the environment.

[0054] Among them, the so-called task can be realized by a set of operation procedures, which includes fixed target operations that the first robot arm needs to perform and a fixed execution order of each target operation. In other words, when the operation procedure of the target operation that the first robot arm needs to perform is obtained, the first planned path can be determined according to the operation procedure. For example: in an industrial assembly scenario, the task of the first robot arm on the assembly line may be an operation procedure that includes a series of target operations such as grabbing parts, moving to a specified position, and inserting parts. These target operations can be decomposed into ordered steps, and the above-mentioned first planned path can be determined according to the starting and ending postures of each step. Alternatively, multiple target operations matching the first robotic arm can be selected from the candidate operation set associated with the first robotic arm, and the first planned path can be determined according to the multiple target operations and their execution order. Different from the operation flow that defines the fixed target operation and the fixed execution order, the candidate operation set can include various operations supported by the first robotic arm. According to actual conditions, multiple target operations can be selected from the candidate operation set to determine the first planned path. Specifically, the selection of the target operation can be random selection or dynamically changed according to a preset selection rule. For example, in a shooting scene at a shooting range, the candidate operation set for controlling the first robotic arm on the target may include four operations: fast movement from left to right, fast movement from right to left, slow movement from left to right, and slow movement from right to left. Two candidate operations can be randomly selected as target operations, and the selection order can be used as the execution order to determine the first planned path. For example, the preset selection rule can stipulate that after the user misses the target more than a preset number of times, only the two operations of slow movement from left to right and slow movement from right to left are selected as target operations to determine the first planned path.

[0055] It should be noted that the above preliminary path can be directly used as the first planning path to improve the speed of path determination, or it can be further optimized on the basis of the preliminary path to obtain the first planning path with a lower risk of accidental collision. For example, the environmental information of the workspace where the first robot arm and the second robot arm are located is obtained by using sensors such as laser radar and camera, and an environmental map is constructed to clarify the position and shape of obstacles. The workspace is divided into discrete grids or voxels to facilitate sampling of the preliminary path, that is, a series of points are selected as sampling points on the above preliminary path. For each sampling point, a collision detection algorithm is applied to check whether the point collides with an obstacle. The collision detection algorithm can be based on intersection detection of geometric shapes, such as bounding box detection and distance field detection. If a sampling point collides, it means that the preliminary path is not feasible at this position and needs to be adjusted. For the area near the sampling point where the collision is detected, the sampling point can be used as the starting point, and sampling can be performed in the free space around it to find a new path segment that avoids obstacles and can be connected to the subsequent part of the preliminary path. For example, an obstacle avoidance algorithm such as a rapidly-exploring random tree (RRT) is used to sample from the free space near the collision point and grow a tree structure until a new path leading to a collision-free area and connecting with the original path is found as the first planned path.

[0056] Those skilled in the art can understand that the above-mentioned method for obtaining the first planned path can be applicable to any other planned path including the second planned path, so the method for obtaining other planned paths will not be described in detail again in this specification.

[0057] The above-mentioned spatiotemporal region can be realized based on the time and / or space dimensions. Taking the space dimension as an example, the first planned path and the second planned path belong to the same spatiotemporal region, which means that the two paths will overlap or partially overlap at certain spatial positions. For example, in a three-dimensional space working area, the two paths may intersect in a plane area at a certain height, or pass through a specific three-dimensional space area, or both paths are restricted to the same spatial boundary or conditions, for example, both are moving in a workshop with guardrails around and height restrictions above, and the spatial range of this workshop defines their common spatial area. Or in a space with specific obstacles, both paths need to avoid these same obstacles, so that they are limited to the movable space area divided by the obstacles. Taking the time dimension as an example, the first planned path and the second planned path belong to the same spatiotemporal region, which means that on the time axis, the time period when the first robot arm moves along the first planned path and the time period when the second robot arm moves along the second planned path overlap. For example, the first robot arm runs according to the planned path from 10:00 to 10:10 in the morning, and the second robot arm runs according to the planned path from 10:05 to 10:15 in the morning. These two time periods overlap for 5 minutes, that is, within these 5 minutes, the two paths are in the same time and space area. In addition, in the common time interval, the movement of the two paths may have a certain degree of synchronization or timing correlation. For example, in a certain automated production process, the first robot arm first grabs the part and moves it to a certain position, and then the second robot arm must reach the same position within a specific time to perform the next operation. This requires their paths to be closely coordinated in time and be in the same time and space area to complete the collaborative task.

