Six-axis industrial mechanical arm path planning method and device based on improved RRT algorithm

Abstract

The invention discloses a six-axis industrial mechanical arm path planning method and device based on an improved RRT algorithm, and the method comprises the steps: firstly constructing a sampling limiting region, carrying out the adaptive optimization expansion of a random tree in the limiting region through a target bias strategy, generating a new node, and carrying out the collision detection; thirdly, constructing an angle constraint area by adopting an angle constraint strategy, judging whether the new node is in the area or not, and if not, re-sampling to generate the new node as a father node for next planning; then, whether the distance between the new node and the target point is smaller than a set threshold value or not is judged, if yes, whether an obstacle exists or not is further judged, and if no obstacle exists, the new node is directly connected with the target point to generate an initial path; and finally, removing redundant points in the initial path to obtain a planned path. The invention aims to reduce the randomness in the search process and improve the quality and efficiency of path planning.

Description

Technical Field

[0001] The present invention belongs to the technical field of robot arm path planning, and in particular relates to a six-axis industrial robot arm path planning method and device based on an improved RRT algorithm. Background Art

[0002] As a basic and key topic in the research of six-axis industrial robotic arms, path planning technology aims to solve the problem of how to find an optimal motion path that connects the starting point to the target point and avoids all obstacles according to certain evaluation criteria in a working environment with obstacles. Many scholars at home and abroad have conducted in-depth analysis and research in the field of path planning and proposed a variety of algorithms and technical solutions. Among them, the RRT (Rapidly-exploring Random Tree) algorithm has the advantages of probabilistic completeness, strong versatility and easy implementation, especially when dealing with high-dimensional space problems. It has been widely welcomed in the field of robotic arm path planning. However, the RRT algorithm also has some significant disadvantages, such as the large randomness in the search process, which leads to a slow search speed, and the generated path is often tortuous and the path quality is not high.

[0003] In order to overcome these defects of the RRT algorithm and further improve the algorithm efficiency and path quality, domestic and foreign scholars have conducted a lot of improvement research. For example, someone proposed the RRT* algorithm, which effectively improved the length of the path by reselecting the parent node and rewiring strategies, but this improvement also increased the time cost of path planning and affected the real-time performance of the algorithm. Some people proposed a bidirectional RRT algorithm, which accelerated the search speed of the algorithm by expanding two trees from both ends of the starting point and the target point. However, this method is still essentially a global random search, and the quality of the planned path is not ideal. In addition, some scholars have tried to combine other algorithms with the RRT algorithm in order to obtain better planning results, such as introducing the idea of ​​artificial potential field into the RRT algorithm, and shortening the overall path planning time by improving the growth direction of the random tree. However, this method still cannot avoid the algorithm from exploring too much useless space, resulting in a waste of computing resources. Or combining the RRT algorithm with the reinforcement learning algorithm, although it improves the feasibility of planning, it also greatly increases the amount of calculation of the algorithm, which is not conducive to real-time application.

[0004] In summary, although the current research on improving the RRT algorithm has achieved certain results, these improvement methods are mainly focused on improving the convergence speed of the algorithm and improving the path length. There is still a lack of effective optimization methods for the core problem of excessive sampling randomness and poor quality of the planned path in the RRT algorithm. Therefore, how to further improve the RRT algorithm, reduce the randomness in its search process, and improve the quality and efficiency of path planning is still an important issue that needs to be solved in the current path planning field. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention provides a six-axis industrial robot arm path planning method and device based on an improved RRT algorithm, which aims to reduce the randomness in its search process and improve the quality and efficiency of path planning.

