Improved method, device and computer equipment for escaping from local minimum in artificial potential field

Abstract

The present application relates to a method, device, computer equipment and storage medium for improving the escape from local minimum in an artificial potential field. The method comprises: obtaining the position of the local minimum point trapped by an intelligent agent in the artificial potential field, and constructing a filling and repelling potential field including a positive correlation gain factor of the filling and repelling potential field and a maximum influence distance of the filling and repelling potential field with it as the center, when the distance between the current position of the intelligent agent and the local minimum point is greater than the maximum influence distance of the filling and repelling potential field, the filling and repelling potential field is 0; when the distance between the current position of the intelligent agent and the local minimum point is not greater than the maximum influence distance of the filling and repelling potential field, the size of the filling and repelling potential field is positively correlated with the positive correlation gain factor of the filling and repelling potential field, and decreases as the distance from the intelligent agent to the local minimum point increases; adjusting the positive correlation influence factor in the filling and repelling potential field according to the distribution state of obstacles around the intelligent agent until the intelligent agent escapes from the local minimum point.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent agent path planning in artificial potential fields, and in particular to a method, device, computer equipment and storage medium for improving escape from local minima in artificial potential fields. Background Art

[0002] The artificial potential field method has a strong ability to adapt to scenarios in actual planning applications and can display the topological model of the scene. At the same time, it can solve the defects of large amount of calculation and complex operation of global planning. The planning modeling is concise and the method is clear, which has attracted more and more attention and application.

[0003] However, there are defects and constraints in the actual application scenarios of the path planning of intelligent agents through the artificial potential field method. One of them is the local minimum problem, that is, for the problem of multiple obstacles, when the distribution of obstacles meets specific conditions, local extreme value problems will appear in the planning process, and the intelligent agent cannot obtain the global optimum, and thus always moves and wanders in the local area. The prior art proposes to construct a potential field without local minima to solve the source problem of local minima. However, this method has high requirements for obstacle distribution modeling and repeated calculations, and puts forward higher requirements on computer computing power. Therefore, the prior art has the problem of low efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for escaping from local minima in an improved artificial potential field, which can improve the efficiency of escaping from local minima points in order to solve the above technical problems.

[0005] A method for improving escape from local minima in an artificial potential field, the method comprising:

[0006] Get the location of the local minimum point where the agent is trapped in the artificial potential field;

[0007] Taking the position of the local minimum point as the center, construct a filling and repulsive potential field; the filling and repulsive potential field includes a filling and repulsive potential field positive correlation gain factor and a filling and repulsive potential field maximum influence distance; when the distance between the current position of the agent and the local minimum point is greater than the filling and repulsive potential field maximum influence distance, the filling and repulsive potential field is 0; when the distance between the current position of the agent and the local minimum point is not greater than the filling and repulsive potential field maximum influence distance, the size of the filling and repulsive potential field is positively correlated with the filling and repulsive potential field positive correlation gain factor, and decreases as the distance from the agent to the local minimum point increases;

[0008] Obtain the obstacle distribution state around the intelligent agent, and adjust the positive correlation influencing factors in the filling repulsive potential field according to the obstacle distribution state until the intelligent agent escapes from the local minimum point.

[0009] In one of the embodiments, it also includes: the artificial potential field includes a repulsive potential field generated by an obstacle and an attractive potential field generated by a target; the property of the filling repulsive potential field is the same as that of the repulsive potential field.

[0010] In one embodiment, the repulsive potential field is a modified repulsive potential field, and the modified repulsive potential field is:

[0011]

[0012] Among them, k rep is the positive correlation gain factor of the modified repulsive potential field, X is the current position of the agent, X0 is the position of the local minimum point, ρ0 is the maximum influence distance of the modified repulsive potential field, ρ(X,X0)=||X0-X|| is the distance between the agent and the obstacle, ρ(X,X g )=||X g -X|| is the distance between the agent and the target.

[0013] In one embodiment, the method further comprises: constructing a filling repulsive potential field with the position of the local minimum point as the center, comprising:

[0014] Taking the position of the local minimum point as the center, the filled repulsive potential field is constructed as follows:

[0015]

[0016] Among them, k m is the positive correlation gain factor for filling the repulsive potential field, X m is the position of the local minimum point, ρ1 is the maximum influence distance of the filling repulsive potential field, ρ(X,X m )=||X m -X|| is the Euclidean distance between the agent and the local minimum point.