[0058] Step S104: divide the spatiotemporal region into a plurality of sub-regions, and determine each first-category sub-region to which the first planned path belongs and each second-category sub-region to which the second planned path belongs.

[0059] After obtaining the first planned path and the second planned path, the sub-region to which each planned path belongs can be determined according to the multiple sub-regions obtained by dividing the space-time region. For the first planned path, the sub-region to which it belongs in the space-time region is called a first-type sub-region, and for the second planned path, the sub-region to which it belongs in the space-time region is called a second-type sub-region.

[0060] According to different time-space regions, the method of determining the corresponding first-type sub-region and second-type sub-region in this specification will also be different.

[0061] In one embodiment, the spatiotemporal region is implemented based on the spatial dimension and can be considered to include a spatial range. Therefore, the same spatial range to which the first planned path and the second planned path belong can be divided into multiple spatial sub-ranges, and the first-class spatial sub-ranges to which the first planned path belongs and the second-class spatial sub-ranges to which the second planned path belongs can be determined. Figure 3 For example, the entire spatial range can be divided into three spatial sub-ranges A, B, and C, wherein the first type of spatial sub-range to which the first planned path belongs includes spatial sub-ranges A and B, and the second type of spatial sub-range to which the second planned path belongs includes spatial sub-ranges B and C. The dark part in the spatial sub-range can be used to characterize the specific postures of the first robotic arm and the second robotic arm in the working area when they move according to their respective planned paths. Of course, for the convenience of explanation, Figure 3 The spatial sub-range and the robot arm posture therein are described only based on a specific two-dimensional plane. In fact, each spatial sub-range can also be represented by a three-dimensional space, and the above-mentioned robot arm posture can also be represented by a three-dimensional model in the three-dimensional space. This manual will not go into details.

[0062] In another embodiment, the spatiotemporal region is implemented based on the time dimension and can be considered to include time intervals. Therefore, the same spatial range to which the first planned path and the second planned path belong can be divided into multiple time sub-intervals, and the first-type time sub-intervals to which the first planned path belongs and the second-type time sub-intervals to which the second planned path belongs can be determined. Figure 4 For example, assuming that the time period required for each robot to perform each operation according to its own planned path is called a time slice, then each of the above operations can be further divided into slice actions according to the unit time in the time period, for example Figure 4 The time slice 41 formed from the fifth unit time to the eighth unit time can be represented as the entire time period spent by the first robotic arm in performing the grasping action. Similarly, the time slice 42 corresponding to the second robotic arm can also be reflected in the same coordinate axis corresponding to the first robotic arm, which will not be elaborated in this manual.

[0063] In another embodiment, the spatiotemporal region is implemented based on both the spatial dimension and the temporal dimension, and can be considered to include a spatial range and a temporal interval. Therefore, the same spatial range to which the first planned path and the second planned path belong can be divided into multiple temporal sub-intervals, and the same spatial range to which the first planned path and the second planned path belong can be divided into multiple spatial sub-ranges, and then each first-class spatial sub-range and each first-class temporal sub-interval to which the first planned path belongs, and each second-class spatial sub-range and each second-class temporal sub-interval to which the second planned path belongs can be determined from the multiple temporal sub-intervals and the multiple spatial sub-ranges, respectively. This embodiment combines the solutions of the above two embodiments at the same time, and divides the same spatiotemporal region into different types of spatial sub-ranges and temporal sub-intervals according to different dimensions, so that the first planned path and the second planned path can be more accurately disassembled and analyzed.

[0064] Step S106: When the first type of sub-area and the second type of sub-area include the same overlapping sub-area, adjust the first planned path and / or the second planned path according to the overlapping sub-area so that the adjusted first planned path does not conflict with the second planned path.

[0065] As can be seen from the foregoing, the first planned path belongs to the first type of sub-region in the space-time region, and the second planned path belongs to the second type of sub-region in the space-time region. When the two include the same overlapping sub-region, it means that the first planned path and the second planned path overlap in the time or space dimension, which may cause the first planned path and the second planned path to conflict with each other, and then cause the first robot arm and the second robot arm according to their respective planned paths to collide unexpectedly. Correspondingly, when a planned path and the second planned path do not include any overlapping sub-regions, it can be considered that there is no conflict between the originally obtained first planned path and the second planned path, and there is no possibility of an accidental collision between the first robot arm and the second robot arm, and thus there is no need to adjust the first planned path and / or the second planned path.

