Dynamic path planning method and device, storage medium and electronic equipment

Abstract

The invention provides a dynamic path planning method and device, a storage medium and electronic equipment, and the method comprises the steps: carrying out the up-sampling path planning and path planning in stages according to a path point feasibility strategy or a whole path reachable strategy, carrying out the iteration updating of a real-time search step size, and finally obtaining a target path which the whole path can reach. By adopting an up-sampling strategy, the algorithm does not need manual debugging and optimal step length setting any more, the long-standing problem of step length selection in the path planning method based on random sampling is solved, and the efficiency of path planning and post-processing is improved. Therefore, the real-time requirement of the series robot for intelligent autonomous obstacle avoidance in a dynamic environment is met. And meanwhile, by deleting redundant path points, the path length can be gradually shortened by dynamically simplifying the path.

Description

Technical Field

[0001] The present invention relates to the field of robot motion planning. Specifically, it relates to a dynamic path planning method, device, storage medium, and electronic device. Background Art

[0002] Serial robots have been widely used in many fields such as manufacturing, logistics, and environmental monitoring due to their flexibility and high precision. As one of the key technologies for serial robots to achieve autonomous navigation and efficient operation, dynamic path planning technology has received extensive attention and research in recent years. The dynamic path planning technology aims to calculate and optimize an optimal or sub-optimal path in real time based on the current position of the robot, the target position, and the obstacle information in the environment. This technology not only requires the path planning algorithm to be efficient and accurate, but also needs to be able to cope with the dynamic changes in the environment, such as the movement of obstacle positions and the emergence of new obstacles. With the continuous progress of artificial intelligence and machine learning technologies, the dynamic path planning technology of serial robots is also constantly developing, from traditional graph search-based algorithms such as the A* algorithm and the Dijkstra algorithm to the intelligent path planning methods based on reinforcement learning and deep learning that have emerged in recent years. The introduction of these technologies has greatly improved the dynamic path planning ability of serial robots in complex environments.

[0003] Although serial robots have made significant progress in dynamic path planning, there are still many technical challenges in real-time obstacle avoidance planning. Therefore, developing a real-time obstacle avoidance planning algorithm that can not only efficiently handle dynamic environments but also fully consider the physical characteristics of the robot is of great significance for improving the autonomous navigation and operation capabilities of serial robots. Summary of the Invention

[0004] The purpose of the present invention is to provide a dynamic path planning method, device, storage medium, and electronic device to improve the above problems.

[0005] To achieve the above purpose, the technical solutions adopted in the embodiments of the present invention are as follows: In a first aspect, an embodiment of the present invention provides a dynamic path planning method, the method includes: Perform first-class upsampling path planning according to the path point feasibility strategy, based on the real-time search step size and the basic path, to obtain a first-class upsampling path; Perform dynamic path simplification on the first-class upsampling path, delete the redundant points therein, and use the simplified path as the new basic path; Perform shortening update based on the current real-time search step size to obtain a new real-time search step size; If the new real-time search step size is greater than or equal to the step size threshold, then repeat the first type of upsampling path planning according to the path point feasibility strategy, based on the real-time search step size and the basic path, to obtain the first type of upsampling path; If the new real-time search step size is less than the step size threshold, then perform the second type of upsampling path planning according to the entire path reachability strategy, based on the new real-time search step size and the basic path, to obtain the second type of upsampling path; Perform dynamic path simplification on the second type of upsampling path, deleting the redundant points therein, to obtain the target path that is reachable for the entire path.

[0006] In a second aspect, an embodiment of the present invention provides a dynamic path planning device, which includes: A first processing unit, configured to perform the first type of upsampling path planning according to the path point feasibility strategy, based on the real-time search step size and the basic path, to obtain the first type of upsampling path; A second processing unit, configured to perform dynamic path simplification on the first type of upsampling path, deleting the redundant points therein, and using the simplified path as the new basic path; The first processing unit is further configured to perform shortening update based on the current real-time search step size to obtain a new real-time search step size; The first processing unit is further configured to, if the new real-time search step size is greater than or equal to the step size threshold, then repeat the first type of upsampling path planning according to the path point feasibility strategy, based on the real-time search step size and the basic path, to obtain the first type of upsampling path; The first processing unit is further configured to, if the new real-time search step size is less than the step size threshold, then perform the second type of upsampling path planning according to the entire path reachability strategy, based on the new real-time search step size and the basic path, to obtain the second type of upsampling path; The second processing unit is further configured to perform dynamic path simplification on the second type of upsampling path, deleting the redundant points therein, to obtain the target path that is reachable for the entire path.

[0007] In a third aspect, an embodiment of the present invention provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented.

[0008] In a fourth aspect, an embodiment of the present invention provides an electronic device, which includes: a processor and a memory, where the memory is used to store one or more programs; when the one or more programs are executed by the processor, the above method is implemented.

