Multi-agent boundary game method based on priority path planning

Abstract

The invention provides a multi-agent boundary game method based on priority path planning. The multi-agent boundary game method comprises the following steps: calculating relative assault time of intrusion from an agent to a boundary assault point and relative defense time of defense from the agent to the boundary assault point; based on the relative assault time and the relative defense time, calculating a priority parameter of each defense agent, optimizing a maximum matching algorithm by using the priority parameters, and determining a defense strategy combination; planning a path for each defense agent according to the defense strategy combination, optimizing a global path planning cost function by using a particle swarm algorithm, and generating a global optimal path of the defense agent; and the motion state of the defense agent is adjusted through a linear feedback control algorithm, so that the defense agent moves according to a global optimal path, and path tracking is realized. According to the method, priority path planning is combined with a maximum matching method, so that the problems of multi-agent defense task allocation and path planning in a complex obstacle environment are solved, and the defense success rate and adaptability are effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent control and path planning, and in particular to a multi-agent boundary game method based on priority path planning. Background Art

[0002] In recent years, adversarial game problems in multi-agent systems have gradually become a research hotspot, such as pursuit games, target pursuit defense games, and boundary game problems. Among them, boundary game problems are widely used in scenarios such as drone formation defense and marine unmanned boat defense. The research goal is that the defender prevents as many invaders as possible from breaking through the designated boundary, while the invader tries to break through the defense to enter the target area.

[0003] In existing boundary game research, most of them use the maximum matching algorithm to achieve the allocation of defense tasks, that is, to assign an intrusion target to each defense agent according to the possibility of successful defense. However, these methods usually assume that there is no collision problem between agents, which cannot fully meet the needs in complex practical applications. Especially in limited space, when a large number of agents are involved, collisions between agents are almost inevitable, and ignoring the collision problem may lead to the failure of defense tasks.

[0004] In addition, most existing studies design algorithms for simple barrier-free environments, without fully considering the complexity of actual scenarios, such as the presence of obstacles and the need for collision avoidance of multiple autonomous agents. In actual applications such as island defense and border patrols, defense scenarios often contain complex obstacle structures, and autonomous agents need to complete efficient defense while avoiding collisions, which places higher requirements on traditional algorithms.

[0005] Therefore, in view of the shortcomings of existing algorithms, how to realize the defense task allocation and path planning of multi-autonomous agent systems in complex obstacle environments, and at the same time solve the collision problem between autonomous agents, has become an important issue that needs to be urgently solved in the current field of boundary games. Summary of the invention

[0006] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0007] To this end, the first purpose of this application is to propose a multi-agent boundary game method based on priority path planning.

[0008] The second objective of this application is to propose a multi-autonomous agent boundary game device based on priority path planning.

[0009] The third objective of the present application is to provide an electronic device.

[0010] A fourth objective of the present application is to provide a computer-readable storage medium.

[0011] A fifth object of the present application is to provide a computer program product.

[0012] To achieve the above objectives, the first embodiment of the present application proposes a multi-agent boundary game method based on priority path planning, including:

[0013] According to the position, speed direction and boundary shape of the invading subject, the projection point and assault point of the invading direction are calculated, and the relative assault time is calculated by combining the path length and maximum speed;

[0014] According to the position of the defending agent and the obstacle environment, a local path length cost function and a local collision cost function are constructed to calculate the optimal path length, and the relative defense time is calculated in combination with the maximum speed of the defending agent.

[0015] Based on the relative attack time and the relative defense time, calculating the priority parameter of each of the defense agents, optimizing the maximum matching algorithm using the priority parameter, and determining a defense strategy combination;

[0016] Planning a path for each defense agent according to the combination of defense strategies, and optimizing the global path planning cost function using a particle swarm algorithm to generate a global optimal path for the defense agent;

[0017] The motion state of the defensive autonomous body is adjusted through a linear feedback control algorithm so that it moves along a global optimal path to achieve path tracking.