[0066] It can be understood that the so-called adjusted first planned path and the second planned path do not conflict with each other. According to the actual situation, it can be understood that only the first planned path or the second planned path is adjusted, thereby avoiding the conflict with the other planned path. It can also be understood that the first planned path and the second planned path are adjusted at the same time, thereby avoiding the conflict between each other.

[0067] In combination with the different space-time regions described above, the situation where the first type of sub-regions and the second type of sub-regions include the above-mentioned overlapping sub-regions is further classified.

[0068] In the case where the space-time region includes a spatial range, the same spatial overlapping subrange contained in the first type of spatial subrange and the second type of spatial subrange can be used as the above-mentioned overlapping subrange, wherein the spatial overlapping subrange can be the same spatial range occupied by the first robot arm and the second robot arm to perform corresponding actions according to their respective planned paths. Figure 3 For example, when both the first type of spatial sub-range and the second type of spatial sub-range involve spatial sub-range B, it can be considered that the specific postures of the first robot arm and the second robot arm in the working area when they move according to their respective planned paths involve spatial sub-range B, so there is a risk of accidental collision between the first robot arm and the second robot arm. Similarly, when the first type of spatial sub-range only involves spatial sub-range A and\or the second type of spatial sub-range only involves spatial sub-range C, no matter which spatial sub-ranges the spatial sub-range corresponding to the other robot arm contains, since at least one robot arm must be in a completely non-intersecting range in the figure when moving according to its respective planned path, there is no risk of accidental collision between the first robot arm and the second robot arm, and they can move according to the original planned path.

[0069] In the case where the space-time region includes a time interval, the same time overlapping subinterval contained in the first type of time subinterval and the second type of time subinterval can be used as the above-mentioned overlapping subinterval, wherein the time overlapping subinterval can be the same time interval occupied by the first robot arm and the second robot arm when performing corresponding actions according to their respective planned paths. Figure 5For example, suppose that the first robot arm determines the first planning path according to operations 1 and 2 in task 1 in the figure, and takes the time sub-interval corresponding to 3 to 5 unit time points of the time axis when performing operation 1, and the time sub-interval corresponding to 10 to 13 unit time points of the time axis when performing operation 2 as the first type of time sub-interval; the second robot arm determines the second planning path according to operations 3 and 4 in task 2 in the figure, and takes the time sub-interval corresponding to 6 to 9 unit time points of the time axis when performing operation 3, and the time sub-interval corresponding to 12 to 16 unit time points of the time axis when performing operation 4 as the second type of time sub-interval. Obviously, the first planning path corresponding to operation 2 and the second planning path corresponding to operation 4 have the same time overlapping sub-interval, that is, the time interval corresponding to 13 unit time points, which means that the first robot arm and the second robot arm will perform their respective operations at the same time at 13 unit time points, resulting in the risk of accidental collision between the first robot arm and the second robot arm. Similarly, when there is no time overlapping sub-interval between the first type of time sub-interval and the second type of time sub-interval, for example, the first type of time sub-interval corresponding to operation 1 and the second type of time sub-interval corresponding to operation 3, the corresponding robotic arms can be directly controlled to perform their respective operations in time sharing, so that only one robotic arm moves according to the corresponding planned path at the same time point, thereby avoiding the risk of accidental collision caused by the simultaneous movement of the two robotic arms.

[0070] Similarly, when the space-time region includes a spatial range and a time interval, it can be determined that the first type of time sub-interval contains the same spatial overlapping sub-range as the second type of time sub-interval, and the first type of time sub-interval contains the same time overlapping sub-interval as the second type of time sub-interval. Only when both the spatial overlapping sub-range and the time overlapping sub-interval exist at the same time, can it be considered that the first type of sub-region and the second type of sub-region contain the same overlapping sub-region. Figure 3 and Figure 5 For example, it can be understood that the first robot arm and the second robot arm are simultaneously involved in the spatial sub-range B, and the first robot arm and the second robot arm simultaneously perform their respective corresponding operations in the spatial sub-range B to move, then the first planned path and the second planned path are likely to conflict, resulting in an unexpected collision between the first robot arm and the second robot arm. Similarly, in the case where there is only a time overlapping sub-interval, there is no possibility of collision between the first robot arm and the second robot arm in space, so the first planned path cannot conflict with the second planned path, or, in the case where there is only a spatial overlapping sub-range, at most only one robot arm between the first robot arm and the second robot arm is moving according to the planned path, and the other robot arms will be regarded as environmental obstacles and avoided in the corresponding time interval.