[0009] Compared with the prior art, a dynamic path planning method, device, storage medium and electronic device provided by an embodiment of the present invention perform first-class up-sampling path planning according to a path point feasibility strategy, based on a real-time search step and a basic path, to obtain a first-class up-sampled path; perform dynamic path simplification on the first-class up-sampled path, delete redundant points therein, and use the simplified path as a new basic path; perform shortening update based on the current real-time search step to obtain a new real-time search step; if the new real-time search step is greater than or equal to the step threshold, repeat performing first-class up-sampling path planning according to the path point feasibility strategy, based on the real-time search step and the basic path, to obtain a first-class up-sampled path; if the new real-time search step is less than the step threshold, perform second-class up-sampling path planning according to an entire path reachability strategy, based on the new real-time search step and the basic path, to obtain a second-class up-sampled path; perform dynamic path simplification on the second-class up-sampled path, delete redundant points therein, to obtain a target path that can reach the entire path. By adopting the up-sampling strategy, the algorithm no longer requires manual debugging and setting of the optimal step size, solves the long-existing step size selection problem in such path planning methods based on random sampling, and realizes the improvement of the efficiency of path planning and post-processing to meet the real-time requirements of a serial robot for intelligent autonomous obstacle avoidance in a dynamic environment. At the same time, by deleting redundant path points, path dynamic simplification can gradually shorten the path length.

[0010] To make the above objects, features and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0013] Figure 2 It is one of the schematic flowcharts of the dynamic path planning method provided by an embodiment of the present invention.

[0014] Figure 3 It is an iterative schematic diagram of up-sampling path planning provided by an embodiment of the present invention.

[0015] Figure 4 It is a schematic diagram of dynamic path simplification provided by an embodiment of the present invention.

[0016] Figure 5 This is the second flowchart diagram of the dynamic path planning method provided by the embodiments of the present invention.

[0017] Figure 6 This is the unit diagram of the dynamic path planning device provided by the embodiments of the present invention.

[0018] In the figure: 10 - processor; 11 - memory; 12 - bus; 13 - communication interface; 501 - first processing unit; 502 - second processing unit. Detailed implementation manners

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. Components of the embodiments of the present invention usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present invention, terms such as "first", "second", etc. are only used for differential description and cannot be understood as indicating or implying relative importance.

[0022] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprises", "comprising", or any other variation thereof is intended to cover a non - exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0023] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the inventive product is customarily placed during use. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0024] In the description of the present invention, it should also be noted that unless otherwise clearly specified and defined, the terms "arrangement" and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] The following will describe in detail some embodiments of the present invention with reference to the drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0026] When a serial robot performs a dynamic obstacle avoidance task, it often needs to consider the position change of obstacles. How to effectively avoid obstacles while ensuring real-time performance is an important challenge. Secondly, real-time obstacle avoidance planning also needs to consider the performance of the planning result. If there are too many redundant points, it will significantly affect the movement efficiency of the robot. These challenges require that the real-time obstacle avoidance planning algorithm of the serial robot not only has a high degree of intelligence and adaptability, but also needs to be able to efficiently handle the obstacle avoidance planning problem and make quick and accurate decisions.

[0027] The embodiment of the present invention provides a dynamic path planning method, which adopts an upsampling strategy, so that the algorithm no longer needs to be manually debugged and set the optimal step size, solves the long-existing step size selection problem in such path planning methods based on random sampling, and realizes the improvement of the efficiency of path planning and post-processing to meet the real-time requirements of intelligent autonomous obstacle avoidance of serial robots in a dynamic environment.

[0028] The embodiment of the present invention provides an electronic device, which can be a mobile phone device, a computer device, and a server device. The electronic device can maintain a communication connection with the robot, or the electronic device is the central control device of the robot. Please refer to Figure 1 , the structural schematic diagram of the electronic device. The electronic device includes a processor 10, a memory 11, and a bus 12. The processor 10 and the memory 11 are connected through the bus 12, and the processor 10 is used to execute the executable module stored in the memory 11, such as a computer program.

[0029] The processor 10 may be an integrated circuit chip having signal processing capabilities. In the implementation process, each step of the dynamic path planning method may be completed by an integrated logic circuit of hardware in the processor 10 or by instructions in the form of software. The above-mentioned processor 10 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components.

[0030] The memory 11 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory.

[0031] The bus 12 may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. Figure 1 Although only one bidirectional arrow is used in the figure, it does not mean that there is only one bus 12 or only one type of bus 12 .

[0032] The memory 11 is used to store programs, such as programs corresponding to the dynamic path planning device. The dynamic path planning device includes at least one software function module that can be stored in the memory 11 in the form of software or firmware or fixed in the operating system (OS) of the electronic device. After receiving the execution instruction, the processor 10 executes the program to implement the dynamic path planning method.

[0033] Possibly, the electronic device provided by the embodiment of the present invention further includes a communication interface 13. The communication interface 13 is connected to the processor 10 via a bus.