[0017] In one of the embodiments, it further includes: obtaining the obstacle distribution state around the intelligent agent;

[0018] When the number of obstacles within the preset range of the agent is greater than a preset threshold, obtaining the distance between the agent and the target point;

[0019] The positive correlation gain factor of the filling repulsive potential field is reduced according to the number of obstacles and the distance between the intelligent agent and the target point.

[0020] A device for improving escape from local minimum in an artificial potential field, the device comprising:

[0021] A local minimum point determination module is used to obtain the position of the local minimum point where the agent is trapped in the artificial potential field;

[0022] A filling and repulsive potential field construction module is used to construct a filling and repulsive potential field with the position of the local minimum point as the center; the filling and repulsive potential field includes a filling and repulsive potential field positive correlation gain factor and a filling and repulsive potential field maximum influence distance; when the distance between the current position of the agent and the local minimum point is greater than the filling and repulsive potential field maximum influence distance, the filling and repulsive potential field is 0; when the distance between the current position of the agent and the local minimum point is not greater than the filling and repulsive potential field maximum influence distance, the size of the filling and repulsive potential field is positively correlated with the filling and repulsive potential field positive correlation gain factor, and decreases as the distance from the agent to the local minimum point increases;

[0023] The filling and repulsive potential field adjustment module is used to obtain the obstacle distribution state around the intelligent agent, and adjust the positive correlation influencing factors in the filling and repulsive potential field according to the obstacle distribution state until the intelligent agent escapes from the local minimum point.

[0024] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0025] Get the location of the local minimum point where the agent is trapped in the artificial potential field;

[0026] Taking the position of the local minimum point as the center, construct a filling and repulsive potential field; the filling and repulsive potential field includes a filling and repulsive potential field positive correlation gain factor and a filling and repulsive potential field maximum influence distance; when the distance between the current position of the agent and the local minimum point is greater than the filling and repulsive potential field maximum influence distance, the filling and repulsive potential field is 0; when the distance between the current position of the agent and the local minimum point is not greater than the filling and repulsive potential field maximum influence distance, the size of the filling and repulsive potential field is positively correlated with the filling and repulsive potential field positive correlation gain factor, and decreases as the distance from the agent to the local minimum point increases;

[0027] Obtain the obstacle distribution state around the intelligent agent, and adjust the positive correlation influencing factors in the filling repulsive potential field according to the obstacle distribution state until the intelligent agent escapes from the local minimum point.

[0028] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0029] Get the location of the local minimum point where the agent is trapped in the artificial potential field;

[0030] Taking the position of the local minimum point as the center, construct a filling and repulsive potential field; the filling and repulsive potential field includes a filling and repulsive potential field positive correlation gain factor and a filling and repulsive potential field maximum influence distance; when the distance between the current position of the agent and the local minimum point is greater than the filling and repulsive potential field maximum influence distance, the filling and repulsive potential field is 0; when the distance between the current position of the agent and the local minimum point is not greater than the filling and repulsive potential field maximum influence distance, the size of the filling and repulsive potential field is positively correlated with the filling and repulsive potential field positive correlation gain factor, and decreases as the distance from the agent to the local minimum point increases;

[0031] Obtain the obstacle distribution state around the intelligent agent, and adjust the positive correlation influencing factors in the filling repulsive potential field according to the obstacle distribution state until the intelligent agent escapes from the local minimum point.

[0032] The above-mentioned improved method, device, computer equipment and storage medium for escaping from the local minimum in the artificial potential field obtain the position of the local minimum point trapped by the intelligent agent in the artificial potential field, and construct a filling and repelling potential field including a positive correlation gain factor of the filling and repelling potential field and a maximum influence distance of the filling and repelling potential field with the position of the local minimum point as the center. When the distance between the current position of the intelligent agent and the local minimum point is greater than the maximum influence distance of the filling and repelling potential field, the filling and repelling potential field is 0; when the distance between the current position of the intelligent agent and the local minimum point is not greater than the maximum influence distance of the filling and repelling potential field, the size of the filling and repelling potential field is positively correlated with the positive correlation gain factor of the filling and repelling potential field, and decreases as the distance from the intelligent agent to the local minimum point increases; the obstacle distribution state around the intelligent agent is obtained, and the positive correlation influence factor in the filling and repelling potential field is adjusted according to the obstacle distribution state until the intelligent agent escapes from the local minimum point. The present invention designs a filling-in repulsive potential field including a positively correlated gain factor, and can adjust the filling-in repulsive potential field according to the situation of surrounding obstacles, adaptively filling in the "saddle" of the local minimum, so that the intelligent agent can pass through the local minimum trap. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A schematic flow chart of a method for improving escape from a local minimum in an artificial potential field in one embodiment;

