Multi-agent motion modeling method and device based on environment

Abstract

The invention discloses an environment-based multi-agent motion modeling method and device. The method comprises the following steps: acquiring task demand information; constructing a multi-agent dynamic environment management model; and processing the task demand information based on the multi-agent dynamic environment management model to obtain simulation result information. According to the method, the multi-agent dynamic environment management model and the multi-agent self-adaptive motion resolving model are utilized, high-precision prediction and simulation of the formation motion state of the multi-agents under different environment conditions are achieved, and the authenticity and application value of analog simulation are improved.

Description

Technical Field

[0001] The present invention relates to the field of modeling and simulation, and particularly to a method and device for multi-agent motion modeling based on an environment. Background Art

[0002] In the current field of simulation modeling, traditional motion modeling usually focuses on the behavior analysis of a single object, and it is easy to ignore the environmental factors and the direct influence of other agents on its motion state. For example, when a ground vehicle moves, it usually needs to move along a road and maintain a specific distance, and at the same time, it also needs to take into account the influencing factors such as road conditions. To address this limitation, the present invention introduces the concept of environment dominance, uses a multi-agent dynamic environment management model to dynamically manage and adjust the route information of each agent, and on the premise of fully considering environmental factors, schedules the motion solution model of multiple agents as needed, thereby improving the authenticity and application value of the simulation. Summary of the Invention

[0003] The technical problem to be solved by the present invention is that the present invention provides a method and device for multi-agent motion modeling based on an environment, which uses a multi-agent dynamic environment management model and a multi-agent adaptive motion solution model to achieve high-precision prediction and simulation of the formation-keeping motion state of multiple agents under different environmental conditions, and improves the authenticity and application value of the simulation.

[0004] To solve the above technical problem, in the first aspect of the embodiments of the present invention, a method for multi-agent motion modeling based on an environment is disclosed, and the method includes:

[0005] S1, obtaining task requirement information;

[0006] S2, constructing a multi-agent dynamic environment management model;

[0007] S3, processing the task requirement information based on the multi-agent dynamic environment management model to obtain simulation result information.

[0008] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the constructing of the multi-agent dynamic environment management model includes:

[0009] S21, obtaining the motion input interface requirement information of the agent;

[0010] S22, obtaining the position state output interface requirement information of the agent;

[0011] S23, obtaining the motion route information of the agent based on the basic environment dynamic database;

[0012] S24. Based on the motion input interface requirement information, the position status output interface requirement information, and the agent motion route information, a multi-agent dynamic environment management model is constructed.

[0013] As an alternative implementation, in the first aspect of the embodiments of the present invention, processing the task requirement information based on the multi-agent dynamic environment management model to obtain simulation result information includes:

[0014] S31. Analyze and process the task requirement information to obtain motion request information;

[0015] The motion request information includes starting point information, destination point information, travel route information, travel formation information, and task time information;

[0016] S32. Based on the multi-agent dynamic environment management model, process the motion request information to obtain simulation result information.

[0017] As an alternative implementation, in the first aspect of the embodiments of the present invention, processing the motion request information based on the multi-agent dynamic environment management model to obtain simulation result information includes:

[0018] S321. Use the travel route information to match the basic environment dynamic database to obtain road information and terrain information;

[0019] S322. Use the road information, the terrain information, and the agent performance information to calculate the motion time information;

[0020] S323. Based on the multi-agent dynamic environment management model, perform a solution process on the motion time information and the agent performance information to obtain the agent solution position information;

[0021] S324. Process the agent solution position information to obtain simulation result information.

[0022] As an alternative implementation, in the first aspect of the embodiments of the present invention, performing a solution process on the motion time information and the agent performance information based on the multi-agent dynamic environment management model to obtain the agent solution position information includes:

[0023] S3231. Obtain the travel formation information;

[0024] S3232. Analyze the travel formation information to obtain the total number value of the vehicles in the travel convoy;

[0025] S3233. Use the multi-agent dynamic environment management model to obtain the driving vehicle information set;

[0026] S3234. Based on the multi-agent dynamic environment management model, using the multi-agent adaptive motion solution model, process the information set of the traveling vehicles and the total number of vehicles in the traveling fleet to obtain the expected position information of the agents and the calculated position information of the agents.

[0027] As an alternative implementation, in the first aspect of the embodiments of the present invention, the step of processing the information set of the traveling vehicles and the total number of vehicles in the traveling fleet based on the multi-agent dynamic environment management model using the multi-agent adaptive motion solution model to obtain the expected position information of the agents and the calculated position information of the agents includes:

[0028] S32341. Obtain the current time information.

[0029] S32342. Use the current time information to calculate and obtain the vehicle travel time information.

[0030] S32343. Perform calculation processing on the vehicle travel time information and the information set of the traveling vehicles to obtain the vehicle position information.