[0034] It should be understood that Figure 1 The structure shown is only a schematic diagram of a portion of the electronic device. The electronic device may also include Figure 1more or fewer components as shown, or having a configuration different from that Figure 1 shown. Figure 1 Each component shown in Figure 1 can be implemented by hardware, software, or a combination thereof.

[0035] A dynamic path planning method provided by an embodiment of the present invention can be, but is not limited to, applied to Figure 1 the electronic device shown. For the specific process, please refer to Figure 2 . The dynamic path planning method includes: S21, S22, S23, S24, S25, and S26, which are specifically described as follows.

[0036] S21. According to the path point feasibility strategy, perform first-class upsampling path planning based on the real-time search step size and the basic path to obtain a first-class upsampling path.

[0037] It should be noted that when there are obstacles on the linear path from the starting point to the ending point in the joint space, the linear path from the starting point to the ending point cannot be directly adopted. In this case, S21 can be executed.

[0038] When performing the first-class upsampling path planning for the first time, the real-time search step size can be a preset step size, or the real-time search step size can be determined according to the length of the linear path from the starting point to the ending point in the joint space and the search step size scaling factor.

[0039] When performing the first-class upsampling path planning for the first time, the basic path is empty, that is, there is no constraint condition of the basic path.

[0040] The path point feasibility strategy is used to ensure that there are no obstacles within the preset range of each path node on the first-class upsampling path.

[0041] S22. Perform dynamic path simplification on the first-class upsampling path, delete the redundant points therein, and use the simplified path as the new basic path.

[0042] It can be understood that the redundant points refer to the nodes that take a detour in the path.

[0043] S23. Perform shortening update on the basis of the current real-time search step size to obtain a new real-time search step size.

[0044] Among them, the new real-time search step size is smaller than the original real-time search step size.

[0045] Optionally, perform iterative update on the real-time search step size according to the search step size scaling factor to obtain a new real-time search step size.

[0046] In an alternative embodiment, the formula for the new real-time search step size is: S s1 = Ss0 / f s Wherein, S s1 represents the new real-time search step size, and S s0 represents the current real-time search step size, and f s represents the search step size scaling factor.

[0047] S24. Determine whether the new real-time search step size is less than the step size threshold. If the new real-time search step size is greater than or equal to the step size threshold, then repeat the execution of S21. According to the path point feasibility strategy, perform the first type of up-sampling path planning based on the real-time search step size and the basic path to obtain the first type of up-sampled path. If the new real-time search step size is less than the step size threshold, then execute S25.

[0048] S25. According to the whole path reachability strategy, perform the second type of up-sampling path planning based on the new real-time search step size and the basic path to obtain the second type of up-sampled path.

[0049] Wherein, the whole path reachability strategy is used to ensure that there are no obstacles within the preset range of each path node on the second type of up-sampled path, and there are no obstacles within the corresponding robotic arm movement sweeping space between any two adjacent path nodes.

[0050] S26. Perform dynamic path simplification on the second type of up-sampled path, and delete the redundant points therein to obtain the target path that is reachable for the whole path.

[0051] Wherein, there are no obstacles within the preset range of each path node on the target path, and there are no obstacles within the corresponding robotic arm movement sweeping space between any two adjacent path nodes. The target path is the joint space movement path of the robot. In the embodiment of the present invention, the starting point refers to the starting point in the joint space, and the ending point refers to the ending point in the joint space.

[0052] In the dynamic path planning method provided by the embodiment of the present invention, an up-sampling strategy is adopted, so that the algorithm no longer requires manual debugging and setting of the optimal step size, solves the long-existing step size selection problem in such path planning methods based on random sampling, and realizes the improvement of the efficiency of path planning and post-processing to meet the real-time requirements of a serial robot for intelligent autonomous obstacle avoidance in a dynamic environment. At the same time, by deleting redundant path points, path dynamic simplification can gradually shorten the path length.

[0053] In the early and middle stages, upsampling path planning is carried out with a large step size to quickly cover the search space, efficiently explore and identify a series of reachable intermediate path points. These intermediate path points act as a bridge between the starting point and the ending point, effectively decomposing the long-distance complex planning problem into a series of simpler sub-problems. In the early and middle stages, continuous collision detection will be skipped, and only the feasibility of the path points (whether there are obstacles within the preset range of the path nodes) will be judged, significantly reducing the computational complexity in the early and middle stages, so as to search for reachable path areas faster. When the step size is reduced below the preset step size threshold, according to the whole path reachability strategy, the last round of upsampling is carried out. During this round of search, continuous collision detection is required to ensure the reachability of the whole path, ensuring that there are no obstacles within the preset range of each path node on the second type of upsampling path, and there are no obstacles within the swept space corresponding to the movement of the robotic arm between any two adjacent path nodes.

[0054] During the planning process, path dynamic simplification can dynamically simplify the path after each round of upsampling planning. By deleting redundant path points, path dynamic simplification can gradually shorten the path length.