[0034] Figure 2 A structural block diagram of a device for improving escape from a local minimum in an artificial potential field in one embodiment;

[0035] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0037] The method for improving the escape from local minimum in artificial potential field provided by the present application can be applied to Figure 1 In the application environment shown. In the artificial potential field method, due to the arbitrary dynamic distribution of obstacles, there is a certain situation that when the intelligent agent enters the area where the repulsive and attractive forces are balanced, according to the concept of the potential field method, the intelligent agent cannot obtain the driving force, so it always wanders in the area and cannot reach the terminal, that is, it falls into the local minimum. The present invention is applied to the path planning problem based on the artificial potential field method, and provides a method for improving the escape from the local minimum in the artificial potential field, which is used to guide the intelligent agent to escape from the local minimum point.

[0038] In one embodiment, Figure 1 As shown, a method for improving escape from local minima in an artificial potential field is provided, comprising the following steps:

[0039] Step 102, obtaining the position of the local minimum point where the agent is trapped in the artificial potential field.

[0040] In the case of a local minimum, the shape of the potential field is like a saddle, causing the agent that falls into it to move back and forth until it reaches the saddle point and becomes stationary. Therefore, the saddle can be filled to allow the agent to pass through the original trap and overcome the surrounding obstacles.

[0041] Step 104, constructing a filled repulsive potential field with the position of the local minimum point as the center.

[0042] The intelligent agent will be affected by the repulsive potential field generated by the local minimum area that it has not encountered before, and the repulsive potential field generated by the obstacle and the attractive potential field generated by the target will still be effective. Under the joint action of these three, the intelligent agent will move away from the local minimum area in accordance with the requirements of the artificial potential field method.

[0043] The concept of the present invention is that before the intelligent agent completely leaves the local minimum area, the repulsive potential energy decreases as the distance from the intelligent agent to the local minimum increases. After the intelligent agent completely leaves the local minimum area, the repulsive potential energy that fills the repulsive potential field is zero and no longer affects the normal path planning of the intelligent agent.

[0044] Specifically, the filling-in repulsive potential field includes the filling-in repulsive potential field positive correlation gain factor and the filling-in repulsive potential field maximum influence distance. When the distance between the current position of the agent and the local minimum point is greater than the filling-in repulsive potential field maximum influence distance, the filling-in repulsive potential field is 0; when the distance between the current position of the agent and the local minimum point is not greater than the filling-in repulsive potential field maximum influence distance, the size of the filling-in repulsive potential field is positively correlated with the filling-in repulsive potential field positive correlation gain factor, and decreases as the distance from the agent to the local minimum point increases.

[0045] Step 106, obtaining the obstacle distribution state around the intelligent agent, and adjusting the positive correlation influencing factors in the repulsive potential field according to the obstacle distribution state until the intelligent agent escapes from the local minimum point.

[0046] When obstacles are close to each other and there are too many of them, the agent may collide with normal obstacles in the environment. Appropriately reducing the filling repulsive potential field can prevent the agent from colliding with obstacles. However, if the filling repulsive potential field is reduced too much, the agent may fall into the local minimum again after escaping.

[0047] Therefore, according to the arrangement of obstacles, different positive correlation gain factors k can be assigned to them respectively. m For example, the value can be assigned based on the angle between the line from the agent to the end point and the line from the agent to the obstacle. When the angle is smaller and closer to 0 (indicating that the obstacle is closer to the agent's forward path), a larger gain factor can be assigned to it, and vice versa.

[0048] In the above-mentioned improved method for escaping from a local minimum in an artificial potential field, by obtaining the position of the local minimum point where the agent is trapped in the artificial potential field, taking the position of the local minimum point as the center, a filling and repelling potential field including a positive correlation gain factor for filling and repelling potential field and a maximum influence distance of filling and repelling potential field is constructed. When the distance between the current position of the agent and the local minimum point is greater than the maximum influence distance of filling and repelling potential field, the filling and repelling potential field is 0; when the distance between the current position of the agent and the local minimum point is not greater than the maximum influence distance of filling and repelling potential field, the size of the filling and repelling potential field is positively correlated with the positive correlation gain factor for filling and repelling potential field, and decreases as the distance from the agent to the local minimum point increases; the obstacle distribution state around the agent is obtained, and the positive correlation influence factor in the filling and repelling potential field is adjusted according to the obstacle distribution state until the agent escapes from the local minimum point. The present invention can adjust the filling and repelling potential field according to the situation of the surrounding obstacles by designing a filling and repelling potential field including a positive correlation gain factor, and adaptively fill the "saddle" of the local minimum, so that the agent can pass through the local minimum trap.

