Self-adaptive path planning method and system

By combining the Vino graph and A* algorithm in robot path planning, using the Vino distance heuristic function to optimize path search, the problem of safety hazards of robot traffic in complex environments is solved, and more efficient and safe path planning is achieved.

CN118913270APending Publication Date: 2024-11-08HUAZHONG UNIV OF SCI & TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410861811.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-28
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Existing robot path planning methods may choose narrow routes to pass in complex environments, resulting in traffic safety hazards and failing to effectively ensure the safety of robots.

Method used

Combining the Vino graph and A* path planning algorithm, by obtaining the robot's current location map and obstacle distribution, building the Vino graph, using the Vino distance heuristic function to optimize the path search, select the least cost critical point as the child node, and reduce the search space, improve path planning efficiency and security.

Benefits of technology

By optimizing the path search space, the efficiency and security of robot path planning are improved, and the safe passage of robots in complex environments is ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118913270A_ABST
    Figure CN118913270A_ABST
Patent Text Reader

Abstract

The invention provides a self-adaptive path planning method and system, and the method comprises the steps: obtaining a current position map and obstacle distribution of a robot, constructing a Voronoi diagram based on the current position map and the obstacle distribution, and obtaining Voronoi boundary nodes, a critical point set and a node Voronoi distance; path searching is carried out in the Voronoi diagram based on an A * path planning algorithm, critical points around Voronoi boundary nodes are evaluated through a heuristic function based on the Voronoi distance, and the critical point with the minimum cost is selected as a child node; and judging whether the robot reaches a target point to verify whether path search is completed or not, if not, continuously obtaining a critical point to be evaluated based on the Voronoi boundary, and obtaining a sub-node with the minimum cost until path optimization is completed. According to the scheme, the self-adaptive path searching efficiency can be improved, and the safety of the passing path is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular relates to an adaptive path planning method and system. Background Art

[0002] With the rapid development of artificial intelligence technology, intelligent robots have become more and more common and are playing an increasingly important role in all walks of life. Robots usually need to plan their paths autonomously during their movements. Currently, most common path planning is based on the A* search algorithm. However, since the A* search algorithm mostly uses the shortest path as the optimization goal, robots may choose narrow routes in complex environments, making it difficult to ensure the safety of the robots. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides an adaptive path planning method and system for solving the problem that current robot adaptive path planning has certain safety risks.

[0004] In a first aspect of an embodiment of the present invention, an adaptive path planning method is provided, comprising:

[0005] Obtain the robot's current position map and obstacle distribution, build a Voronoi diagram based on the current position map and obstacle distribution, and obtain the Voronoi boundary nodes, critical point sets, and node Voronoi distances;

[0006] Based on the A* path planning algorithm, a path search is performed in the Voronoi graph, and the critical points around the Voronoi boundary nodes are evaluated by a heuristic function based on the Voronoi distance, and the critical point with the minimum cost is selected as a child node;

[0007] Determine whether the robot has reached the target point to verify whether the path search is completed. If not, continue to obtain the critical point to be evaluated based on the Voronoi frontier and obtain the child node with the minimum cost until the path optimization is completed.

[0008] In a second aspect of an embodiment of the present invention, an adaptive path planning system is provided, including:

[0009] A data acquisition module is used to obtain the robot's current position map and obstacle distribution, build a Voronoi diagram based on the current position map and obstacle distribution, and obtain the Voronoi boundary nodes, critical point sets and node Voronoi distances;

[0010] The node search module is used to perform path search in the Voronoi diagram based on the A* path planning algorithm, and evaluate the critical points around the Voronoi boundary node through the heuristic function based on the Voronoi distance, and select the critical point with the minimum cost as the child node; determine whether the robot has reached the target point to verify whether the path search is completed. If not, continue to obtain the critical points to be evaluated based on the Voronoi boundary, and obtain the child node with the minimum cost until the path optimization is completed.

[0011] In a third aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect of the embodiment of the present invention when executing the computer program.

[0012] In a fourth aspect of an embodiment 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 steps of the method provided in the first aspect of the embodiment of the present invention are implemented.