[0006] In order to solve the above technical problems, the present invention is implemented by the following technical solutions: According to a first aspect of the present invention, a six-axis industrial robot arm path planning method based on an improved RRT algorithm is provided, comprising: S1, construct a sampling restriction area, use the target bias strategy to perform adaptive optimization and expansion of the random tree in the restriction area, generate new nodes, and determine whether the new nodes pass the collision detection. If they pass, execute S2. If they do not pass, re-sample in the restriction area until they pass. S2, construct an angle constraint region using the angle constraint strategy, and determine whether the new node in S1 is within the angle constraint region; if so, use the new node in S1 as the parent node for the next planning; if not, resample and generate a new node within the angle constraint region, and use the node as the parent node for the next planning; S3, determine whether the distance between the new node generated in S2 and the target point is less than the set threshold; if not, return to S1 to continue the adaptive optimization and expansion of the random tree; if less, determine whether there is an obstacle between the new node generated in S2 and the target point; if there is an obstacle, return to S1 to continue the adaptive optimization and expansion of the random tree, if there is no obstacle, directly connect the new node generated in S2 to the target point, complete the search and generate the initial path; S4. Remove redundant points in the initial path to obtain the planned path.

[0007] In a possible implementation manner of the first aspect, constructing a sampling restriction area specifically includes: Determine sampling points And the parent node closest to the sampling point in the random tree , connect the target points With parent node , with the target point With parent node The formed line segment is used as the diameter to construct a circle, and this area is the sampling restriction area.

[0008] In a possible implementation manner of the first aspect, the adaptive optimization expansion of the random tree in the restricted area using the target bias strategy is specifically: Set a threshold , which ranges from (0, 1); When the random tree selects sampling points When a random number between (0, 1) is generated ; like , then set the sampling point to the target point Perform target bias sampling; like , random sampling is performed.

[0009] In a possible implementation manner of the first aspect, the adopting the angle constraint strategy to construct the angle constraint area is specifically: The starting point Respectively with the parent node and target point Connect them to get the angle constraint area.

[0010] In a possible implementation manner of the first aspect, the adaptive optimization expansion of the random tree is specifically: The distance between the node and the obstacle To determine the step length and set the first level safety distance , Secondary safety distance And three different step sizes, three different step sizes are large step sizes , Normal step length and small step length ; When the distance between the node and the obstacle Greater than secondary safety distance When using a large step size ; When the distance between the node and the obstacle Between the first safety distance Secondary safety distance When the normal step length is used ; When the distance between the node and the obstacle Less than the first level safety distance When using a small step size .

[0011] In a possible implementation manner of the first aspect, removing redundant points in the initial path specifically includes: Traverse the nodes in the initial path. Assume that the nodes from the starting point to the target point in the initial path are numbered from 1 to n. Starting from the first path node, connect the subsequent nodes in the path in order. If there is no collision with an obstacle when connecting with nodes 1 and 2, try to connect the next node until an obstacle is encountered and a collision occurs when connecting with the mth node. At this time, directly connect node 1 with node m-1, and use node m-1 as the new starting point. Repeat the above process and iterate until the target point is reached. <m<n。

[0012] In a possible implementation manner of the first aspect, after removing the redundant points in the initial path, the method further includes: The fitting process is performed with a cubic B-spline curve.

[0013] According to a second aspect of the present invention, there is provided a device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for path planning of a six-axis industrial robot arm based on an improved RRT algorithm is implemented.

[0014] According to a third aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the six-axis industrial robot arm path planning method based on the improved RRT algorithm is implemented.

[0015] According to a fourth aspect of the present invention, a computer program product is provided, which, when executed by a processor, implements the six-axis industrial robot arm path planning method based on the improved RRT algorithm.