[0018] Optionally, the step of calculating the projection point and the assault point of the invasion direction according to the position, speed direction and the shape of the boundary of the defense area of ​​the invading subject, and calculating the relative assault time in combination with the path length and the maximum speed includes:

[0019] According to the invasion of the subject I j Current location and velocity direction vector u j =(cosφ j ,sinφ j ), determine the invasion direction;

[0020] The projection point P of the line connecting the invasion direction and the target perimeter center O is j As a reference point, the formula is:

[0021]

[0022] in, Indicates that from the intrusion self-agent I j The vector to the center O of the target area With the velocity direction vector u j The inner product of

[0023] From the reference point P j Calculate the boundary assault point A of the target area along the invasion direction j , the formula is:

[0024] A j =P j -u j (R 2 -|OP j |) 1 / 2

[0025] Where R is the radius of the target area, |OP j | represents the distance from the center of the target area to the projection point;

[0026] According to the path length and Invasion of the Self-Subject I j Maximum speed Calculate the relative assault time, the formula is:

[0027]

[0028] in, To invade the subject I j To Border Assault Point A j Relative assault time.

[0029] Optionally, the method of constructing a local path length cost function and a local collision cost function to calculate the optimal path length according to the position of the defending autonomous body and the obstacle environment, and calculating the relative defense time in combination with the maximum speed of the defending autonomous body includes:

[0030] Constructing a local path length cost function The formula used to calculate the path length of the defense agent from the current position to the boundary assault point is:

[0031]

[0032] in, are the continuous position points of the defending autonomous body in path planning, and n is the total number of path points;

[0033] Constructing local obstacle and collision avoidance cost functions It is used to handle obstacles and collision avoidance costs in the path. The formula is:

[0034]

[0035] like

[0036] in, is the distance from the defense agent to the obstacle center, r cis the obstacle radius;

[0037] The particle swarm algorithm is used to solve the local path planning cost function and obtain the defense agent D i From the initial position to the border assault point A j The length of the shortest path planned is l ij , where the formula of the local path planning cost function is:

[0038]

[0039] Among them, w 1 With w 2 are the weight parameters of the local path length cost and the local obstacle and collision avoidance cost respectively;

[0040] According to the length of the shortest path j ij and the maximum speed of the defensive agent The relative defense time is calculated as follows:

[0041]

[0042] in, To defend the subject D i To Border Assault Point A j Relative defense time.

[0043] Optionally, the step of calculating a priority parameter of each of the defense agents based on the relative attack time and the relative defense time, optimizing a maximum matching algorithm using the priority parameter, and determining a defense strategy combination includes:

[0044] Based on the relative attack time and the relative defense time, the priority parameter of each defense agent is calculated, and the formula is:

[0045]

[0046] Where, ΔD i Denotes the defensive agent D i The priority parameter;

[0047] Through the maximum matching algorithm, defense agents and intrusion agents with low priority parameters are matched first. The matching conditions are:

[0048]

[0049] For the defense agents and intrusion agents that meet the matching conditions, tasks are assigned according to their priorities and a defense strategy combination is generated.

[0050] Optionally, planning a path for each defense agent according to the defense strategy combination, and optimizing the global path planning cost function using a particle swarm algorithm to generate an optimal path for the defense agent, includes:

[0051] Based on the defense strategy combination, a global path planning cost function of the defense cluster is constructed. The formula is:

[0052]

[0053] Among them, Δ 0 is the offset adjustment constant;

[0054] And, construct the global obstacle and collision avoidance cost function of the defense cluster The formula is:

[0055]

[0056] in, represents the distance between the defending agents, r 0 is the collision avoidance distance threshold;

[0057] The global path planning cost function is solved by the particle swarm algorithm to generate the global optimal path of the defense agent. The formula of the global path planning cost function is:

[0058]

[0059] Among them, w' 1 With w' 2 are the weight parameters of the global path length cost and the global obstacle and collision avoidance cost respectively.

[0060] Optionally, the step of adjusting the motion state of the defense autonomous body by a linear feedback control algorithm so that the defense autonomous body moves along a global optimal path to achieve path tracking includes:

[0061] Design a linear feedback control algorithm, the formula is:

[0062]

[0063] Wherein, k is the feedback gain parameter;

[0064] The linear feedback control algorithm is used to adjust the motion state of the defense autonomous body so that it moves along the global optimal path, thereby achieving path tracking.