[0055] In an alternative embodiment, dynamic path simplification for the first type of upsampling path only considers the distance factor, and dynamic path simplification for the second type of upsampling path needs to consider both the distance factor and the collision factor to reduce the computational amount of continuous collision detection.

[0056] On the basis of Figure 2 , regarding the content in S21, the embodiments of the present invention also provide an alternative embodiment. Please refer to the following. S21, according to the path point feasibility strategy, perform the first type of upsampling path planning based on the real-time search step size and the basic path to obtain the first type of upsampling path, including: S211, S212, S213, S214, S215, and S216, which are specifically described as follows.

[0057] S211, according to the real-time search step size and the basic path, respectively expand the random search tree from the starting point and the ending point with the bidirectional connected rapid search random tree algorithm, and perform the first growth.

[0058] Among them, the bidirectional connected rapid search random tree algorithm is also called the RRT-Connect algorithm.

[0059] S212, after the random search tree completes the i-th growth, determine whether there is a matching node combination. If there is a matching node combination, execute S213; if there is no matching node combination, execute S215.

[0060] Among them, the distance between the starting-side node and the ending-side node in the matching node combination is less than or equal to the real-time search step size; the starting-side node is a node on the random search tree on the starting side, and the ending-side node is a node on the random search tree on the ending side.

[0061] S213, determine whether there is a current matching path that meets the first type of feasible conditions. If there is a current matching path that meets the first type of feasible conditions, execute S214; if there is no current matching path that meets the first type of feasible conditions, execute S215.

[0062] Among them, the current matching path is the path formed by splicing along the starting point to the starting-side node in the matching node combination and along the ending point to the ending-side node in the matching node combination, and the first type of feasible condition means that there are no obstacles within the preset range of each path node on the current matching path.

[0063] Among them, the preset range is the space range required for the robotic arm to occupy at the path node.

[0064] S214, if there is a current matching path that meets the first type of feasible conditions, use the current matching path with the shortest path length as the first type of up-sampling path.

[0065] The current matching path with the shortest path length is the current matching path with the fewest path nodes.

[0066] S215, let i = i + 1, and determine whether i is greater than the growth times threshold. If i is less than or equal to the growth times threshold, execute S216; if i is greater than the growth times threshold, determine that the path planning fails.

[0067] S216, perform the i-th growth.

[0068] After S216, repeat S212. After the i-th growth of the random search tree is completed, determine whether there is a matching node combination.

[0069] At Figure 2 On this basis, regarding the content in S22, the embodiments of the present invention also provide an optional implementation manner. Please refer to the following. S22, perform dynamic path simplification on the first type of up-sampling path, delete the redundant points therein, and use the simplified path as the new base path, including: S221, S222, S223, S224, S225, and S226, which are specifically described as follows.

[0070] S221, use the starting point of the first type of up-sampling path as the identification point.

[0071] S222. Determine whether the current recognition point meets the first type of simplification condition. If the current recognition point meets the first type of simplification condition, execute S223; if the current recognition point does not meet the first type of simplification condition, execute S224.

[0072] Among them, the first type of simplification condition means that within a preset range with the current recognition point as the center and the real-time search step length as the radius, there are points to be confirmed. The points to be confirmed are the nodes on the first type of up-sampling path that are sorted after the current recognition point and the sorting interval is greater than 1. S223. Take the next path node on the first type of up-sampling path that is sorted after the current recognition point and the first M-1 points to be confirmed corresponding to the current recognition point as redundant points and delete them. Take the Mth point to be confirmed after the current recognition point as the new recognition point.

[0073] Among them, M represents the number of points to be confirmed corresponding to the current recognition point.

[0074] It can be understood that the path nodes located after the simplified recognition point and before the last point to be confirmed are taken as redundant points and deleted. The last point to be confirmed is the one with the largest sorting on the first type of up-sampling path among the points to be confirmed corresponding to the simplified recognition point.

[0075] S224. Take the next node on the first type of up-sampling path that is sorted after the current recognition point as the new recognition point.

[0076] S225. After determining the new recognition point, judge whether the new recognition point is the end point of the first type of up-sampling path. If it is not the end point, repeat to execute S222 to determine whether the current recognition point meets the first type of simplification condition; if the new recognition point is the end point of the first type of up-sampling path, execute S226.

[0077] S226. Take the simplified path after deleting the redundant points as the new basic path.

[0078] Based on Figure 2 Regarding the content in S25, the embodiment of the present invention also provides an optional implementation manner. Please refer to the following text. S25. According to the entire path reachability strategy, perform the second type of up-sampling path planning based on the new real-time search step length and the basic path to obtain the second type of up-sampling path, including: S251, S252, S253, S254, S255, and S256, which are specifically described as follows.

[0079] S251. According to the real-time search step length and the basic path, respectively expand the random search tree from the starting point and the end point using the bidirectional connected fast search random tree algorithm for the first growth.