[0016] Compared with the prior art, the present invention has at least the following beneficial effects: The present invention provides a six-axis industrial robot path planning method based on an improved RRT algorithm. By constructing a sampling restriction area and adopting a target bias strategy, a random tree is guided to grow toward a target point with a certain probability, and the expansion of the random tree is limited to a specific area. This improvement effectively solves the problem of excessive randomness of the traditional RRT algorithm, reduces the exploration of the algorithm in useless space, and significantly improves the efficiency and convergence speed of path planning. The traditional RRT algorithm uses a fixed step size to expand the random tree, and the exploration efficiency is limited. The present invention adaptively optimizes the expansion of the random tree, makes full use of the information of the environment and obstacles, and dynamically adjusts the expansion direction and step size of the node, thereby accelerating the generation and expansion speed of the node, and further improving the exploration efficiency of the algorithm. An angle constraint strategy is introduced to construct an angle constraint area to ensure that the newly generated node is expanded under the condition of satisfying the motion constraints of the robot. This strategy effectively avoids the problem of tortuous paths and many inflection points generated by the traditional RRT algorithm, and improves the smoothness and executability of the path. The path generated by the traditional RRT algorithm usually contains a large number of redundant points and inflection points, resulting in a tortuous and non-smooth path. After generating the initial path, the present invention performs smooth optimization processing on the path by removing redundant points, so that the final planned path is more concise and smooth, ensuring that the robot arm can smoothly and efficiently complete the task during operation. The present invention significantly reduces the computational complexity of the algorithm by reducing randomness, optimizing path generation and expansion strategies, and improves the real-time performance of path planning, so that the present invention can better meet the real-time path planning requirements of the six-axis industrial robot arm in practical applications. In summary, the present invention effectively solves the problems of high randomness, poor path quality, and low computational efficiency of the traditional RRT algorithm by improving the sampling strategy, expansion method, and path optimization method of the RRT algorithm, and significantly improves the efficiency and path quality of the path planning of the six-axis industrial robot arm.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the specific implementation modes of the present invention, the drawings required for use in the description of the specific implementation modes will be briefly introduced below. Obviously, the drawings described below are some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is an overall flow chart of a six-axis industrial robot arm path planning method based on an improved RRT algorithm according to an embodiment of the present invention; Figure 2 A schematic diagram of a restricted area of ​​a sampling point in an embodiment; Figure 3 Schematic diagram of angle limitation of sampling points in an embodiment; Figure 4 It is a schematic diagram of adaptive optimization expansion of an embodiment; Figure 5 This is a schematic diagram of redundant point removal in secondary optimization of the path of the embodiment; Figure 6 Schematic diagram of the secondary optimization smoothing process of the path in the embodiment. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Combination Figure 1 As shown, an embodiment of the present invention provides a path planning method for a six-axis industrial robot arm based on an improved RRT algorithm. In view of the problem that the traditional RRT algorithm has weak purpose and excessive exploration of useless spatial areas, the algorithm is enhanced in goal orientation by introducing a sampling area restriction strategy, thereby avoiding the random tree from exploring unnecessary spatial areas and reducing the generation of useless nodes. Secondly, the adaptive optimization expansion strategy is combined to accelerate the convergence of the random tree and reduce the path generation time. Finally, the initially planned path is subjected to secondary optimization processing to improve the path quality. Specifically, the following steps are included: S1, construct a sampling restriction area, use the target bias strategy to perform adaptive optimization and expansion of the random tree in the restriction area, generate new nodes, and determine whether the new nodes pass the collision detection. If they pass, execute S2. If they do not pass, re-sample in the restriction area until they pass.

[0022] like Figure 2 As shown, after sampling in space through the target bias strategy, the sampling restriction area is constructed as follows: Determine the sampling point And the parent node closest to the sampling point in the random tree , connect the target points With parent node , with the target point With parent node The formed line segment is used as the diameter to construct a circle, and this area is the sampling restriction area.

[0023] The sampling area restriction strategy is introduced to enhance the goal orientation of the algorithm. First, the target bias strategy is introduced to make the random tree grow towards the target point with a certain probability, enhance the target tendency of the random tree expansion, and improve the efficiency of the algorithm. Specifically, the target bias strategy is used to perform adaptive optimization and expansion of the random tree in the restricted area, specifically: set a threshold , which ranges from (0, 1); when the random tree selects the sampling point When a random number between (0, 1) is generated ;like , then set the sampling point to the target point Perform target bias sampling; if , random sampling is performed.

[0024]

[0025] Specifically, the adaptive optimization extension of random trees is as follows: The distance between the node and the obstacle To determine the step length and set the first level safety distance , Secondary safety distance And three different step sizes, three different step sizes are large step sizes , Normal step length and small step length ; When the distance between the node and the obstacle Greater than secondary safety distance When using a large step size , speeding up the exploration of the random tree to the unknown environment; when the distance between the node and the obstacle Between the first safety distance Secondary safety distance When the normal step length is used ; When the distance between the node and the obstacle Less than the first level safety distance When using a small step size , enhancing the ability of random trees to explore complex environments.