[0071] It is necessary to explain that the solution of the present application can be used to adjust the first planned path and / or the second planned path to avoid accidental collision between the first robotic arm and the second robotic arm, but the first planned path and / or the second planned path can also be adjusted according to environmental obstacles other than any robotic arm, and there is no correlation or exclusion between the two during the implementation process.

[0072] After the overlapping sub-regions are determined, the first planned path and / or the second planned path can be adjusted according to the overlapping sub-regions to avoid conflicts between the first planned path and the second planned path. Specifically, the adjustment strategy can be divided into two cases according to the number of adjusted paths.

[0073] The first case: only the first planned path is adjusted according to the overlapping sub-area, for example, the motion posture of the second robot arm in the overlapping sub-area is obtained to use it as a dynamic obstacle for the first robot arm, and the above-mentioned first planned path is adjusted according to the fast exploration random tree algorithm and the dynamic obstacle. Specifically, when the first robot arm is the slave arm and the second robot arm is the master arm, a collision-free path is first planned for the master arm, and then the motion posture of the master arm at each moment is regarded as a dynamic obstacle when the slave arm moves. Starting from the starting point, the RRT algorithm is used to randomly sample in the free space and grow a tree structure towards the sampling point. At the same time, it is checked whether the generated new node will collide with the dynamic obstacle (that is, the motion posture of the master arm). If there is a collision risk, the node is discarded or the growth direction is adjusted. On the basis of the original planned path of the slave arm, a collision-free path is planned for it. A feasible motion path; or, only adjusting the second planned path according to the overlapping sub-area, for example, obtaining the motion posture of the first robotic arm in the overlapping sub-area to use it as a dynamic obstacle for the second robotic arm, and adjusting the above-mentioned second planned path according to an obstacle avoidance algorithm such as a fast exploration random tree algorithm and the dynamic obstacle. At this time, the first robotic arm is the master arm and the second robotic arm is the slave arm. An initial planned path can be planned for the slave arm first, and then the motion posture of the first robotic arm in the overlapping sub-area is used as the dynamic obstacle of the second robotic arm. Using the RRT algorithm, the original planned path of the slave arm is taken as the basis, and by continuously exploring new nodes and edges, try to find a new path branch that avoids the motion posture of the master arm, so as to ensure that the slave arm does not collide with the master arm during movement, thereby generating a safer and feasible planned path. In this way, the motion posture of one of the robotic arms can be used as a dynamic obstacle for the other robotic arm, and the RRT algorithm can be used to make adjustments based on the original planned path to achieve optimization of only a single planned path, ensuring safe and collision-free operation between the robotic arms in the same space-time area. This is suitable for simpler dual-robotic arm collaboration scenarios, where the path of one robotic arm is relatively fixed or difficult to change, while the path of the other robotic arm can be flexibly adjusted to avoid collision risks.

[0074] The second case: the first planned path and the second planned path are adjusted simultaneously according to the optimization algorithm or machine learning technology. For example, an optimization strategy based on a genetic algorithm is adopted. The first planned path of the first manipulator and the second planned path of the second manipulator are regarded as two interrelated gene individuals, and a fitness function is defined. The function comprehensively considers factors such as the time efficiency, energy consumption, path smoothness, and collision avoidance of the manipulator movement. Through the selection, crossover, and mutation operations in the genetic algorithm, the two "gene individuals" are continuously evolved so that the overall performance of the two paths is optimal under the premise of satisfying the same space-time region constraints. Specifically, the two initial planned paths are first encoded and converted into a gene form suitable for genetic algorithm operation. Then, for each generation of path combinations, its fitness value is calculated, and the better path combination is selected according to the fitness size to enter the next generation. In the crossover operation, some fragments of the two paths are randomly selected for exchange to generate a new path combination, simulating the gene exchange process in biological inheritance. The mutation operation randomly adjusts certain key nodes in the path and introduces new path possibilities to avoid the algorithm from falling into a local optimal solution. Through multiple generations of evolution, the first planned path and the second planned path that are optimized at the same time are finally obtained. Alternatively, reinforcement learning technology is used to model the motion environment of the robot arm as a Markov decision process. The first robot arm and the second robot arm are regarded as two intelligent agents. Each agent learns the optimal motion strategy based on the reward signal obtained by interacting with the environment, thereby adjusting its own planned path. When defining the reward function, positive rewards are given for behaviors such as successfully avoiding collisions and completing tasks efficiently, while negative rewards are given for situations such as high collision risks and low motion efficiency. During the training process, the two agents continuously explore different path options and gradually learn the optimal path for coordinated motion in the same space-time area, that is, they simultaneously adjust the optimized first planned path and second planned path.