[0049] In one of the embodiments, the artificial potential field includes a repulsive potential field generated by an obstacle and an attractive potential field generated by a target; and the property of filling the repulsive potential field is the same as that of the repulsive potential field.

[0050] In one embodiment, the repulsive potential field is a modified repulsive potential field, and the modified repulsive potential field is:

[0051]

[0052] Among them, k rep is the positive correlation gain factor of the modified repulsive potential field, X is the current position of the agent, X0 is the position of the local minimum point, ρ0 is the maximum influence distance of the modified repulsive potential field, ρ(X,X0)=||X0-X|| is the distance between the agent and the obstacle, ρ(X,X g )=||X g -X|| is the distance between the agent and the target.

[0053] In one embodiment, the method further includes: constructing a filling repulsive potential field with the position of the local minimum point as the center, including:

[0054] Taking the position of the local minimum point as the center, the filled repulsive potential field is constructed as:

[0055]

[0056] Among them, k m To fill the positive correlation gain factor of the repulsive potential field, X m is the position of the local minimum point, ρ1 is the maximum influence distance of the filling repulsive potential field, ρ(X,X m )=||X m -X|| is the Euclidean distance between the agent and the local minimum point.

[0057] If the effect is still not ideal after filling, the filled potential field can be regarded as an obstacle, and its corresponding position is X m , the influence range is twice that of ρ1, and then added to the modified potential field model.

[0058] In one of the embodiments, it further includes: obtaining the obstacle distribution state around the intelligent agent;

[0059] When the number of obstacles within the preset range of the agent is greater than the preset threshold, the distance between the agent and the target point is obtained;

[0060] The positive correlation gain factor of the filling repulsive potential field is reduced according to the number of obstacles and the distance of the intelligent agent from the target point.

[0061] It should be understood that although Figure 1The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0062] In one embodiment, Figure 2 As shown, a device for improving the escape from local minimum in artificial potential field is provided, comprising: a local minimum point determination module 202, a filling and repelling potential field construction module 204 and a filling and repelling potential field adjustment module 206, wherein:

[0063] A local minimum point determination module 202 is used to obtain the position of the local minimum point where the agent is trapped in the artificial potential field;

[0064] The filling and repulsive potential field construction module 204 is used to construct a filling and repulsive potential field with the position of the local minimum point as the center; the filling and repulsive potential field includes a filling and repulsive potential field positive correlation gain factor and a filling and repulsive potential field maximum influence distance; when the distance between the current position of the agent and the local minimum point is greater than the filling and repulsive potential field maximum influence distance, the filling and repulsive potential field is 0; when the distance between the current position of the agent and the local minimum point is not greater than the filling and repulsive potential field maximum influence distance, the size of the filling and repulsive potential field is positively correlated with the filling and repulsive potential field positive correlation gain factor, and decreases as the distance from the agent to the local minimum point increases;

[0065] The filling and repelling potential field adjustment module 206 is used to obtain the obstacle distribution state around the intelligent agent, and adjust the positive correlation influencing factors in the filling and repelling potential field according to the obstacle distribution state until the intelligent agent escapes from the local minimum point.

[0066] The filling repulsive potential field construction module 204 is also used to construct a filling repulsive potential field with the position of the local minimum point as the center:

[0067]

[0068] Among them, k m To fill the positive correlation gain factor of the repulsive potential field, X m is the position of the local minimum point, ρ1 is the maximum influence distance of the filling repulsive potential field, ρ(X,X m )=||X m-X|| is the Euclidean distance between the agent and the local minimum point.

[0069] The filling and repulsive potential field adjustment module 206 is also used to obtain the obstacle distribution status around the intelligent agent; when the number of obstacles within the preset range of the intelligent agent is greater than the preset threshold, the distance between the intelligent agent and the target point is obtained; and the filling and repulsive potential field positive correlation gain factor is reduced according to the number of obstacles and the distance between the intelligent agent and the target point.

[0070] The specific limitation of the device for escaping from the local minimum in the improved artificial potential field can be referred to the limitation of the method for escaping from the local minimum in the improved artificial potential field above, which will not be repeated here. Each module in the above-mentioned device for escaping from the local minimum in the improved artificial potential field can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor calls and executes the operations corresponding to the above modules.

[0071] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for improving the escape from the local minimum in the artificial potential field is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0072] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0073] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above method embodiment when executing the computer program.