[0080] S252. After the \(i\) -th growth of the random search tree is completed, determine whether there is a matching node combination. If there is a matching node combination, execute S253; if there is no matching node combination, execute S255.

[0081] Among them, the distance between the start - side node and the end - side node in the matching node combination is less than or equal to the real - time search step; the start - side node is a node on the random search tree on the start side, and the end - side node is a node on the random search tree on the end side.

[0082] S253. Determine whether there is a current matching path that meets the second - type feasible condition. If there is a current matching path that meets the second - type feasible condition, execute S254; if there is no current matching path that meets the second - type feasible condition, execute S255.

[0083] Among them, the current matching path is the path formed by splicing along the start point to the start - side node in the matching node combination and along the end point to the end - side node in the matching node combination. The second - type feasible condition means that there are no obstacles within the preset range of the path nodes on the current matching path, and there are no obstacles within the mechanical - arm motion sweeping space corresponding to any two adjacent path nodes.

[0084] S254. If there is a current matching path that meets the second - type feasible condition, use the current matching path with the shortest path length as the second - type up - sampling path.

[0085] The current matching path with the shortest path length is the current matching path with the fewest number of path nodes.

[0086] S255. Let \(i = i + 1\), and determine whether \(i\) is greater than the growth - times threshold. If \(i\) is less than or equal to the growth - times threshold, execute S256; if \(i\) is greater than the growth - times threshold, determine that the path planning fails.

[0087] S256. Perform the \(i\) -th growth.

[0088] After S256, repeat S252. After the \(i\) -th growth of the random search tree is completed, determine whether there is a matching node combination.

[0089] On the basis of Figure 2 Regarding the content in S26, the embodiment of the present invention also provides an optional implementation manner. Please refer to the following. S26. Dynamically simplify the second - type up - sampling path, delete the redundant points therein to obtain a target path reachable by the entire path, including: S261, S262, S263, S264, S265, S266, and S267, which are specifically described as follows.

[0090] S261. Use the start point of the second - type up - sampling path as the current recognition point.

[0091] S262, Determine whether the current recognition point satisfies the first type of simplification condition. If the current recognition point satisfies the first type of simplification condition, execute S263; if the current recognition point does not satisfy the first type of simplification condition, execute S265.

[0092] Among them, the first type of simplification condition means that within a preset range with the current recognition point as the center and the real-time search step length as the radius, there are points to be confirmed. The points to be confirmed are nodes on the first type of upsampling path that are sorted after the current recognition point and have a sorting interval greater than 1.

[0093] S263, Determine whether there is a point to be confirmed among the M points to be confirmed that satisfies the second type of simplification condition. If there is a point to be confirmed that satisfies the second type of simplification condition, execute S264; if there is no point to be confirmed that satisfies the second type of simplification condition, execute S265.

[0094] Among them, M represents the number of points to be confirmed corresponding to the current recognition point, and the second type of simplification condition means that there are no obstacles in the mechanical arm movement sweeping space corresponding to the current recognition point to the point to be confirmed.

[0095] S264, If there is a point to be confirmed that satisfies the second type of simplification condition, then use the path nodes on the second type of upsampling path that are sorted after the current recognition point and before the target node as redundant points and delete them, and use the target node as the new recognition point.

[0096] Among them, the target node is the last point to be confirmed that satisfies the second type of simplification condition, that is, the one with the largest sorting on the second type of upsampling path among the points to be confirmed that satisfy the second type of simplification condition.

[0097] S265, Use the next node on the second type of upsampling path that is sorted after the current recognition point as the new recognition point.

[0098] S266, After determining the new recognition point, determine whether the new recognition point is the end point of the second type of upsampling path. If the new recognition point is the end point of the second type of upsampling path, execute S267; if the new recognition point is not the end point of the second type of upsampling path, repeat S262 to determine whether the current recognition point satisfies the first type of simplification condition.

[0099] S267, Use the simplified path after deleting the redundant points as the target path.

[0100] Please refer to Figure 3 and Figure 4 , Figure 3 , which is the iterative schematic diagram of the upsampling path planning provided by the embodiment of the present invention, Figure 4 , which is the schematic diagram of the dynamic path simplification provided by the embodiment of the present invention. Optionally,Figure 3 The number of iterations for the upsampling path planning increases sequentially and is arranged from top to bottom as follows: the initial linear path, the first type of upsampling path No. 1, the first type of upsampling path No. 2, the first type of upsampling path No. 1. It can be seen that the step size gradually decreases. Figure 4 Arranged from top to bottom are: the first type of upsampling path or the second type of upsampling path, the path simplification process, and the path simplification result, where R s represents the radius and is equal to the current real-time search step size S s .

[0101] An alternative implementation manner is also provided in an embodiment of the present invention. Please refer to Figure 5 , and the dynamic path planning method further includes: S11, S12, S13, S14, S15, S16, and S17, which are specifically described as follows.