[0075] In short, no matter which of the above situations is the premise of adjusting the planned path, the premise is to determine the above-mentioned overlapping sub-areas. Compared with adjusting the first planned path and the second planned path in the entire space-time area, the premise of overlapping sub-areas introduced in this application can reduce the algorithm complexity in the above-mentioned adjustment strategy, thereby improving the calculation efficiency of the adjusted planned path and shortening the planning time, thereby improving the success rate of the path adjustment.

[0076] In addition, as mentioned above, the solution of this specification is also applicable to multi-robot arm scenarios. For example, in the scenario of an automated factory assembly workshop, there are robot arms A, B, and C, among which robot arm A takes parts from the parts library, robot arm B preprocesses, and robot arm C is responsible for assembly, and the three work together. During path planning, each robot arm first generates a preliminary path according to the task, and then builds an environmental map through sensors. After sampling and collision detection, the planned path is optimized using the RRT algorithm; then, the workspace is divided into multiple sub-ranges such as the parts library area in the spatial dimension, and the time sub-intervals are divided according to the operation time in the time dimension to determine the sub-area to which each robot arm path belongs; then check whether there are overlapping sub-areas, such as a transition area is a spatial overlapping sub-range of at least two robot arms, and the above-mentioned at least two robot arms are operating here within a specific time period, constituting a time overlapping sub-interval, and it is determined that there are overlapping sub-areas. If so, a single path adjustment strategy can be adopted. For example, robot A is set as the slave arm, and the positions of robot arms B and C in the overlapping area are taken as dynamic obstacles of A. The RRT algorithm is used to adjust the path of A to ensure that the robots avoid collisions when working together and complete the task efficiently.

[0077] The following takes the first and second robotic arms of the coffee robot as an example. Figure 6 The path planning method of the first robot arm and the second robot arm in the spatial overlapping sub-range and the temporal overlapping sub-range is introduced.

[0078] S602: Acquire a first planned path for the first robotic arm and a second planned path for the second robotic arm.

[0079] In one embodiment, it is assumed that the first robot arm of the coffee robot is responsible for the task of grabbing and delivering coffee beans. First, its specific task is clarified, such as grabbing coffee beans from a coffee bean storage container and delivering them to a grinding device. This task can be subdivided into multiple continuous operations, such as moving above the coffee bean storage container, descending to grab coffee beans, rising and moving above the grinding device, delivering coffee beans, etc. Each operation corresponds to a corresponding action of the first robot arm, and each action is preset with a motion path. According to these operation steps and the kinematic model of the first robot arm, a preliminary path is generated through simple geometric calculations, such as a straight line from the storage container to the grinding device. The above preliminary path only considers the task requirements and does not consider obstacles. Then, the laser radar is used to obtain the environmental information of the coffee robot's workspace, build an environmental map, and clarify the location of obstacles, such as other equipment, supporting structures, etc. The workspace is divided into discrete grids, the preliminary path is sampled, and a series of sampling points are selected. A collision detection algorithm based on bounding box detection is used to check whether the sampling point collides with an obstacle. If a sampling point collides, the RRT algorithm is used to sample the free space around it, taking the point as the starting point to find a new path segment that avoids obstacles and can be connected to the subsequent part of the preliminary path, and finally the first planned path is obtained.

[0080] In addition, the second robotic arm is responsible for the task of picking up and placing coffee cups. Similarly, the task is first clarified, such as taking a coffee cup from the cup holder and placing it in the brewing position. The task is broken down into operations, such as moving to the top of the cup holder, grabbing the coffee cup, moving to the brewing position, placing the coffee cup, etc. A preliminary path is generated based on the operation steps and the kinematic model of the second robotic arm, and then the second planned path is obtained through a series of processes similar to those of the first robotic arm, namely, using environmental maps, discrete grid division, sampling point selection, collision detection algorithms, and RRT algorithms.