[0065] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a multi-agent boundary game device based on priority path planning, including:

[0066] The assault time calculation module is used to calculate the projection point and assault point of the invasion direction according to the position, speed direction and boundary shape of the defense area of ​​the invading subject, and calculate the relative assault time in combination with the path length and maximum speed;

[0067] The defense time calculation module is used to construct a local path length cost function and a local collision cost function to calculate the optimal path length according to the position of the defense agent and the obstacle environment, and calculate the relative defense time in combination with the maximum speed of the defense agent;

[0068] A defense task allocation module, used to calculate the priority parameter of each of the defense autonomous bodies based on the relative attack time and the relative defense time, optimize the maximum matching algorithm using the priority parameter, and determine the defense strategy combination;

[0069] A global path planning module is used to plan a path for each defense agent according to the combination of defense strategies, and to optimize the global path planning cost function using a particle swarm algorithm to generate a global optimal path for the defense agent;

[0070] The motion control module is used to adjust the motion state of the defensive autonomous body through a linear feedback control algorithm so that it moves along a global optimal path to achieve path tracking.

[0071] To achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0072] The memory stores computer-executable instructions;

[0073] The processor executes the computer-executable instructions stored in the memory to implement the method as described in any one of the first aspects.

[0074] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, in which computer-readable storage medium is stored computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method as described in any one of the first aspects.

[0075] To achieve the above-mentioned purpose, the fifth aspect of the present application proposes a computer program product, which implements any method in the first aspect when executed by a processor.

[0076] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0077] By setting the defense priority by calculating the relative defense time and the relative attack time, the present application effectively improves the success rate of border defense; by combining the collision avoidance problem of obstacles and defense autonomous bodies, the present application is not only applicable to simple barrier-free environments, but also to complex environments with multiple obstacles; by realizing the overall planning and design of border defense through optimization methods, the present application can make full use of existing optimization algorithms to efficiently solve the defense path.

[0078] Compared with the prior art, this application proposes a defense strategy based on priority path planning for the multi-autonomous boundary game problem, which can control multiple autonomous entities to defend against the invasion of external autonomous entities into the region. Most existing algorithms complete task allocation based on the maximum matching idea, that is, a defense target is assigned to each autonomous entity according to the possibility of successful defense. This application has made an important extension on this basis, and through the combination of priority path planning and maximum matching method, the defense algorithm can adapt to complex obstacle environments. This coupling method has significant application value in multiple scenarios. For example, in the island and reef defense scenario based on unmanned boats, facing the complex situation of multiple reefs around the islands and reefs, the algorithm of this application can efficiently complete the defense task. In addition, this application solves the collision avoidance problem between defensive autonomous entities by introducing a collision avoidance cost function in path planning, which is particularly important in the problem of large-scale autonomous boundary defense in a small area. This function enhances the practicality and reliability of the defense system in complex and dynamic environments.

[0079] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0081] Figure 1 A flowchart of a multi-agent boundary game method based on priority path planning provided in an embodiment of the present application;

[0082] Figure 2 A structural schematic diagram of a multi-autonomous agent boundary game device based on priority path planning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0083] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0084] In view of the problems existing in the prior art, the present application provides a multi-agent boundary game method based on priority path planning. Figure 1 A flowchart of a multi-agent boundary game method based on priority path planning provided in an embodiment of the present application.

[0085] Before explaining the technical solution of the present application, the technical scenario of the present application is first explained.

[0086] The scenario studied in this application is a two-dimensional plane area The border defense problem in the region Ω in The core area contains important targets, and its boundary is a circle with center O = (0,0) and radius R in The region Ω is the region containing Ω in A larger region whose boundary is also circular with center O=(0,0) and radius R, and satisfies Define the buffer as Ω loop =Ω-Ω in , which is the annular area between the two circles.

[0087] In the boundary game problem of this scenario, consider a multi-agent system with n agents, which includes two types of agents: defending agents and invading agents. The goal of the invading agent is to break through the buffer zone Ω loop , enter the core area Ω in The goal of the defense agent is to block the intruder and ensure that it cannot enter the core areaΩ in .

[0088] This scenario is widely used in tasks such as drone patrol defense and maritime unmanned boat island and reef defense. The research focuses on how to achieve effective interception of invaders by defenders through reasonable task allocation and path planning in a complex dynamic environment.