[0102] S11, solve the robot end pose at the starting point according to the inverse kinematics of the robot to obtain the starting joint angle of the robot at the starting point.

[0103] S12, solve the robot end pose at the end point according to the inverse kinematics of the robot to obtain the end joint angle of the robot at the end point.

[0104] S13, determine the Euclidean distance in the joint space between the two based on the starting joint angle and the end joint angle, and use it as the linear path length from the starting point to the end point in the joint space.

[0105] S14, perform interpolation along the linear direction from the starting point to the end point in the joint space according to the preset interpolation step size to generate a linear path.

[0106] S15, determine whether a collision will occur when the robot moves along the linear path. If no collision occurs, execute S16; if a collision occurs, execute S17.

[0107] If a collision occurs, it means that there is an obstacle on the linear path from the starting point to the end point in the joint space.

[0108] S16, determine the linear path as the target path.

[0109] S17, determine the real-time search step size according to the linear path length from the starting point to the end point in the joint space and the search step size scaling factor.

[0110] In an alternative implementation manner, the formula for the real-time search step size is: S s = L0 / f s where S s represents the real-time search step size, L0 represents the linear path length, and fs Represents the search step size scaling factor.

[0111] It should be noted that after S17, steps such as S21 can be executed.

[0112] A dynamic path planning method provided by an embodiment of the present invention can complete real-time obstacle avoidance planning for a serial robot based on upsampling and dynamic path simplification. First, based on the bidirectional connected rapidly-exploring random tree path planning framework, a targeted upsampling strategy is proposed, and an adaptive step size adjustment mechanism and a lightweight continuous collision detection mechanism are used to ensure efficient and safe path planning. Secondly, for the problem of redundant path points caused by random search, a dynamic path simplification method based on real-time search step size is carried out to eliminate redundant path points, shorten the path length, and reduce the computational load at the same time. By adopting the upsampling strategy, the algorithm no longer requires manual debugging and setting of the optimal step size, solves the long-existing step size selection problem in such random sampling-based path planning methods, and realizes the improvement of the efficiency of path planning and post-processing to meet the real-time requirements of the serial robot for intelligent autonomous obstacle avoidance in a dynamic environment.

[0113] Please refer to Figure 6 , Figure 6 which is a dynamic path planning device provided by an embodiment of the present invention. Optionally, this dynamic path planning device is applied to the electronic device described above.

[0114] The dynamic path planning device includes: a first processing unit 501 and a second processing unit 502.

[0115] The first processing unit 501 is used to perform a first type of upsampling path planning according to the path point feasibility strategy, based on the real-time search step size and the base path, to obtain a first type of upsampling path; The second processing unit 502 is used to perform dynamic path simplification on the first type of upsampling path, delete the redundant points therein, and use the simplified path as the new base path; The first processing unit 501 is further used to perform shortening update on the basis of the current real-time search step size to obtain a new real-time search step size; The first processing unit 501 is further used to, if the new real-time search step size is greater than or equal to the step size threshold, repeat performing the first type of upsampling path planning according to the path point feasibility strategy, based on the real-time search step size and the base path, to obtain a first type of upsampling path; The first processing unit 501 is further used to, if the new real-time search step size is less than the step size threshold, perform a second type of upsampling path planning according to the whole path reachability strategy, based on the new real-time search step size and the base path, to obtain a second type of upsampling path; The second processing unit 502 is further configured to perform dynamic path simplification on the second type of upsampling path, and delete redundant points therein to obtain a target path reachable by the entire path.

[0116] Optionally, the second processing unit 502 may execute S22 and S26 described above, and the first processing unit 501 may execute other steps in the above method embodiments.

[0117] It should be noted that the dynamic path planning device provided in this embodiment can execute the method flow shown in the above method flow embodiment to achieve the corresponding technical effects. For the sake of brief description, for the parts not mentioned in this embodiment, reference may be made to the corresponding content in the above embodiments.

[0118] An embodiment of the present invention further provides a storage medium, which stores computer instructions and programs. When the computer instructions and programs are read and run, they execute the dynamic path planning method in the above embodiment. The storage medium may include memory, flash memory, registers or a combination thereof, etc.

[0119] The following provides an electronic device, which may be a mobile phone device, a computer device, and a server device. The electronic device is as Figure 1 shown, and can implement the above dynamic path planning method; specifically, the electronic device includes: a processor 10, a memory 11, and a bus 12. The processor 10 may be a CPU. The memory 11 is used to store one or more programs. When the one or more programs are executed by the processor 10, the dynamic path planning method in the above embodiment is executed.