[0026]

[0027] The adaptive optimization expansion strategy can better expand new nodes according to different environments, enhance the algorithm's exploration ability and reduce invalid searches, thereby improving the efficiency of the algorithm.

[0028] S2. Use the angle constraint strategy to construct the angle constraint area and determine whether the new node in S1 is within the angle constraint area. If so, use the new node in S1 as the parent node for the next planning. If not, resample and generate a new node within the angle constraint area and use the node as the parent node for the next planning.

[0029] That is to say, after obtaining new nodes through region restriction, further optimization judgment is made on them according to the angular restriction conditions, as Figure 3 shown. Specifically, the angular constraint strategy is adopted to construct an angular constraint region, specifically: the starting point is respectively connected to the parent node and the target point to obtain the angular constraint region.

[0030] By restricting the sampling region, the exploration of the random tree for invalid space can be effectively reduced, and as the parent node continuously approaches the target point, the sampling region is continuously restricted and compressed, thereby accelerating the convergence speed of the algorithm.

[0031] S3. Judge whether the distance between the new node generated in S2 and the target point is less than the set threshold; if not less, return to S1 to continue the adaptive optimization expansion of the random tree; if less, judge whether there is an obstacle between the new node generated in S2 and the target point; if there is an obstacle, return to S1 to continue the adaptive optimization expansion of the random tree, if there is no obstacle, directly connect the new node generated in S2 and the target point, and there is no step size limit when directly connecting, and the search is completed and the initial path is generated, as Figure 4 shown.

[0032] S4. Remove the redundant points in the initial path and perform fitting processing with a cubic B-spline curve to obtain the final planned path.

[0033] Specifically, as Figure 5 shown, removing the redundant points in the initial path is specifically: Traverse the nodes in the initial path. Suppose the node numbers from the starting point to the target point in the initial path are 1 to n. Then starting from the first path node, connect the subsequent nodes in the path in sequence. If there is no collision with an obstacle when connecting between the 1st and 2nd nodes, try to connect the next node until a collision occurs with an obstacle when connecting to the mth node (1 < m < n). At this time, directly connect the 1st node and the (m - 1)th node, and take the (m - 1)th node as the new starting point, and repeat the above process for iteration until reaching the target point.

[0034] After removing the redundant points in the path, there will still be some inflection points in the path. To ensure the smoothness of the planned motion path, the path is fitted and optimized with a cubic B-spline to generate a path with better smoothness. The B-spline curve is a linear combination based on the B-spline basis function, and its k-order B-spline curve formula is as shown below.

[0035]

[0036] Among them, is the node vector, is the control point, is the basis function of the k-order B-spline curve, and its formula is as follows.

[0037]

[0038] In the cubic B-spline curve, the knot vector is set to a non-decreasing set, that is, ,in , , so the basis function can be obtained from formula (5), as shown below.

[0039]

[0040] So we can get the formula of cubic B-spline curve as follows.

[0041]

[0042] like Figure 6 As shown, the path after redundancy removal is fitted with a cubic B-spline curve, which effectively removes the inflection points in the path and makes the turning points of the path smoother.

[0043] To sum up, the present invention can solve the problem that the existing path planning methods are limited to convergence speed and path length, and cannot effectively deal with the problems of excessive randomness of the algorithm itself and poor quality of the planned path. It can be widely used in various working scenarios of six-axis industrial robot arms and has certain theoretical research and practical application value.

[0044] In another embodiment of the present invention, a computer device is provided, the computer device including a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a six-axis industrial robot arm path planning method based on an improved RRT algorithm.

[0045] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the above-mentioned embodiment regarding a six-axis industrial robot path planning method based on an improved RRT algorithm.

[0046] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0047] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0048] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0049] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0050] The present invention also provides a computer program product, which is used to execute any of the above-mentioned six-axis industrial robot arm path planning methods based on the improved RRT algorithm. Since the computer program product provided by the present invention and the above-mentioned six-axis industrial robot arm path planning method based on the improved RRT algorithm belong to the same inventive concept, the computer program product provided by the present invention has all the advantages of the above-mentioned six-axis industrial robot arm path planning method based on the improved RRT algorithm, so the beneficial effects of the computer program product provided by the present invention will not be described one by one here.