[0089] like Figure 1 As shown, a multi-agent boundary game method based on priority path planning shown in this application includes the following steps:

[0090] Step 101, according to the position, speed direction and boundary shape of the invading subject, the projection point and the assault point of the invading direction are calculated, and the relative assault time is calculated in combination with the path length and the maximum speed.

[0091] In the embodiment of the present application, firstly, according to the intrusion self-subject I j Current location and velocity direction vector u j =(cosφ j ,sinφ j) to determine the invasion direction to further calculate its assault position in the target area.

[0092] In the embodiment of the present application, the intrusion direction is calculated based on the current position and velocity direction vector of the intruding subject, and the velocity direction vector is expressed as a unit vector, which describes the moving direction of the intruding subject. The intrusion direction is the starting point for the assault point calculation and reflects the expected movement trajectory of the intruding subject.

[0093] Then, the projection point P of the line connecting the invasion direction and the target perimeter center O is j As a reference point, the formula is:

[0094]

[0095] in, Indicates that from the intrusion self-agent I j The vector to the center O of the target area With the velocity direction vector u j The inner product of .

[0096] In the embodiment of the present application, the projection point is the projection position of the center of the target area on the straight line of the invasion direction. Its calculation formula uses the property of the vector inner product. By obtaining the projection relationship between the current position and the speed direction, the path point where the invading subject is most likely to approach the target area can be determined. The calculation accuracy of the projection point directly affects the accuracy of the assault point position.

[0097] Then, from the reference point P j Calculate the boundary assault point A of the target area along the invasion direction j , the formula is:

[0098] A j =P j -u j (R 2 -|OP f |) 1 / 2

[0099] Where R is the radius of the target area, |OP j |Indicates the distance from the center of the target area to the projection point.

[0100] In the embodiment of the present application, the assault point is the contact point of the invading subject on the boundary of the target area, which is calculated based on the position of the projection point and the geometric parameters of the target area (such as the radius).

[0101] Finally, according to the path length and Invasion of the Self-Subject I j Maximum speed Calculate the relative assault time using the formula:

[0102]

[0103] in, To invade the subject I j To Border Assault Point A j Relative assault time.

[0104] In the embodiment of the present application, the relative assault time is the time required for the invading agent to reach the assault point from the current position. Its calculation combines the path length and the maximum speed of the invading agent. The formula reflects the shortest time path of the invading agent under ideal conditions. The relative assault time is the core parameter in the allocation of defense tasks and provides an important reference for the priority setting and task planning of the defense agent.

[0105] Step 102, based on the position of the defending agent and the obstacle environment, a local path length cost function and a local collision cost function are constructed to calculate the optimal path length, and the relative defense time is calculated in combination with the maximum speed of the defending agent.

[0106] In the present embodiment, in order to simplify the calculation, it is assumed that the defense agent D i Only at Border Assault Point A j Block the invasion of the subject I j ,By ignoring the collision avoidance problem between the defending autonomous agents and simplifying the obstacle model, the path planning problem can be ,converted to the path optimization problem of a single autonomous agent in an ,obstacle environment.

[0107] The specific steps are as follows:

[0108] First, construct a local path length cost function It is used to calculate the path length from the current position of the defense agent to the boundary assault point. The formula is:

[0109]

[0110] in, are the continuous position points of the defense agent in path planning, and n is the total number of path points, indicating the number of path segments.

[0111] This function describes the geometric length of the path and is the basic optimization goal of path planning, used to solve the shortest path.

[0112] Secondly, construct local obstacle and collision avoidance cost function The formula used to handle obstacles and collision avoidance costs in the path is:

[0113]

[0114] like

[0115] in, is the distance from the defense agent to the obstacle center, r c is the obstacle radius, and z is the total number of obstacles.

[0116] Then, the local path length cost function and the local obstacle and collision avoidance cost function are combined to form a complete local path planning cost function. By adding obstacle constraints to path planning, it is possible to ensure that the defending agent avoids obstacles and thus generates a feasible path. The formula of the local path planning cost function is:

[0117]

[0118] Among them, w 1 With w 2 are the weight parameters of the local path length cost and the local obstacle and collision avoidance cost respectively.