[0031] S32344. Use the vehicle position information to match the basic environment dynamic database to obtain the current road state information.

[0032] S32345. Determine whether the value of the current road state information is equal to a first preset value to obtain a first road state judgment value.

[0033] S32346. When the first road state judgment value is yes, based on the first multi-agent motion solution sub-model, process the vehicle travel time information and the information set of the traveling vehicles to obtain the expected position information of the agents and the calculated position information of the agents.

[0034] When the first road state judgment value is no, execute S32347.

[0035] S32347. Determine whether the value of the current road state information is equal to a second preset value to obtain a second road state judgment value.

[0036] When the second road state judgment value is yes, based on the second multi-agent motion solution sub-model, process the vehicle travel time information and the information set of the traveling vehicles to obtain the expected position information of the agents and the calculated position information of the agents.

[0037] When the second road state judgment value is no, execute S32348.

[0038] S32348, determine whether the value of the current road status information is equal to the third preset value to obtain a third road status judgment value;

[0039] When the third road status judgment value is yes, based on the first multi-intelligent motion operator model, process the vehicle driving time information and the set of driving vehicle information to obtain the expected position information of the intelligent agent and the calculated position information of the intelligent agent;

[0040] When the third road status judgment value is no, execute S32349;

[0041] S32349, obtain the current road obstacle information, update the current road obstacle information to the basic environment dynamic database, and execute S321.

[0042] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the expression of the first multi-intelligent motion operator model is:

[0043]

[0044] Among them, represents the expected position of the i-th vehicle; represents the calculated position of the i-th vehicle; represents the initial position vector of the i-th vehicle, represents the unit vector of the maneuvering direction of the i-th vehicle, V represents the maneuvering speed; T i represents the maneuvering time of the i-th vehicle; i represents the vehicle index in the marching formation; represents the unit vector of the formation direction; S 间距 represents the formation spacing;

[0045] The expression of the second multi-intelligent motion operator model is:

[0046]

[0047] Among them, represents the expected position of the i-th vehicle; represents the calculated position of the i-th vehicle; V represents the maneuvering speed represents the unit vector of the maneuvering direction of the i-th vehicle; ΔT i represents the integration step length of the i-th vehicle; a represents the initial value of integration; b represents the end value of integration.

[0048] The second aspect of the embodiments of the present invention discloses a multi-agent motion modeling device based on the environment, and the device includes: a data acquisition module, a management model construction module, and a simulation processing module;

[0049] The data acquisition module is used to acquire task requirement information;

[0050] The management model construction module is used to construct a multi-agent dynamic environment management model;

[0051] The simulation processing module is used to process the task requirement information based on the multi-agent dynamic environment management model to obtain simulation result information.

[0052] The third aspect of the present invention discloses another multi-agent motion modeling device based on the environment. The device includes:

[0053] A memory storing executable program code;

[0054] A processor coupled to the memory;

[0055] The processor calls the executable program code stored in the memory and executes some or all of the steps in the multi-agent motion modeling method based on the environment disclosed in the first aspect of the embodiments of the present invention.

[0056] The fourth aspect of the present invention discloses a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, and when the computer instructions are called, some or all of the steps in the multi-agent motion modeling method based on the environment disclosed in the first aspect of the embodiments of the present invention are executed.

[0057] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0058] In the embodiments of the present invention, the multi-agent dynamic environment management model is used to dynamically manage and adjust the route information of each agent, and the multi-agent adaptive motion resolution model is used to schedule the motion resolution algorithm of the multi-agent as needed according to the environment information, realizing high-precision prediction and simulation of the formation-keeping motion state of multi-agents under different environmental conditions, and improving the authenticity and application value of the simulation. Description of the Drawings

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0060] Figure 1 It is a scenario schematic diagram of the multi-agent motion modeling device based on the environment provided by the embodiments of the present invention;

[0061] Figure 2 It is a flowchart of a multi-agent motion modeling method based on the environment disclosed by the embodiments of the present invention;

[0062] Figure 3 It is a schematic structural diagram of a multi-agent motion modeling device based on the environment disclosed in an embodiment of the present invention;

[0063] Figure 4 It is a schematic structural diagram of another multi-agent motion modeling device based on the environment disclosed in an embodiment of the present invention. Specific Embodiments

[0064] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0065] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0066] Referring to "embodiments" herein means that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0067] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description". Any embodiment described as "exemplary" in this application is not necessarily to be construed as more preferred or more advantageous than other embodiments. In order to enable any person skilled in the art to implement and use this application, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that this application can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid unnecessary details from obscuring the description of this application. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in this application.

[0068] It should be noted that since the method of the embodiment of the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time, which is actually time information. It can be understood that in subsequent embodiments, if dimensions, quantities, positions, etc. are mentioned, they are all corresponding data existences for the computer device to process, and specific details are not elaborated here.