[0081] S604: Determine, based on the spatial range, each first-type spatial sub-range to which the first planned path belongs and each second-type spatial sub-range to which the second planned path belongs.

[0082] In one embodiment, assuming that the working space of the coffee robot is an operating room surrounded by guardrails and with a height limit above, the working space can be regarded as a space-time region based on the spatial dimension. According to the motion trajectory of the first planned path in the space, the different spatial areas it passes through are divided as the first type of spatial sub-ranges. For example, the motion path of the first robotic arm from the coffee bean storage container to the grinding device may pass through the storage area, the intermediate transition area, the grinding area, etc., which are the first type of spatial sub-ranges. Similarly, according to the second planned path, the spatial area passed by the motion trajectory of the second robotic arm from the cup holder to the brewing position is determined as the second type of spatial sub-range, such as the cup holder area, the mobile transition area, the brewing area, etc.

[0083] S606: Determine, based on the time interval, each first-type time sub-interval to which the first planned path belongs and each second-type time sub-interval to which the second planned path belongs.

[0084] In one embodiment, it is assumed that the first robotic arm takes different time to perform each operation, starting from moving to the top of the coffee bean storage container to completing the operation of placing coffee beans, each operation corresponds to a time slice. For example, it takes 1-3 seconds to move to the top of the storage container, 3-5 seconds to grab the coffee beans, 5-8 seconds to rise and move to the top of the grinding device, and 8-10 seconds to place the coffee beans. These time slices are the first type of time sub-intervals. For the second robotic arm, from moving to the top of the cup holder to completing the operation of placing the coffee cup, each operation also corresponds to a different time slice. For example, it takes 1-2 seconds to move to the top of the cup holder, 2-4 seconds to grab the coffee cup, 4-7 seconds to move to the brewing position, and 7-9 seconds to place the coffee cup, which constitute the second type of time sub-interval.

[0085] S608: Adjust the first planned path according to the overlapping sub-areas.

[0086] In one embodiment, spatial overlap judgment and temporal overlap judgment are performed simultaneously, that is, it is checked whether the first type of spatial sub-range and the second type of spatial sub-range have the same spatial overlap sub-range. For example, if the first robotic arm passes through a specific middle area in the path from the coffee bean storage container to the grinding device and the second robotic arm passes through a specific middle area in the path from the cup holder to the brewing position, then this middle area is the spatial overlap sub-range. At the same time, it is checked whether the first type of time sub-interval and the second type of time sub-interval have the same temporal overlap sub-interval. Assuming that the first robotic arm is at a certain position to perform an operation within the time slice of 5-8 seconds, and the second robotic arm will also reach the vicinity of this position to perform an operation within the time slice of 6-9 seconds, then 6-8 seconds is the temporal overlap sub-interval. Only when the spatial overlap sub-range and the temporal overlap sub-interval exist at the same time, is it determined that there is an overlapping sub-interval.

[0087] At this time, the first robot can be used as the slave arm and the second robot can be used as the master arm. The motion posture of the second robot in the overlapping sub-area (the area where both space and time overlap) is obtained and used as a dynamic obstacle for the first robot. According to the fast exploration random tree algorithm, starting from the starting point of the first robot, random sampling is performed in the free space and a tree structure is grown toward the sampling point. At the same time, it is checked whether the generated new node will collide with the motion posture of the second robot as a dynamic obstacle. If there is a collision risk, the node is discarded or the growth direction is adjusted. Based on the original planned path of the first robot, a feasible motion path is planned for it as the adjusted first planned path.

[0088] Figure 7 is a schematic structural diagram of a device provided by an exemplary embodiment. Figure 7 At the hardware level, the device includes a processor 702, an internal bus 704, a network interface 706, a memory 708, and a non-volatile memory 710, and may also include hardware required for other functions. One or more embodiments of this specification may be implemented based on software, such as the processor 702 reading the corresponding computer program from the non-volatile memory 710 into the memory 708 and then running it. Of course, in addition to the software implementation, one or more embodiments of this specification do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0089] Corresponding to the above-mentioned embodiment of the path planning method of the robot arm, this specification also provides an embodiment of the path planning device of the robot arm. Figure 8 ; The device comprises:

[0090] The planned path acquisition unit 802 is used to acquire a first planned path of the first robotic arm and a second planned path of the second robotic arm, wherein the first planned path and the second planned path belong to the same space-time region.