[0119] Then the particle swarm algorithm is used to solve the above local path planning cost function to obtain the defense agent D i From the initial position to the border assault point A j The length of the shortest path planned is l ij , and further according to the length of the shortest path l ij and the maximum speed of the defensive agent Calculate the relative defense time, the formula is:

[0120]

[0121] in, To defend the subject D i To Border Assault Point A j Relative defense time.

[0122] It can be understood that the particle swarm algorithm transforms the path planning problem into an optimization problem, and finds the optimal solution of the cost function through global and local searches of particles.

[0123] Through the above steps, the relative defense time can be quickly calculated while ignoring the need for collision avoidance between defense agents. In addition, the introduction of the particle swarm algorithm makes the optimization of path planning more efficient, which not only meets the requirement of the shortest path, but also takes into account the impact of obstacles on the path.

[0124] Step 103, based on the relative attack time and the relative defense time, the priority parameter of each defense agent is calculated, and the maximum matching algorithm is optimized using the priority parameter to determine the defense strategy combination.

[0125] In the embodiment of the present application, the priority parameter of each defense autonomous body is first calculated, and the formula is:

[0126]

[0127] Where, ΔD i Denotes the defensive agent D i The priority parameter.

[0128] It is understandable that if ΔD i is greater than 0, it means that the defending agent can intercept the invading agent before it reaches the boundary assault point, and ΔD i The lower the value, the more urgent the defense mission is.

[0129] Then, the defense agents and intrusion agents are mapped into a bipartite graph G, and a set definition is performed: a set D includes all defense agents D i , another set = including all intrusion agents I j For any defensive agent D i Invasion of the Self-Subject I j , if the condition is met That is, the defending agent can intercept the invading agent before it reaches the assault point, then add D to the bipartite graph G i and I j The edge between.

[0130] Then, in the constructed bipartite graph G, run the maximum matching algorithm to prioritize matching with the priority parameter low ΔD i The matching conditions for the defense agent and the intrusion agent are:

[0131]

[0132] In the embodiment of the present application, a linear programming algorithm or a Hopcroft-Karp algorithm may be selected to calculate the maximum match, and the present application does not make any specific limitation on this.

[0133] Finally, the best matching combination between the defending agent and the intruding agent is found in the bipartite graph G through the maximum matching algorithm, that is, the maximum matching result, and the defense strategy combination is generated according to the maximum matching result.

[0134] Specifically, tasks are assigned to defense agents and intrusion agents that meet the matching conditions; the intrusion target assigned to each defense agent is its defense task; and the defense strategy combination is output as the input for path planning and trajectory tracking.

[0135] Step 104 , plans a path for each defense agent according to the defense strategy combination, and uses a particle swarm algorithm to optimize the global path planning cost function to generate a global optimal path for the defense agent.

[0136] In the embodiment of the present application, based on the combination of defense strategies, a path is planned for each defense agent, and a global path planning cost function of the defense cluster is constructed to optimize the path and generate a global optimal path. This step is intended to ensure that all defense agents achieve overall optimization of cluster movement while completing the assigned tasks.

[0137] The specific steps are as follows:

[0138] First, construct the global path planning cost function of the defense cluster The formula used to describe the path optimization goal of the entire defense cluster is:

[0139]

[0140] Among them, Δ 0 This is an offset adjustment constant used to prevent the priority parameter from being too small, resulting in an excessively large path weight.

[0141] Then, construct the global obstacle and collision avoidance cost function of the defense cluster It is used to deal with obstacles in the defense cluster and collision avoidance requirements between defense agents. The formula is:

[0142]

[0143] like

[0144] in, represents the distance between the defending agents, r 0 is the collision avoidance distance threshold.

[0145] Then, the global path length cost function and the global obstacle and collision avoidance cost function are combined to form a comprehensive cost function for global path planning, which is:

[0146]

[0147] Among them, w' 1 With w' 2 are the weight parameters of the global path length cost and the global obstacle and collision avoidance cost respectively.

[0148] Finally, the global path planning cost function is solved by the particle swarm algorithm to generate the global optimal path of the defense cluster.

[0149] It can be understood that the particle swarm algorithm transforms the path planning problem into an optimization problem, and finds the optimal solution of the cost function through global and local searches of particles.

[0150] Step 105, adjusting the motion state of the defense autonomous body through a linear feedback control algorithm so that it moves along the global optimal path to achieve path tracking.