[0120] In summary, a dynamic path planning method, device, storage medium, and electronic device provided by an embodiment of the present invention perform first-class upsampling path planning according to a path point feasibility strategy, based on a real-time search step size and a basic path, to obtain a first-class upsampling path; perform dynamic path simplification on the first-class upsampling path, delete redundant points therein, and use the simplified path as a new basic path; perform shortening update on the basis of the current real-time search step size to obtain a new real-time search step size; if the new real-time search step size is greater than or equal to the step size threshold, repeat performing first-class upsampling path planning according to the path point feasibility strategy, based on the real-time search step size and the basic path, to obtain a first-class upsampling path; if the new real-time search step size is less than the step size threshold, perform second-class upsampling path planning according to an entire path reachability strategy, based on the new real-time search step size and the basic path, to obtain a second-class upsampling path; perform dynamic path simplification on the second-class upsampling path, delete redundant points therein, to obtain a target path that can reach the entire path. By adopting the upsampling strategy, the algorithm no longer requires manual debugging and setting of the optimal step size, solves the long-existing step size selection problem in such path planning methods based on random sampling, and realizes the improvement of the efficiency of path planning and post-processing to meet the real-time requirements of a serial robot for intelligent autonomous obstacle avoidance in a dynamic environment. At the same time, by deleting redundant path points, path dynamic simplification can gradually shorten the path length.

[0121] The foregoing is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0122] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to include all changes falling within the meaning and scope of the equivalent elements of the claims in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

Claims

1. A dynamic path planning method, characterized in that: The method comprises: According to the path point feasibility strategy, the first type of upsampling path planning is performed according to the real-time search step size and the basic path to obtain the first type of upsampling path; Dynamically simplify the first type of upsampling path, delete redundant points therein, and use the simplified path as a new basic path; Based on the current real-time search step length, shorten and update it to obtain a new real-time search step length; If the new real-time search step is greater than or equal to the step threshold, then repeat the path point feasibility strategy to perform first-class upsampling path planning according to the real-time search step and the basic path to obtain the first-class upsampling path; If the new real-time search step size is less than the step size threshold, the second type of upsampling path planning is performed according to the new real-time search step size and the basic path according to the entire path reachability strategy to obtain the second type of upsampling path; Dynamic path simplification is performed on the second type of up-sampled path, and redundant points are deleted to obtain the target path that is reachable by the entire path.

2. The dynamic path planning method according to claim 1, characterized in that: The first type of upsampling path planning is performed according to the path point feasibility strategy and the real-time search step size and the basic path to obtain the first type of upsampling path, including: According to the real-time search step size and the basic path, the random search tree is expanded from the starting point and the end point respectively using the bidirectional connection type fast search random tree algorithm to perform the first growth; After the random search tree is grown for the i-th time, determining whether there is a matching node combination; Wherein, the distance between the starting point side node and the ending point side node in the matching node combination is less than or equal to the real-time search step length; If there is a matching node combination, determine whether there is a current matching path that meets the first type of feasible conditions; The current matching path is a path formed by the path from the starting point to the starting point side node in the matching node combination and from the end point to the end point side node in the matching node combination, and the first type of feasible condition indicates that there is no obstacle within a preset range of each path node on the current matching path; If there is a current matching path that meets the first type of feasible conditions, the current matching path with the shortest path length is used as the first type of upsampling path; If there is no matching node combination, or there is no current matching path that satisfies the first type of feasible conditions, then let i=i+1, determine whether i is greater than the growth number threshold, if i is less than or equal to the growth number threshold, perform the i-th growth, and repeat after the i-th growth of the random search tree is completed, determine whether there is a matching node combination.

3. The dynamic path planning method according to claim 1, characterized in that: Dynamically simplify the first type of upsampling path, delete redundant points therein, and use the simplified path as a new basic path, including: Taking the starting point of the first type of upsampling path as an identification point; Determine whether the current identification point meets the first type of simplification conditions; The first type of simplified condition indicates that there is a point to be confirmed within a preset range with the current identification point as the center and the real-time search step as the radius, and the point to be confirmed is a node that is sorted after the current identification point on the first type of upsampling path and whose sorting interval is greater than 1; If the current recognition point meets the first type of simplification conditions, the next path node ordered after the current recognition point on the first type of upsampling path and the first M-1 to-be-confirmed points corresponding to the current recognition point are taken as redundant points and deleted, and the Mth to-be-confirmed point after the current recognition point is taken as a new recognition point, where M represents the number of to-be-confirmed points corresponding to the current recognition point; If the current identification point does not meet the first type of simplification condition, the next node sorted after the current identification point on the first type of upsampling path is used as a new identification point; After determining the new identification point, determining whether the new identification point is an end point of the first type of upsampling path; If it is not the end point, then repeatedly determine whether the current identification point satisfies the first type of simplified conditions; If the new identification point is the end point of the first type of upsampling path, the simplified path after deleting the redundant points is used as the new basic path.