[0091] The particle generation unit 804 is used to divide the space-time region into a plurality of sub-regions, and determine each first-type sub-region to which the first planned path belongs and each second-type sub-region to which the second planned path belongs.

[0092] The planned path adjustment unit 806 is used to adjust the first planned path and / or the second planned path according to the overlapping sub-area when the first type of sub-area and the second type of sub-area include the same overlapping sub-area, so that the adjusted first planned path and the second planned path do not conflict with each other.

[0093] Optionally, the spatiotemporal region includes a spatial range;

[0094] The particle generation unit 804 is specifically used to: divide the spatial range into a plurality of spatial sub-ranges; determine each first-type spatial sub-range to which the first planned path belongs and each second-type spatial sub-range to which the second planned path belongs;

[0095] The planned path adjustment unit 806 is specifically used to: the first type of time sub-interval and the second type of time sub-interval contain the same spatial overlapping sub-range, and the spatial overlapping sub-range is the same spatial range occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths.

[0096] Optionally, the spatiotemporal region includes a time interval;

[0097] The particle generation unit 804 is specifically used to: divide the time interval into a plurality of time sub-intervals; determine each first-type time sub-interval to which the first planned path belongs and each second-type time sub-interval to which the second planned path belongs;

[0098] The planned path adjustment unit 806 is specifically used to: the first type of time sub-interval and the second type of time sub-interval contain the same time overlapping sub-interval, and the time overlapping sub-interval is the same time interval occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths.

[0099] Optionally, the space-time region includes a spatial range and a time interval;

[0100] The particle generation unit 804 is specifically used to: divide the spatial range into a plurality of spatial sub-ranges and a plurality of time sub-intervals respectively; determine each first-class spatial sub-range and each first-class time sub-interval to which the first planned path belongs, and each second-class spatial sub-range and each second-class time sub-interval to which the second planned path belongs;

[0101] The planned path adjustment unit 806 is specifically used for: the first type of time sub-interval and the second type of time sub-interval contain the same spatial overlapping sub-range, the first type of time sub-interval and the second type of time sub-interval contain the same time overlapping sub-interval, the spatial overlapping sub-range is the same spatial range occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths, and the time overlapping sub-interval is the same time interval occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths.

[0102] Optionally, the planned path adjustment unit 806 is specifically configured to:

[0103] acquiring a motion posture of the second robotic arm in the overlapping sub-area as a dynamic obstacle for the first robotic arm, and adjusting the first planned path according to a fast exploration random tree algorithm and the dynamic obstacle; or,

[0104] acquiring a motion posture of the first robotic arm in the overlapping sub-area as a dynamic obstacle for the second robotic arm, and adjusting the second planned path according to a fast exploration random tree algorithm and the dynamic obstacle; or,

[0105] The first planned path and the second planned path are adjusted simultaneously according to an optimization algorithm or a machine learning technique.

[0106] Optionally, the planned path acquisition unit 802 is specifically used to: acquire an operation process of a target operation to be performed by the first robot arm, and determine the first planned path according to the operation process;

[0107] Alternatively, multiple target operations matching the first robotic arm are selected from a set of candidate operations associated with the first robotic arm, and the first planned path is determined according to the multiple target operations and their execution order.

[0108] Optionally, the device further comprises:

[0109] An environmental adjustment unit, used to adjust the first planned path and / or the second planned path according to environmental obstacles other than any one of the robotic arms

[0110] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing processor executable instructions; wherein the processor implements the steps of the method described in any of the above embodiments by running the executable instructions.

[0111] Based on the same concept as the above method, this specification also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0112] Based on the same concept as the above method, this specification also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any of the above embodiments when executed by a processor.

[0113] Although the present invention includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of the specific embodiments of specific inventions. Certain features described in multiple embodiments of the present invention may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claimed as such, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of a sub-combination.