[0013] In an embodiment of the present invention, by combining the Voronoi space with the A* path search algorithm, the Voronoi space is used to obtain nodes far away from obstacles, the traditional neighborhood search is optimized to the Voronoi boundary search, the search space is reduced, the efficiency of the adaptive path search is improved, the obstacle distance search is optimized, and the safety of the passage path is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A schematic flow chart of an adaptive path planning method provided by an embodiment of the present invention;

[0016] Figure 2 A schematic diagram of a path search provided by an embodiment of the present invention;

[0017] Figure 3 A schematic diagram of path search in Voronoi space provided by an embodiment of the present invention;

[0018] Figure 4 A schematic diagram of the structure of an adaptive path planning system provided by an embodiment of the present invention;

[0019] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only 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] It should be understood that the term "including" and other similar expressions in the specification or claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, such as a process, method, system, or device including a series of steps or units is not limited to the listed steps or units. In addition, "first" and "second" are used to distinguish different objects, not to describe a specific order.

[0022] It is understandable that the traditional adaptive A* does not fully consider the impact of the environment on the active obstacle avoidance capability. The robot cannot maintain a sufficient safety distance from obstacles, which makes the planned path close to obstacles. It is necessary to propose a new path search method to ensure the safe passage of the robot.

[0023] See also Figure 1 , a flow chart of an adaptive path planning method provided by an embodiment of the present invention includes:

[0024] S101, obtaining a current position map and obstacle distribution of the robot, constructing a Voronoi diagram based on the current position map and obstacle distribution, and obtaining Voronoi boundary nodes, critical point sets, and node Voronoi distances;

[0025] Obstacle distribution around the robot is obtained by positioning the robot, and a Voronoi diagram is constructed based on the obstacle and position information. The Voronoi diagram is composed of continuous polygons composed of perpendicular bisectors of lines connecting adjacent points.

[0026] S102, performing path search in the Voronoi graph based on the A* path planning algorithm, evaluating critical points around the Voronoi boundary nodes through a heuristic function based on the Voronoi distance, and selecting the critical point with the minimum cost as a child node;

[0027] The A* path planning algorithm is a heuristic search algorithm that can find the path with the lowest cost in a path with multiple nodes on a graph plane. The A* algorithm is used to search for paths in the Voronoi graph, and the Voronoi space is used to obtain nodes that are as far away from obstacles as possible. The node search is optimized from the traditional global grid map 8-neighborhood search to the Voronoi boundary search, which reduces the search space and improves the efficiency of path planning. Figure 2 As shown in the figure, there is a clear difference between the search space of the traditional A* algorithm and the search space of the A* algorithm under the Voronoi diagram. The traditional A* algorithm needs to search the 8-neighborhood of the entire grid map, while the A* algorithm under the Voronoi diagram only searches for critical points around the Voronoi boundary points. The Voronoi diagram can narrow the search space.

[0028] Wherein, the heuristic function is:

[0029] F(n)=G(n)+ω(n)H(n);

[0030] Among them, the weight coefficient ω(n) in the heuristic function is expressed as:

[0031]

[0032] In the formula, F(n) represents the total cost of node n, G(n) represents the actual distance cost from the starting point to node n, H(n) represents the estimated distance cost from node n to the desired target point, and d safe is the safe Voronoi distance, d min is the collision Voronoi distance, d n is the Voronoi distance.

[0033] It can be understood that the size of the ω(n) weight affects the efficiency of A* search in the following ways: the larger the weight coefficient, the fewer nodes are searched and the higher the search efficiency; conversely, the more complete the search is but the more nodes are searched, the lower the efficiency. Therefore, the weight can affect the search efficiency and optimization goal of path planning. In order to plan a safe path that is as far away from obstacles as possible, the Voronoi planning space can be combined with the adaptive weight A* optimization strategy.

[0034] In order to obtain the optimal path with low risk on the basis of search space optimization, the Voronoi distance corresponding to the node is introduced as an obstacle factor into the adaptive weight A* heuristic function. The Voronoi distance corresponds to the risk level of the current area. When the Voronoi distance dp is lower than the safety threshold, the smaller it is, the greater the risk level is. Therefore, a fast search for the path corresponding to the maximum Voronoi distance is achieved.