4. The dynamic path planning method according to claim 1, characterized in that: According to the entire path reachability strategy, the second type of upsampling path planning is performed according to the new real-time search step and the basic path to obtain the second type of upsampling path, including: According to the real-time search step size and the basic path, the random search tree is expanded from the starting point and the end point respectively using the bidirectional connection type fast search random tree algorithm to perform the first growth; After the random search tree is grown for the i-th time, determining whether there is a matching node combination; Wherein, the distance between the starting point side node and the ending point side node in the matching node combination is less than or equal to the real-time search step length; If there is a matching node combination, determine whether there is a current matching path that meets the second type of feasible conditions; The current matching path is a path formed by the path from the starting point to the starting point side node in the matching node combination and from the end point to the end point side node in the matching node combination, and the second type of feasible condition indicates that there are no obstacles within a preset range of the path nodes on the current matching path, and there are no obstacles in the corresponding robot arm motion sweep space between any two adjacent path nodes; If there is a current matching path that meets the second type of feasible conditions, the current matching path with the shortest path length is used as the second type of upsampling path; If there is no matching node combination, or there is no current matching path that satisfies the second type of feasible conditions, then let i=i+1, determine whether i is greater than the growth number threshold, if i is less than or equal to the growth number threshold, perform the i-th growth, and repeat after the i-th growth of the random search tree is completed, determine whether there is a matching node combination.

5. The dynamic path planning method according to claim 1, characterized in that: The step of dynamically simplifying the second type of up-sampling path and deleting redundant points therein to obtain a target path that is reachable by the entire path includes: Taking the starting point of the second type of upsampling path as the current identification point; Determine whether the current identification point meets the first type of simplification conditions; The first type of simplified condition indicates that there is a point to be confirmed within a preset range with the current identification point as the center and the real-time search step as the radius, and the point to be confirmed is a node that is sorted after the current identification point on the first type of upsampling path and whose sorting interval is greater than 1; If the current recognition point satisfies the first type of simplified condition, it is determined whether there is a point to be confirmed that satisfies the second type of simplified condition among the M points to be confirmed, where M represents the number of points to be confirmed corresponding to the current recognition point, and the second type of simplified condition represents that there are no obstacles in the corresponding sweeping space of the robot arm motion between the current recognition point and the point to be confirmed; If there is a point to be confirmed that meets the second type of simplification conditions, the path nodes on the second type of upsampling path that are sorted after the current identification point and before the target node are deleted as redundant points, and the target node is used as a new identification point; wherein the target node is the last point to be confirmed that meets the second type of simplification conditions; If the current identification point does not meet the first type of simplification conditions, or there is no point to be confirmed that meets the second type of simplification conditions, the next node on the second type of upsampling path that is sorted after the current identification point is used as a new identification point; After determining the new identification point, determining whether the new identification point is an end point of the second type of upsampling path; If it is not the end point, then repeatedly determine whether the current identification point satisfies the first type of simplified conditions; If the new identification point is the end point of the second type of up-sampling path, the simplified path after deleting redundant points is used as the target path.

6. The dynamic path planning method according to claim 1, characterized in that: The method further comprises: The robot end position at the starting point is solved according to the robot inverse kinematics to obtain the starting joint angle of the robot at the starting point; The robot end position at the end point is solved according to the robot inverse kinematics to obtain the end point joint angle of the robot at the end point; Determine the joint space Euclidean distance between the start point joint angle and the end point joint angle according to the start point joint angle and the end point joint angle, as the linear path length from the start point to the end point in the joint space; According to a preset interpolation step, linear interpolation is performed along the linear direction from the starting point to the end point in the joint space to generate a linear path; determining whether a collision will occur when the robot moves along the linear path; If no collision occurs, determining the linear path as the target path; If a collision occurs, the real-time search step size is determined based on the linear path length from the start point to the end point in the joint space and the search step size scaling factor.

7. The dynamic path planning method according to claim 1, characterized in that: The shortening and updating based on the current real-time search step length to obtain a new real-time search step length includes: The real-time search step size is iteratively updated according to the search step size scaling factor to obtain a new real-time search step size.

8. A dynamic path planning device, characterized in that: The device comprises: A first processing unit is configured to perform first-type upsampling path planning according to a path point feasibility strategy, a real-time search step size and a basic path, so as to obtain a first-type upsampling path; a second processing unit, configured to dynamically simplify the first type of upsampling path, delete redundant points therein, and use the simplified path as a new basic path; The first processing unit is further used to shorten and update the current real-time search step length to obtain a new real-time search step length; The first processing unit is further configured to repeatedly perform first-type upsampling path planning according to the real-time search step size and the basic path according to the path point feasibility strategy if the new real-time search step size is greater than or equal to the step size threshold, so as to obtain the first-type upsampling path; The first processing unit is further configured to, if the new real-time search step size is less than the step size threshold, perform second-type upsampling path planning according to the entire path reachability strategy and the new real-time search step size and the basic path to obtain a second-type upsampling path; The second processing unit is further configured to perform dynamic path simplification on the second type of up-sampled path and delete redundant points therein to obtain a target path that is reachable by the entire path.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: A processor and a memory, the memory being used to store one or more programs; When the one or more programs are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

Images