[0051] In the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0052] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A six-axis industrial robot path planning method based on an improved RRT algorithm, characterized in that: include: S1, construct a sampling restriction area, use the target bias strategy to perform adaptive optimization and expansion of the random tree in the restriction area, generate new nodes, and determine whether the new nodes pass the collision detection. If they pass, execute S2. If they do not pass, re-sample in the restriction area until they pass. S2, construct an angle constraint region using the angle constraint strategy, and determine whether the new node in S1 is within the angle constraint region; if so, use the new node in S1 as the parent node for the next planning; if not, resample and generate a new node within the angle constraint region, and use the node as the parent node for the next planning; S3, determine whether the distance between the new node generated in S2 and the target point is less than the set threshold; if not, return to S1 to continue the adaptive optimization and expansion of the random tree; If it is less than, determine whether there is an obstacle between the new node generated in S2 and the target point; if there is an obstacle, return to S1 to continue the adaptive optimization and expansion of the random tree; if there is no obstacle, directly connect the new node generated in S2 to the target point, complete the search and generate the initial path; S4. Remove redundant points in the initial path to obtain the planned path.

2. According to claim 1, a six-axis industrial robot arm path planning method based on an improved RRT algorithm is characterized in that: The construction of the sampling restriction area is specifically as follows: Determine sampling points And the parent node closest to the sampling point in the random tree , connect the target points With parent node , with the target point With parent node The formed line segment is used as the diameter to construct a circle, and this area is the sampling restriction area.

3. According to claim 1, a six-axis industrial robot arm path planning method based on an improved RRT algorithm is characterized in that: The target bias strategy is used to perform adaptive optimization and expansion of random trees in a restricted area, specifically: Set a threshold , which ranges from (0, 1); When the random tree selects sampling points When a random number between (0, 1) is generated ; like , then set the sampling point to the target point Perform target bias sampling; like , random sampling is performed.

4. According to claim 1, a six-axis industrial robot arm path planning method based on an improved RRT algorithm is characterized in that: The angle constraint strategy is used to construct the angle constraint area, specifically: The starting point Respectively with the parent node and target point Connect them to get the angle constraint area.

5. The six-axis industrial robot arm path planning method based on the improved RRT algorithm according to claim 1 is characterized in that: The adaptive optimization extension of the random tree is specifically: The distance between the node and the obstacle To determine the step length and set the first level safety distance , Secondary safety distance And three different step sizes, three different step sizes are large step sizes , Normal step length and small step length ; When the distance between the node and the obstacle Greater than secondary safety distance When using a large step size ; When the distance between the node and the obstacle Between the first safety distance Secondary safety distance When the normal step length is used ; When the distance between the node and the obstacle Less than the first safety distance When using a small step size .

6. A six-axis industrial robot arm path planning method based on an improved RRT algorithm according to claim 1, characterized in that: The method of removing redundant points in the initial path is specifically as follows: Traverse the nodes in the initial path. Assume that the nodes from the starting point to the target point in the initial path are numbered from 1 to n. Starting from the first path node, connect the subsequent nodes in the path in order. If there is no collision with an obstacle when connecting with nodes 1 and 2, try to connect the next node until an obstacle is encountered and a collision occurs when connecting with the mth node. At this time, directly connect node 1 with node m-1, and use node m-1 as the new starting point. Repeat the above process and iterate until the target point is reached. <m<n。 7. The six-axis industrial robot arm path planning method based on the improved RRT algorithm according to claim 1 is characterized in that: After removing the redundant points in the initial path, the method further includes: The fitting process is performed with a cubic B-spline curve.

8. A device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the six-axis industrial robot arm path planning method based on the improved RRT algorithm as described in any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the six-axis industrial robot arm path planning method based on the improved RRT algorithm as described in any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that When the computer program product is executed by a processor, it implements a six-axis industrial robot arm path planning method based on an improved RRT algorithm as described in any one of claims 1 to 7.

Images