[0114] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or requiring that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0115] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0116] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A path planning method for a robotic arm, characterized in that: The method comprises: Acquire a first planned path of the first robotic arm and a second planned path of the second robotic arm, wherein the first planned path and the second planned path belong to the same space-time region; Dividing the spatiotemporal region into a plurality of sub-regions, and determining each first-category sub-region to which the first planned path belongs and each second-category sub-region to which the second planned path belongs; In the case where the first type of sub-area and the second type of sub-area include the same overlapping sub-area, the first planned path and / or the second planned path are adjusted according to the overlapping sub-area so that the adjusted first planned path and the second planned path do not conflict with each other.

2. The method according to claim 1, characterized in that The spatiotemporal region includes a spatial range; The dividing the spatiotemporal region into a plurality of sub-regions comprises: dividing the spatial range into a plurality of spatial sub-ranges; The determining of each first-category sub-area to which the first planned path belongs and each second-category sub-area to which the second planned path belongs includes: determining each first-category spatial sub-range to which the first planned path belongs and each second-category spatial sub-range to which the second planned path belongs; Among them, the first type of sub-area and the second type of sub-area contain the same overlapping sub-area, including: the first type of time sub-interval and the second type of time sub-interval contain the same spatial overlapping sub-range, and the spatial overlapping sub-range is the same spatial range occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths.

3. The method according to claim 1, characterized in that The space-time region includes a time interval; The dividing the spatiotemporal region into a plurality of sub-regions comprises: dividing the time interval into a plurality of time sub-intervals; The determining of each first-type sub-area to which the first planned path belongs and each second-type sub-area to which the second planned path belongs includes: determining each first-type time sub-interval to which the first planned path belongs and each second-type time sub-interval to which the second planned path belongs; Among them, the first type of sub-area and the second type of sub-area contain the same overlapping sub-area, including: the first type of time sub-interval and the second type of time sub-interval contain the same time overlapping sub-interval, and the time overlapping sub-interval is the same time interval occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths.

4. The method according to claim 1, characterized in that: The space-time region includes a spatial range and a time interval; The dividing the spatiotemporal region into a plurality of sub-regions comprises: dividing the spatial range into a plurality of spatial sub-ranges and a plurality of temporal sub-ranges respectively; The determining of each first-class sub-area to which the first planned path belongs and each second-class sub-area to which the second planned path belongs includes: determining each first-class spatial sub-range and each first-class time sub-interval to which the first planned path belongs, and each second-class spatial sub-range and each second-class time sub-interval to which the second planned path belongs; Among them, the first type of sub-area and the second type of sub-area contain the same overlapping sub-area, including: the first type of time sub-interval and the second type of time sub-interval contain the same spatial overlapping sub-range, the first type of time sub-interval and the second type of time sub-interval contain the same time overlapping sub-interval, the spatial overlapping sub-range is the same spatial range occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths, and the time overlapping sub-interval is the same time interval occupied by the first robotic arm and the second robotic arm when performing corresponding actions according to their respective planned paths.

5. The method according to claim 1, characterized in that The adjusting the first planned path according to the overlapping sub-area includes: obtaining the motion posture of the second robotic arm in the overlapping sub-area as a dynamic obstacle for the first robotic arm, and adjusting the first planned path according to the fast exploration random tree algorithm and the dynamic obstacle; or, The adjusting the second planned path according to the overlapping sub-area includes: obtaining the motion posture of the first robotic arm in the overlapping sub-area as a dynamic obstacle for the second robotic arm, and adjusting the second planned path according to the fast exploration random tree algorithm and the dynamic obstacle; or, The adjusting the first planned path and the second planned path according to the overlapping sub-area includes: adjusting the first planned path and the second planned path simultaneously according to an optimization algorithm or a machine learning technique.

6. The method according to claim 1, characterized in that The obtaining of a first planned path of the first robotic arm includes: Acquire an operation process of a target operation to be performed by the first robotic arm, and determine the first planned path according to the operation process; Alternatively, multiple target operations matching the first robotic arm are selected from a set of candidate operations associated with the first robotic arm, and the first planned path is determined according to the multiple target operations and their execution order.

7. The method according to claim 1, characterized in that The method further comprises: The first planned path and / or the second planned path are adjusted according to environmental obstacles other than any one of the robotic arms.

8. An electronic device, characterized in that: include: processor; A memory for storing processor-executable instructions; wherein the processor implements the steps of the method according to any one of claims 1 to 7 by executing the executable instructions.

9. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The method comprises a computer program / instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

Images