[0035] like Figure 3 As shown, after introducing the Voronoi distance, we can obtain the k nearest nodes of each node p: N p = KNN(p,k), and the Voronoi distance d between the node and the obstaclep , and then use A* to search for a path from the starting position p start Start with each boundary node p k The neighboring node p k+1 Based on the Voronoi distance, the corresponding neighboring node p is selected. k+1 as a child node.

[0036] S103, judging whether the robot has reached the target point to verify whether the path search is completed. If not completed, continuously obtaining the critical point to be evaluated based on the Voronoi frontier and obtaining the child node with the minimum cost until the path optimization is completed.

[0037] When the robot has not reached the target point, that is, the end point of the path, it needs to search the child nodes of the current node, evaluate the child nodes and select the child node with the minimum cost until it reaches the target point.

[0038] Specifically, the minimum cost critical point is obtained as the child node of the current Voronoi boundary node, and the critical points around the child node are continuously determined. When the Voronoi boundary child node is detected as the target point, the Voronoi boundary parent node is backtracked to obtain the planned path.

[0039] In this embodiment, the Voronoi space is combined with the A* path search algorithm, and the Voronoi distance corresponding to the node is introduced into the A* algorithm heuristic function as an obstacle factor. This can not only reduce the path search space and improve the efficiency of path planning, but also optimize the obstacle safety distance search to ensure the safety of path passage.

[0040] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0041] Figure 4 A schematic diagram of the structure of an adaptive path planning system provided by an embodiment of the present invention, the system comprising:

[0042] The data acquisition module 410 is used to obtain the robot's current position map and obstacle distribution, construct a Voronoi diagram based on the current position map and obstacle distribution, and obtain Voronoi boundary nodes, critical point sets and node Voronoi distances;

[0043] The node search module 420 is used to perform path search in the Voronoi diagram based on the A* path planning algorithm, and evaluate the critical points around the Voronoi boundary nodes through the heuristic function based on the Voronoi distance, and select the critical point with the minimum cost as the child node; determine whether the robot has reached the target point to verify whether the path search is completed. If not, continue to obtain the critical points to be evaluated based on the Voronoi boundary, and obtain the child node with the minimum cost until the path optimization is completed.

[0044] Wherein, the heuristic function is:

[0045] F(n)=G(n)+ω(n)H(n);

[0046] Among them, the weight coefficient ω(n) in the heuristic function is expressed as:

[0047]

[0048] In the formula, F(n) represents the total cost of node n, G(n) represents the actual distance cost from the starting point to node n, H(n) represents the estimated distance cost from node n to the desired target point, and d safe is the safe Voronoi distance, d min is the collision Voronoi distance, d n is the Voronoi distance.

[0049] Specifically, the minimum cost critical point is obtained as the child node of the current Voronoi boundary node, and the critical points around the child node are continuously determined. When the Voronoi boundary child node is detected as the target point, the Voronoi boundary parent node is backtracked to obtain the planned path.

[0050] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0051] Figure 5 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is used for robot path planning. Figure 5 As shown, the electronic device 5 of this embodiment includes: a memory 510, a processor 520 and a system bus 530, wherein the memory 510 includes an executable program 5101 stored thereon, and those skilled in the art can understand that Figure 5 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0052] Combine the following Figure 5 A detailed introduction to the various components of electronic equipment:

[0053] The memory 510 can be used to store software programs and modules, and the processor 520 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 510. The memory 510 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cache data), etc. In addition, the memory 510 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0054] The memory 510 includes an executable program 5101 of a network request method, and the executable program 5101 can be divided into one or more modules / units, which are stored in the memory 510 and executed by the processor 520 to implement adaptive path planning, etc. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program 5101 in the electronic device 5. For example, the computer program 5101 can be divided into functional modules such as a data acquisition module and a node search module.

[0055] The processor 520 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 510, and calling data stored in the memory 510, it performs various functions of the electronic device and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 320 may include one or more processing units; preferably, the processor 520 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 520.

[0056] The system bus 530 is used to connect the various functional components inside the computer, and can transmit data information, address information, and control information. Its types can be, for example, PCI bus, ISA bus, CAN bus, etc. The instructions of the processor 520 are transmitted to the memory 510 through the bus, and the memory 510 feeds back data to the processor 520. The system bus 530 is responsible for the data and instruction exchange between the processor 520 and the memory 510. Of course, the system bus 530 can also be connected to other devices, such as network interfaces, display devices, etc.