[0074] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0075] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0076] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0077] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method to improve the escape from local minima in artificial potential fields, It is characterized in that The method comprises: Get the location of the local minimum point where the agent is trapped in the artificial potential field; Taking the position of the local minimum point as the center, construct a filling and repulsive potential field; the filling and repulsive potential field includes a filling and repulsive potential field positive correlation gain factor and a filling and repulsive potential field maximum influence distance; when the distance between the current position of the agent and the local minimum point is greater than the filling and repulsive potential field maximum influence distance, the filling and repulsive potential field is 0; when the distance between the current position of the agent and the local minimum point is not greater than the filling and repulsive potential field maximum influence distance, the size of the filling and repulsive potential field is positively correlated with the filling and repulsive potential field positive correlation gain factor, and decreases with the increase of the distance from the agent to the local minimum point; Obtain the obstacle distribution state around the intelligent agent, and adjust the positive correlation influencing factors in the filling repulsive potential field according to the obstacle distribution state until the intelligent agent escapes from the local minimum point.

2. The method according to claim 1, It is characterized in that The artificial potential field includes a repulsive potential field generated by an obstacle and an attractive potential field generated by a target; the property of the filling repulsive potential field is the same as that of the repulsive potential field.

3. The method according to claim 2, It is characterized in that The repulsive potential field is a modified repulsive potential field, and the modified repulsive potential field is: Among them, k rep is the positive correlation gain factor of the modified repulsive potential field, X is the current position of the agent, and X 0 is the position of the local minimum point, ρ 0 is the maximum influence distance of the modified repulsive potential field, ρ(X,X 0 )=||X 0 -X|| is the distance between the agent and the obstacle, ρ(X,X g )=||X g -X|| is the distance between the agent and the target.

4. The method according to claim 3, It is characterized in that Taking the position of the local minimum point as the center, construct a filling repulsive potential field, including: Taking the position of the local minimum point as the center, the filled repulsive potential field is constructed as follows: Among them, k m is the positive correlation gain factor for filling the repulsive potential field, X m is the position of the local minimum point, ρ 1 is the maximum influence distance of the filling repulsive potential field, ρ(X,X m )=||X m -X|| is the Euclidean distance between the agent and the local minimum point.

5. The method according to claim 4, It is characterized in that Obtaining the obstacle distribution state around the intelligent agent, and adjusting the positive correlation influencing factor in the filling repulsive potential field according to the obstacle distribution state, including: Obtaining the obstacle distribution state around the intelligent agent; When the number of obstacles within the preset range of the agent is greater than a preset threshold, obtaining the distance between the agent and the target point; The positive correlation gain factor of the filling repulsive potential field is reduced according to the number of obstacles and the distance between the intelligent agent and the target point.

6. A device for improving the escape from local minima in artificial potential fields, It is characterized in that The device comprises: A local minimum point determination module is used to obtain the position of the local minimum point where the agent is trapped in the artificial potential field; A filling and repulsive potential field construction module is used to construct a filling and repulsive potential field with the position of the local minimum point as the center; the filling and repulsive potential field includes a filling and repulsive potential field positive correlation gain factor and a filling and repulsive potential field maximum influence distance; when the distance between the current position of the agent and the local minimum point is greater than the filling and repulsive potential field maximum influence distance, the filling and repulsive potential field is 0; when the distance between the current position of the agent and the local minimum point is not greater than the filling and repulsive potential field maximum influence distance, the size of the filling and repulsive potential field is positively correlated with the filling and repulsive potential field positive correlation gain factor, and decreases as the distance from the agent to the local minimum point increases; The filling and repulsive potential field adjustment module is used to obtain the obstacle distribution state around the intelligent agent, and adjust the positive correlation influencing factors in the filling and repulsive potential field according to the obstacle distribution state until the intelligent agent escapes from the local minimum point.

7. The device according to claim 6, It is characterized in that The filling repulsive potential field construction module is also used for: Taking the position of the local minimum point as the center, the filled repulsive potential field is constructed as follows: Among them, k m is the positive correlation gain factor for filling the repulsive potential field, X m is the position of the local minimum point, ρ 1 is the maximum influence distance of the filling repulsive potential field, ρ(X,X m )=||X m -X|| is the Euclidean distance between the agent and the local minimum point.

8. The device according to claim 7, It is characterized in that The filling repulsive potential field adjustment module is also used for: Obtaining the obstacle distribution state around the intelligent agent; When the number of obstacles within the preset range of the agent is greater than a preset threshold, obtaining the distance between the agent and the target point; The positive correlation gain factor of the filling repulsive potential field is reduced according to the number of obstacles and the distance between the intelligent agent and the target point.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images