[0069] It should be noted that a brief description of the artificial intelligence-related technologies that may be involved in the present application is given. Artificial Intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, and is a theory, method, technology, and application system that can perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science. It attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence is also to study the design principles and implementation methods of various intelligent machines to enable the machines to have the functions of perception, reasoning, and decision-making.

[0070] Artificial intelligence technology is an interdisciplinary subject, involving a wide range of fields, including both hardware-level technologies and software-level technologies. Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0071] Computer Vision Technology (CV) Computer vision is a science that studies how to make machines "see". Further, it refers to using cameras and computers to replace human eyes to perform machine vision such as target recognition and measurement, and further perform graphic processing to make the computer-processed images more suitable for human eyes to observe or be transmitted to instruments for detection. As a scientific discipline, computer vision studies related theories and technologies and attempts to establish an artificial intelligence system that can obtain information from images or multi-dimensional data. Computer vision technology usually includes technologies such as image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, etc., and also includes common biometric recognition technologies such as face recognition and fingerprint recognition.

[0072] The single-modal information is data of only one type, such as one of the data information like text, image, audio, video, electromagnetic signal, etc. The multi-modal information is data information including at least two types of single-modal information. Further, the multi-modal information is applicable to complex tasks that require integrating multiple information sources, such as sentiment analysis, robot interaction, autonomous driving, etc. By integrating information of multiple modalities, higher performance and accuracy can usually be achieved in tasks.

[0073] A large model refers to an artificial neural network model with a very large number of parameters. In the field of artificial intelligence, a large model usually refers to a model with hundreds of millions to trillions of parameters. The model usually needs to be trained on a large-scale dataset and requires a large amount of computing resources for optimization and adjustment. Large models are usually used to solve complex natural language processing, computer vision, speech recognition and other tasks. Generative AI is a type of AI that can create new content and ideas, including conversations, stories, images, videos and music. In the embodiments of the present application, the large model can be large language models such as ChatGPT, BERT, XLNet, Zhipu Model, Claude, Moonshot AI Model, ChatGLM Model, Qianyitongwen Model, MiniMax Model, Spark Model, Llama Model, 360GPT Model, Qwen Model, Baichuan Model, Lark Model, vivoLM Model and Wenxin Yiyan, and the embodiments of the present application do not make limitations.

[0074] The embodiments of the present application provide a method, system, device, computer device and computer-readable storage medium for multi-agent motion modeling based on the environment, which will be described in detail below.

[0075] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the scenario of the multi-agent motion analysis and evaluation system provided by the embodiments of the present application. The evaluation and analysis system may include a computer device 100, and a multi-agent motion modeling device based on the environment is integrated in the computer device 100, such as Figure 1 the computer device in

[0076] In the embodiments of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiments of the present application includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. Among them, the cloud server is composed of a large number of computers or network servers based on cloud computing.

[0077] It can be understood that the computer device 100 used in the embodiments of the present application can be a device that includes both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing two-way communication on a two-way communication link. Such devices can include: cellular or other communication devices, which have a single-line display or a multi-line display or cellular or other communication devices without a multi-line display. Specifically, the computer device 100 can be a desktop terminal or a mobile terminal, and the computer device 100 can also be a mobile phone, a tablet computer, a laptop computer, etc.

[0078] Those skilled in the art can understand that Figure 1 the application environment shown in is only one application scenario of the solution of the present application, and does not constitute a limitation on the application scenario of the solution of the present application. Other application environments can also include more or fewer computer devices than Figure 1 shown in, for example Figure 1 only 1 computer device is shown in. It can be understood that the system can also include one or more other services, which are not specifically limited here.

[0079] In addition, as Figure 1 shown, the evaluation and analysis system can also include a memory 200 for storing simulation data, such as expert library data and simulation result data, etc.

[0080] It should be noted that Figure 1 the scenario schematic diagram of the evaluation and analysis system shown is only an example. The evaluation and analysis system and scenario described in the embodiments of the present application are for more clearly explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art know that with the evolution of the simulation control management system and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0081] The present invention discloses a method and device for multi-agent motion modeling based on environment, which uses a multi-agent dynamic environment management model to dynamically manage and adjust the route information of each agent, and uses a multi-agent adaptive motion solution model to schedule the motion solution algorithm of the multi-agent as needed according to the environment information, realizing high-precision prediction and simulation of the formation-keeping motion state of multi-agents under different environmental conditions, and improving the authenticity and application value of the simulation. The following will be described in detail respectively.