[0151] In the embodiment of the present application, a linear feedback control algorithm is first designed, and its formula is:

[0152]

[0153] Where k is the feedback gain parameter, which is used to control the adjustment strength; (x i ,y i ) is the current position of the defending agent, is the coordinate of the target point on the global optimal path

[0154] Then, a linear feedback control algorithm is used to adjust the motion state of the defense agent in real time, so that it moves along the global optimal path and approaches the target point on the planned path.

[0155] It should be noted that during the path tracking process, the defense agent needs to dynamically update the target point: when the defense agent approaches the current target point (the deviation distance is less than the threshold), the path planning system will update the next target point; the defense agent completes all target points on the global optimal path in sequence until it reaches the final target (boundary assault point).

[0156] Through the linear feedback control algorithm, the defense agent can accurately follow the global optimal path and achieve real-time path tracking in a dynamic environment. This control strategy is simple to calculate and fast to adjust, and is suitable for the coordinated motion control of multiple agents. Combined with the global optimal path planning results, the path tracking algorithm can significantly improve the execution accuracy and reliability of the defense task, and has important value in practical applications.

[0157] In order to implement the above embodiments, the present application also proposes a multi-autonomous agent boundary game device based on priority path planning. Figure 2 A schematic diagram of the structure of a multi-agent boundary game device based on priority path planning provided in an embodiment of the present application. Figure 2 As shown, the device comprises:

[0158] The assault time calculation module 100 is used to calculate the projection point and the assault point of the invasion direction according to the position, speed direction and the boundary shape of the defense area of ​​the invading subject, and calculate the relative assault time in combination with the path length and the maximum speed;

[0159] The defense time calculation module 200 is used to construct a local path length cost function and a local collision cost function to calculate the optimal path length according to the position of the defense agent and the obstacle environment, and calculate the relative defense time in combination with the maximum speed of the defense agent;

[0160] The defense task allocation module 300 is used to calculate the priority parameter of each defense agent based on the relative attack time and the relative defense time, optimize the maximum matching algorithm using the priority parameter, and determine the defense strategy combination;

[0161] The global path planning module 400 is used to plan a path for each defense agent according to the defense strategy combination, and optimize the global path planning cost function using a particle swarm algorithm to generate a global optimal path for the defense agent;

[0162] The motion control module 500 is used to adjust the motion state of the defense autonomous body through a linear feedback control algorithm so that it moves along a global optimal path to achieve path tracking.

[0163] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0164] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0165] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0166] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0167] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0168] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0169] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0170] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0171] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0172] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0173] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0174] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0175] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0176] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

[0177] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0178] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A multi-agent boundary game method based on priority path planning, characterized in that: The following steps are involved: According to the position, speed direction and boundary shape of the invading subject, the projection point and assault point of the invading direction are calculated, and the relative assault time is calculated by combining the path length and maximum speed; According to the position of the defending agent and the obstacle environment, a local path length cost function and a local collision cost function are constructed to calculate the optimal path length, and the relative defense time is calculated in combination with the maximum speed of the defending agent. Based on the relative attack time and the relative defense time, calculating the priority parameter of each of the defense agents, optimizing the maximum matching algorithm using the priority parameter, and determining a defense strategy combination; Planning a path for each defense agent according to the combination of defense strategies, and optimizing the global path planning cost function using a particle swarm algorithm to generate a global optimal path for the defense agent; The motion state of the defensive autonomous body is adjusted through a linear feedback control algorithm so that it moves along a global optimal path to achieve path tracking.

2. The method according to claim 1, characterized in that The method of calculating the projection point and the assault point of the invasion direction according to the position, speed direction and the boundary shape of the defense area of ​​the invading subject, and calculating the relative assault time in combination with the path length and the maximum speed includes: According to the invasion of the subject I j Current location and velocity direction vector u j =(cosφ j ,sinφ j ), determine the invasion direction; The projection point P of the line connecting the invasion direction and the target perimeter center O is j As a reference point, the formula is: in, Indicates that from the intrusion self-agent I j The vector to the center O of the target area With the velocity direction vector u j The inner product of From the reference point P j Calculate the boundary assault point A of the target area along the invasion direction j , the formula is: A j =P j -u j (R 2 -|OP j |) 1 / 2 Where R is the radius of the target area, |OP j | represents the distance from the center of the target area to the projection point; According to the path length and Invasion of the Self-Subject I j Maximum speed Calculate the relative assault time, the formula is: in, To invade the subject j To Border Assault Point A j Relative assault time.