[0057] In the embodiment of the present invention, the executable program executed by the processor 520 included in the electronic device includes:

[0058] Obtain the robot's current position map and obstacle distribution, build a Voronoi diagram based on the current position map and obstacle distribution, and obtain the Voronoi boundary nodes, critical point sets, and node Voronoi distances;

[0059] Based on the A* path planning algorithm, a path search is performed in the Voronoi graph, and the critical points around the Voronoi boundary nodes are evaluated by a heuristic function based on the Voronoi distance, and the critical point with the minimum cost is selected as a child node;

[0060] Determine whether the robot has reached the target point to verify whether the path search is completed. If not, continue to obtain the critical point to be evaluated based on the Voronoi frontier and obtain the child node with the minimum cost until the path optimization is completed.

[0061] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0062] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0063] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An adaptive path planning method, characterized in that: include: Obtain the robot's current position map and obstacle distribution, build a Voronoi diagram based on the current position map and obstacle distribution, and obtain the Voronoi boundary nodes, critical point sets, and node Voronoi distances; Performing path search in the Voronoi graph based on the A* path planning algorithm, evaluating critical points around Voronoi boundary nodes through a heuristic function based on Voronoi distance, and selecting the critical point with the minimum cost as a child node; Determine whether the robot has reached the target point to verify whether the path search is completed. If not, continue to obtain the critical point to be evaluated based on the Voronoi frontier and obtain the child node with the minimum cost until the path optimization is completed.

2. The method according to claim 1, characterized in that The heuristic function is: F(n)=G(n)+ω(n)H(n); Among them, the weight coefficient ω(n) in the heuristic function is expressed as: In the formula, F(n) represents the total cost of node n, G(n) represents the actual distance cost from the starting point to node n, H(n) represents the estimated distance cost from node n to the desired target point, and d safe is the safe Voronoi distance, d min is the collision Voronoi distance, d n is the Voronoi distance.

3. The method according to claim 1, characterized in that: If the above is not completed, the critical point to be evaluated is continuously obtained based on the Voronoi boundary, and the child node with the minimum cost is obtained until the path optimization is completed, including: The minimum cost critical point is obtained as the child node of the current Voronoi boundary node, and the critical points around the child node are continued to be determined. When the Voronoi boundary child node is detected as the target point, the Voronoi boundary parent node is backtracked to obtain the planned path.

4. An adaptive path planning system, characterized in that: include: A data acquisition module is used to obtain the robot's current position map and obstacle distribution, build a Voronoi diagram based on the current position map and obstacle distribution, and obtain the Voronoi boundary nodes, critical point sets and node Voronoi distances; The node search module is used to perform path search in the Voronoi diagram based on the A* path planning algorithm, and evaluate the critical points around the Voronoi boundary node through the heuristic function based on the Voronoi distance, and select the critical point with the minimum cost as the child node; determine whether the robot has reached the target point to verify whether the path search is completed. If not, continue to obtain the critical points to be evaluated based on the Voronoi boundary, and obtain the child node with the minimum cost until the path optimization is completed.

5. The system according to claim 4, characterized in that The heuristic function is: F(n)=G(n)+ω(n)H(n); Among them, the weight coefficient ω(n) in the heuristic function is expressed as: In the formula, F(n) represents the total cost of node n, G(n) represents the actual distance cost from the starting point to node n, H(n) represents the estimated distance cost from node n to the desired target point, and d safe is the safe Voronoi distance, d min is the collision Voronoi distance, d n is the Voronoi distance.

6. The system according to claim 4, characterized in that If the above is not completed, the critical point to be evaluated is continuously obtained based on the Voronoi boundary, and the child node with the minimum cost is obtained until the path optimization is completed, including: The minimum cost critical point is obtained as the child node of the current Voronoi boundary node, and the critical points around the child node are continued to be determined. When the Voronoi boundary child node is detected as the target point, the Voronoi boundary parent node is backtracked to obtain the planned path.

7. An electronic 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 steps of an adaptive path planning method as described in any one of claims 1 to 3 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the steps of an adaptive path planning method as claimed in any one of claims 1 to 3 are implemented.