[0082] Embodiment 1

[0083] Please refer to Figure 2 , Figure 2 is a schematic flowchart of a method for multi-agent motion modeling based on environment disclosed in an embodiment of the present invention. Among them, Figure 2The described environment-based multi-agent motion modeling method is applied to a multi-agent motion analysis and evaluation system, such as a local server or a cloud server for a multi-agent motion analysis and evaluation system, which is not limited in the embodiments of the present invention. For example, Figure 2 As shown, the environment-based multi-agent motion modeling method may include the following operations:

[0084] S1. Obtain task requirement information;

[0085] It should be noted that the task requirement information represents the parameter information set by the user according to the task requirements;

[0086] The task requirement information includes starting point information, destination point information, travel route information, travel formation information, and task time information;

[0087] It should be noted that in this embodiment, the starting point information is the school campus; the travel route information is Guanting Avenue; the destination point information is a certain military camp; the travel formation information is a longitudinal one-word formation composed of 3 infantry fighting vehicles, and the distance between the infantry fighting vehicles is 50 meters; the task time information is 2 hours;

[0088] S2. Construct a multi-agent dynamic environment management model;

[0089] S3. Based on the multi-agent dynamic environment management model, process the task requirement information to obtain simulation result information.

[0090] It can be seen that by implementing the multi-agent motion modeling method described in the embodiments of the present invention, the route information of each agent is dynamically managed and adjusted using the multi-agent dynamic environment management model, and the motion solution algorithm of the multi-agent is scheduled as needed according to the environment information using the multi-agent adaptive motion solution model, realizing high-precision prediction and simulation of the multi-agent maintaining the formation motion state under different environmental conditions, and improving the authenticity and application value of the simulation.

[0091] In another optional embodiment, in the above step S2, the constructing of the multi-agent dynamic environment management model includes:

[0092] S21. Obtain the motion input interface requirement information of the agent;

[0093] S22. Obtain the position status output interface requirement information of the agent;

[0094] S23. Based on the basic environment dynamic database, obtain the motion route information of the agent;

[0095] S24. Based on the motion input interface requirement information, the position status output interface requirement information, and the agent motion route information, a multi-agent dynamic environment management model is constructed;

[0096] It should be noted that the multi-agent dynamic environment management model includes an input interface module, an initialization module, a motion requirement processing module, a motion position calculation module, a motion position update module, and an output interface module;

[0097] It should be noted that the input interface module is used to provide an agent motion requirement interface and receive agent motion requirement information;

[0098] It should be noted that the initialization module is used to perform initialization processing on the basic environment dynamic database and the agent position status;

[0099] It should be noted that the motion requirement processing module is used to process the agent motion requirement information, and obtain and store the intelligent motion requirement information and the motion route information of the agent;

[0100] It should be noted that the motion position calculation module is used to perform calculation processing on the intelligent motion requirement information to obtain agent position status information;

[0101] It should be noted that the motion position update module is used to update the basic environment dynamic database based on the motion route information of the agent and the agent position status information;

[0102] The output interface module is used to provide an output interface for the agent position status information and output the agent position status information;

[0103] It should be noted that the input interface module, the initialization module, the motion requirement processing module, the motion position calculation module, the motion position, and the output interface module update module are sequentially connected by data.

[0104] It can be seen that implementing the multi-agent dynamic environment management model construction method described in the embodiments of the present invention provides a technical basis for subsequently dynamically managing and adjusting the route information of each agent using the multi-agent dynamic environment management model, and improves the authenticity and application value of simulation.

[0105] In another optional embodiment, in the above step S3, the processing of the task requirement information based on the multi-agent dynamic environment management model to obtain simulation result information includes:

[0106] S31. Perform parsing processing on the task requirement information to obtain motion request information;

[0107] The movement request information includes starting point information, destination point information, travel route information, travel formation information, and mission time information;

[0108] S32. Based on the multi-agent dynamic environment management model, process the movement request information to obtain simulation result information.

[0109] It can be seen that by implementing the multi-agent motion modeling method described in the embodiments of the present invention, the motion solution algorithms of multi-agents are scheduled as needed according to environmental information using the multi-agent adaptive motion solution model, achieving high-precision prediction and simulation of the formation-keeping motion state of multi-agents under different environmental conditions, and improving the authenticity and application value of the simulation.

[0110] In another optional embodiment, in the above step S32, the process of processing the movement request information based on the multi-agent dynamic environment management model to obtain simulation result information includes:

[0111] S321. Use the travel route information to match the basic environment dynamic database to obtain road information and terrain information;

[0112] It should be noted that in this embodiment, the road information is that the total road length is 100 kilometers, the speed limit is 120 kilometers per hour, the height limit is 4 meters, it is a paved road, the road width is 15 meters, there are 4 lanes in both directions, and there are dense forests on both sides of the road;

[0113] It should be noted that in this embodiment, the terrain information is flat terrain;

[0114] S322. Use the road information, the terrain information, and the agent performance information to calculate the movement time information;

[0115] It should be noted that in this embodiment, the agent performance information represents the performance information of a combat vehicle, including a vehicle length of 7.5 meters, a vehicle width of 2.5 meters, a vehicle height of 2.7 meters, and a maximum driving speed of 94 kilometers per hour;

[0116] It should be noted that the calculation means dividing the total road length by the driving speed according to the terrain information to obtain the movement time information;

[0117] It should be noted that in this embodiment, the terrain information is flat terrain, the vehicle speed is not affected, and it only takes 100 / 94 = 1.1 hours to drive at the maximum speed. 1.1 hours < 2 hours, so the task can be completed on time);

[0118] S323. Based on the multi-agent dynamic environment management model, perform a solution process on the movement time information and the agent performance information to obtain the expected position information of the agent and the solution position information of the agent;

[0119] S324. Process the expected position information and the calculated position information of the agent to obtain simulation result information.