3. The method according to claim 2, characterized in that The method of constructing a local path length cost function and a local collision cost function to calculate the optimal path length according to the position of the defense agent and the obstacle environment, and calculating the relative defense time in combination with the maximum speed of the defense agent, includes: Constructing a local path length cost function The formula used to calculate the path length of the defense agent from the current position to the boundary assault point is: in, are the continuous position points of the defending autonomous body in path planning, and n is the total number of path points; Constructing local obstacle and collision avoidance cost functions It is used to handle obstacles and collision avoidance costs in the path. The formula is: like in, is the distance from the defense agent to the obstacle center, r c is the obstacle radius; The particle swarm algorithm is used to solve the local path planning cost function and obtain the defense agent D i From the initial position to the border assault point A j The length of the shortest path planned is l ij , where the formula of the local path planning cost function is: Among them, w1 and W2 are the weight parameters of the local path length cost and the local obstacle and collision avoidance cost respectively; According to the length of the shortest path l ij and the maximum speed of the defensive agent The relative defense time is calculated as follows: in, To defend the subject D i To Border Assault Point A j Relative defense time.

4. The method according to claim 3, characterized in that The step of calculating the priority parameter of each of the defense agents based on the relative attack time and the relative defense time, optimizing the maximum matching algorithm using the priority parameter, and determining the defense strategy combination comprises: Based on the relative attack time and the relative defense time, the priority parameter of each defense agent is calculated, and the formula is: Where, ΔD i Denotes the defensive agent D i The priority parameter; Through the maximum matching algorithm, defense agents and intrusion agents with low priority parameters are matched first. The matching conditions are: For the defense agents and intrusion agents that meet the matching conditions, tasks are assigned according to their priorities and a defense strategy combination is generated.

5. The method according to claim 4, characterized in that The method of planning a path for each defense agent according to the defense strategy combination and optimizing the global path planning cost function using a particle swarm algorithm to generate an optimal path for the defense agent includes: Based on the defense strategy combination, a global path planning cost function of the defense cluster is constructed. The formula is: Where Δ0 is the offset adjustment constant; And, construct the global obstacle and collision avoidance cost function of the defense cluster The formula is: like in, represents the distance between the defending agents, r0 is the collision avoidance distance threshold; The global path planning cost function is solved by the particle swarm algorithm to generate the global optimal path of the defense agent. The formula of the global path planning cost function is: Among them, w'1 and w'2 are the weight parameters of the global path length cost and the global obstacle and collision avoidance cost respectively.

6. The method according to claim 5, characterized in that The method of adjusting the motion state of the defense autonomous body by a linear feedback control algorithm so that the defense autonomous body moves along a global optimal path to achieve path tracking includes: Design a linear feedback control algorithm, the formula is: Wherein, k is the feedback gain parameter; The linear feedback control algorithm is used to adjust the motion state of the defense autonomous body so that it moves along the global optimal path, thereby achieving path tracking.

7. A multi-agent boundary game device based on priority path planning, characterized in that: Includes the following modules: The assault time calculation module is used to calculate the projection point and assault point of the invasion direction according to the position, speed direction and boundary shape of the defense area of ​​the invading subject, and calculate the relative assault time in combination with the path length and maximum speed; The defense time calculation module is used to construct a local path length cost function and a local collision cost function to calculate the optimal path length according to the position of the defense agent and the obstacle environment, and calculate the relative defense time in combination with the maximum speed of the defense agent; A defense task allocation module, used to calculate the priority parameter of each of the defense autonomous bodies based on the relative attack time and the relative defense time, optimize the maximum matching algorithm using the priority parameter, and determine the defense strategy combination; A global path planning module is used to plan a path for each defense agent according to the combination of defense strategies, and to optimize the global path planning cost function using a particle swarm algorithm to generate a global optimal path for the defense agent; The motion control module is used to adjust the motion state of the defensive autonomous body through a linear feedback control algorithm so that it moves along a global optimal path to achieve path tracking.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images