[0120] It can be seen that by implementing the multi-agent motion modeling method described in the embodiments of the present invention, the motion calculation algorithms of multiple agents are scheduled as needed according to environmental information using the multi-agent adaptive motion calculation model, achieving high-precision prediction and simulation of the formation-keeping motion state of multiple agents under different environmental conditions, and improving the authenticity and application value of the simulation.

[0121] In another alternative embodiment, in the above step S323, the process of calculating and processing the motion time information and the agent performance information based on the multi-agent dynamic environment management model to obtain the expected position information and the calculated position information of the agent includes:

[0122] S3231. Obtain the formation information of the procession.

[0123] S3232. Analyze the formation information of the procession to obtain the total number of vehicles in the procession convoy.

[0124] S3233. Use the multi-agent dynamic environment management model to obtain the set of information on the vehicles in motion.

[0125] S3234. Based on the multi-agent dynamic environment management model, use the multi-agent adaptive motion calculation model to process the set of information on the vehicles in motion and the total number of vehicles in the procession convoy to obtain the expected position information and the calculated position information of the agent.

[0126] It can be seen that by implementing the multi-agent motion modeling method described in the embodiments of the present invention, the motion calculation algorithms of multiple agents are scheduled as needed according to environmental information using the multi-agent adaptive motion calculation model, achieving high-precision prediction and simulation of the formation-keeping motion state of multiple agents under different environmental conditions, and improving the authenticity and application value of the simulation.

[0127] In another alternative embodiment, in the above step S3234, the process of using the multi-agent adaptive motion calculation model to process the set of information on the vehicles in motion and the total number of vehicles in the procession convoy based on the multi-agent dynamic environment management model to obtain the expected position information and the calculated position information of the agent includes:

[0128] S32341. Obtain the current time information.

[0129] S32342. Use the current time information to calculate and obtain the vehicle travel time information.

[0130] S32343. Calculate and process the vehicle driving time information and the set of driving vehicle information to obtain vehicle position information;

[0131] S32344. Use the vehicle position information to match the basic environment dynamic database to obtain the current road state information;

[0132] S32345. Judge whether the value of the current road state information is equal to the first preset value to obtain the first road state judgment value;

[0133] It should be noted that the first preset value is 1, indicating that the road is a straight line route and the road state is good, and the moving vehicle can drive straight at the economic speed;

[0134] S32346. When the first road state judgment value is yes, process the vehicle driving time information and the set of driving vehicle information based on the first multi-intelligent motion solution operator model to obtain the intelligent agent's expected position information and the intelligent agent's calculated position information;

[0135] When the first road state judgment value is no, execute S32347;

[0136] S32347. Judge whether the value of the current road state information is equal to the second preset value to obtain the second road state judgment value;

[0137] It should be noted that the second preset value is 2, indicating that there is a bend in the forward direction of the moving vehicle, the road state is good and there are no other vehicles, and the moving vehicle maneuvers at a lower speed;

[0138] When the second road state judgment value is yes, process the vehicle driving time information and the set of driving vehicle information based on the second multi-intelligent motion solution operator model to obtain the intelligent agent's expected position information and the intelligent agent's calculated position information;

[0139] When the second road state judgment value is no, execute S32348;

[0140] S32348. Judge whether the value of the current road state information is equal to the third preset value to obtain the third road state judgment value;

[0141] It should be noted that the second preset value is 3, indicating that there are obstacles in the forward direction of the moving vehicle, but the road state is good, and the moving vehicle can still drive straight at the economic speed;

[0142] When the third road state judgment value is yes, based on the first multi-intelligent motion solver model, process the vehicle driving time information and the driving vehicle information set to obtain the agent expected position information and the agent solved position information;

[0143] When the third road state judgment value is no, execute S32349;

[0144] S32349, obtain the current road obstacle information, update the current road obstacle information to the basic environment dynamic database, and execute S321.

[0145] It can be seen that by implementing the multi-agent motion modeling method described in the embodiments of the present invention, the motion solving algorithms of multi-agents are scheduled as needed according to environmental information using the multi-agent adaptive motion solving model, realizing high-precision prediction and simulation of the formation-keeping motion state of multi-agents under different environmental conditions, and improving the authenticity and application value of the simulation.

[0146] In another optional embodiment, the expression of the above first multi-intelligent motion solver model is:

[0147]

[0148] Among them, represents the expected position of the i-th vehicle; represents the solved position of the i-th vehicle; represents the initial position vector of the i-th vehicle, represents the unit vector of the maneuvering direction of the i-th vehicle, V represents the maneuvering speed; T i represents the maneuvering time of the i-th vehicle; i represents the vehicle index in the traveling formation; represents the unit vector of the formation direction; S 间距 represents the formation spacing;

[0149] It should be noted that in this embodiment, S 间距 takes a value of 50 meters;

[0150] The expression of the above second multi-intelligent motion solver model is:

[0151]

[0152] Among them, represents the expected position of the i-th vehicle; represents the solved position of the i-th vehicle; V represents the maneuvering speed; represents the unit vector of the maneuvering direction of the i-th vehicle; ΔT i represents the integration step of the i-th vehicle; a represents the initial value of integration; b represents the end value of integration;

[0153] It should be noted that in this embodiment, the S 间距 takes a value of 50 meters;

[0154] It should be noted that in this embodiment, the value of a is set to 0.1; the value of b is set to 3.0;

[0155] It can be seen that by implementing the multi-agent motion modeling method described in the embodiments of the present invention, the first multi-agent motion solution operator model and the second multi-agent motion solution operator model of multi-agents are scheduled as needed according to environmental information by using the multi-agent adaptive motion solution model, realizing high-precision prediction and simulation of the formation-keeping motion state of multi-agents under different environmental conditions, and improving the authenticity and application value of simulation.

[0156] In another optional embodiment, in the above step S32346, the process of processing the vehicle driving time information and the driving vehicle information set based on the first multi-agent motion solution operator model to obtain the expected position information of the agent and the resolved position information of the agent includes:

[0157] S323461, parsing and processing the driving vehicle information set to obtain the vehicle speed information and driving vehicle information of all driving vehicles;

[0158] S323462, using the first multi-agent motion solution operator model to perform a solution process on any one of the vehicle speed information and the driving vehicle information to obtain the expected position information of the agent and the resolved position information of the agent;

[0159] It should be noted that in this embodiment, the process of using the first multi-agent motion solution operator model to perform a solution process on any one of the vehicle speed information and the driving vehicle information to obtain the expected position information of the agent and the resolved position information of the agent includes:

[0160] Using the first multi-agent motion solution operator model to perform a solution process on the speed information of Infantry Fighting Vehicle 1 and the vehicle information of Infantry Fighting Vehicle 1 to obtain the first resolved position information of Infantry Fighting Vehicle 1, the first expected position information of Infantry Fighting Vehicle 2, the first resolved position information of Infantry Fighting Vehicle 2, the first expected position information of Infantry Fighting Vehicle 3, and the first resolved position information of Infantry Fighting Vehicle 3, including;

[0161] Step 1, determining the straight-line route of Infantry Fighting Vehicle 1, and obtaining the route position point set, formation information, and spacing information of Infantry Fighting Vehicle 1;

[0162] It should be noted that the set of route position points of the infantry fighting vehicle 1 includes an initial position point (1.75338, 0.55845, 0), an intermediate position point (1.75339, 0.55845, 0), and a terminal position point (1.75340, 0.55845, 0);

[0163] It should be noted that in this embodiment, the formation direction unit vector is opposite to the maneuver direction unit vector of the infantry fighting vehicle 1, and is (0.98337, 0.18156, 0);

[0164] It should be noted that in this embodiment, the set of route position points of the infantry fighting vehicle 1, that is, the expected position information of the infantry fighting vehicle 1;

[0165] It should be noted that the spacing information S 间距 takes a value of 50 meters;

[0166] Step 2, determine the speed information of the infantry fighting vehicle 1;

[0167] It should be noted that in this embodiment, since the mission time is relatively loose and the road environment is good, the economic speed of 80 km / h (about 22.22 m / s) is used for straight-line driving, that is, the speed information of the infantry fighting vehicle 1 is 80 km / h;

[0168] Step 3, perform coordinate transformation on the first position point to obtain the initial position vector of the infantry fighting vehicle 1 and the maneuver direction unit vector of the infantry fighting vehicle 1

[0169] Set the maneuver time T of the infantry fighting vehicle 1 1 to 3 seconds;

[0170] Step 4, use the first multi-intelligent motion solution operator model to process the initial position vector of the infantry fighting vehicle 1, the speed information of the infantry fighting vehicle 1, the maneuver direction unit vector of the infantry fighting vehicle 1, and the maneuver time of the infantry fighting vehicle 1 to obtain the solution position information of the first infantry fighting vehicle 1;

[0171] It should be noted that in this embodiment, the calculation process of the solution position information of the first infantry fighting vehicle 1 is as follows:

[0172]

[0173] Step 5, perform transformation on the solution position information of the first infantry fighting vehicle 1 to obtain the first solution position information of the infantry fighting vehicle 1;

[0174] It should be noted that the calculated position information of the infantry fighting vehicle 1 obtained after converting the expected position information (981093.2992, 5313475.96229, 3375925.56564) of the infantry fighting vehicle 1 is (1.75338, 0.55845, 0);

[0175] Step six, use the first multi-intelligent motion solver model to process the initial position vector of the infantry fighting vehicle 1, the formation direction unit vector, and the spacing information to obtain the expected position information of the first infantry fighting vehicle 2;

[0176] It should be noted that in this embodiment, the calculation expression of the expected position information of the first infantry fighting vehicle 2 is:

[0177]

[0178] Step seven, perform coordinate transformation processing on the expected position information of the first infantry fighting vehicle 2 to obtain the first expected position information of the infantry fighting vehicle 2;

[0179] It should be noted that in the embodiment of the present invention, the first expected position information of the infantry fighting vehicle 2 is (1.75337, 0.55845, 0);

[0180] Step eight, determine the maneuvering speed of the infantry fighting vehicle 2;

[0181] It should be noted that since the infantry fighting vehicle 1 maintains a constant speed of 80 km / h, and the infantry fighting vehicle 2 also travels at a constant speed of 80 km / h to maintain the formation, the speed information of the infantry fighting vehicle 2 is 80 km / h (about 22.22 m / s);

[0182] Step nine, obtain the initial position point information of the infantry fighting vehicle 2 according to the formation information;

[0183] It should be noted that in this embodiment, the initial position point information of the infantry fighting vehicle 2 is (-980978.46018, 5313497.34786, 3375925.27811);

[0184] Step ten, determine the initial position vector of the infantry fighting vehicle 2 The maneuvering direction unit vector of the infantry fighting vehicle 2 and the maneuvering time T of the combat vehicle 2 2 ;

[0185] It should be noted that in this embodiment, it is a straight-line motion and the road surface is flat. The maneuvering direction unit vector of the infantry fighting vehicle 2 is the same as that of the infantry fighting vehicle 1, which is (-0.98337, -0.18156, 0), and the maneuvering time period is also set to 3 seconds;

[0186] Step Eleven: Use the first multi-intelligent motion resolver model to process the initial position vector of the infantry fighting vehicle 2, the speed information of the infantry fighting vehicle 2, the unit vector of the maneuvering direction of the infantry fighting vehicle 2, and the maneuvering time of the infantry fighting vehicle 2 to obtain the calculated position information of the first infantry fighting vehicle 2;

[0187] It should be noted that in this embodiment, the calculation process of the calculated position information of the first infantry fighting vehicle 2 is as follows:

[0188]

[0189] Step Twelve: Perform coordinate transformation processing on the calculated position information of the first infantry fighting vehicle 2 to obtain the first calculated position information of the infantry fighting vehicle 2;

[0190] It should be noted that the first calculated position information of the infantry fighting vehicle 2 is (1.75337, 0.55845, 0);

[0191] Step Thirteen: Use the first multi-intelligent motion resolver model to process the initial position vector of the infantry fighting vehicle 3, the unit vector of the formation direction, and the spacing information to obtain the expected position information of the first infantry fighting vehicle 3;

[0192] It should be noted that the calculation process of the expected position information of the first infantry fighting vehicle 3 is as follows:

[0193]

[0194] Use the first multi-intelligent motion resolver model to process the initial position vector of the infantry fighting vehicle 3, the speed information of the infantry fighting vehicle 3, the unit vector of the maneuvering direction of the infantry fighting vehicle 3, and the maneuvering time of the infantry fighting vehicle 3 to obtain the calculated position information of the first infantry fighting vehicle 3;

[0195] It should be noted that the calculation process of the calculated position information of the first infantry fighting vehicle 3 is as follows:

[0196]

[0197] Perform coordinate transformation processing on the expected position information of the first infantry fighting vehicle 3 and the calculated position information of the first infantry fighting vehicle 3 to obtain the first expected position information of the infantry fighting vehicle 3 and the first calculated position information of the infantry fighting vehicle 3;

[0198] It should be noted that both the first expected position information of the infantry fighting vehicle 3 and the first calculated position information of the infantry fighting vehicle 3 are (1.75336, 0.55845, 0).

[0199] It can be seen that by implementing the multi-agent motion modeling method described in the embodiments of the present invention, using the first multi-agent motion solution operator model to process the vehicle driving time information and the driving vehicle information set, the expected position information of the agents and the calculated position information of the agents are obtained, realizing high-precision prediction and simulation of the formation-keeping motion state of multi-agents under different environmental conditions, and improving the authenticity and application value of the simulation.

[0200] In another optional embodiment, in the above step S32347, the process of using the second multi-agent motion solution operator model to process the vehicle driving time information and the driving vehicle information set to obtain the expected position information of the agents and the calculated position information of the agents includes:

[0201] S323471, using the travel route information to match the basic environment dynamic database to obtain the bend turning angle information;

[0202] S323472, performing parsing processing on the driving vehicle information set to obtain the vehicle speed information and driving vehicle information of all driving vehicles;

[0203] S323473, for any one of the vehicle speed information and the driving vehicle information, using the second multi-agent motion solution operator model to perform calculation processing on the bend turning angle information, the driving vehicle speed information and the driving vehicle information to obtain the expected position information of the agents and the calculated position information of the agents;

[0204] It should be noted that in this embodiment, the process of using the second multi-agent motion solution operator model to perform calculation processing on any one of the vehicle speed information and the driving vehicle information, the bend turning angle information, the driving vehicle speed information and the driving vehicle information to obtain the expected position information of the agents and the calculated position information of the agents includes:

[0205] Using the first multi-agent motion solution operator model to perform calculation processing on the speed information of Infantry Fighting Vehicle 1 and the vehicle information of Infantry Fighting Vehicle 1 to obtain the second calculated position information of Infantry Fighting Vehicle 1, the second expected position information of Infantry Fighting Vehicle 2, the second calculated position information of Infantry Fighting Vehicle 2, the second expected position information of Infantry Fighting Vehicle 3 and the second calculated position information of Infantry Fighting Vehicle 3, including;

[0206] A01, determining the maneuvering speed of Infantry Fighting Vehicle 1 to obtain the speed information of Infantry Fighting Vehicle 1;

[0207] It should be noted that in this embodiment, since there is a bend on the front road, according to the cornering strategy, it is necessary to reduce the speed to pass, and a speed of 40 km / h (about 11.11 m / s) is used for maneuvering, that is, the speed information of Infantry Fighting Vehicle 1 is 40 km / h (about 11.11 m / s);

[0208] A02. Based on the cornering route determination model, calculate the cornering route to obtain the cornering route position point set;

[0209] The expression of the cornering route determination model is:

[0210]

[0211] Where, R represents the cornering radius; g represents the acceleration due to gravity; θ represents the turning angle of the curve; L represents the cornering distance; V represents the maneuvering speed;

[0212] It should be noted that in this embodiment, the value of g is 9.8 m / s^2; θ is 0.5236 (i.e., 30°);

[0213] Substitute the speed information of the infantry fighting vehicle 1, the value of g, and the value of θ into the cornering route determination model to obtain the cornering radius and the cornering distance:

[0214]

[0215] According to the cornering radius and the cornering distance, fit the curve to obtain the cornering route position point set as (1.75354, 0.55846, 0), (1.753539, 0.558459, 0), (1.753538, 0.558458, 0);

[0216] A03. Determine the initial position vector information of the infantry fighting vehicle 1, the speed information of the infantry fighting vehicle 1, the unit vector of the maneuvering direction of the infantry fighting vehicle 1, the integration step length of the infantry fighting vehicle 1, the integration initial value, and the integration end value;

[0217] It should be noted that in this embodiment, the initial position vector information of the infantry fighting vehicle 1 is (-981861.6583, 5313334.07456, 3375925.54978);

[0218] The integration step length ΔT of the infantry fighting vehicle 1 1 is 0.1 second;

[0219] A04. Use the second multi-intelligent motion solution operator model to process the initial position vector information of the combat vehicle 1, the speed information of the infantry fighting vehicle 1, the unit vector of the maneuvering direction of the infantry fighting vehicle 1, the integration step length of the infantry fighting vehicle 1, the integration initial value, and the integration end value to obtain the solution position information of the second infantry fighting vehicle 1;

[0220] It should be noted that the calculation process of the solution position information of the second infantry fighting vehicle 3 is as follows:

[0221]

[0222] A05. Perform coordinate transformation on the calculated position information of the first infantry fighting vehicle 1 to obtain the second calculated position information of the infantry fighting vehicle 1;

[0223] It should be noted that in the embodiment of the present invention, the second calculated position information of the infantry fighting vehicle 1 is (1.75353, 0.55845, 0);

[0224] A06. Use the second multi-intelligent motion solver model to process the initial position vector of the infantry fighting vehicle 1, the formation direction unit vector, and the spacing information to obtain the expected position information of the second infantry fighting vehicle 2;

[0225] It should be noted that the initial position vector of the infantry fighting vehicle 1 is (-981894.0049, 5313328.01956, 3375925.54978), s 间距 is 50 meters, and the turning radius R of the curve is 21.83 meters. The turning angle of the curve can be calculated Combined with the maneuvering direction unit vector of the infantry fighting vehicle 1 and the road information for orientation correction to ensure that the expected position of the infantry fighting vehicle 2 is within the curve, and obtain as (0.983359, 0.18167, 0);

[0226] It should be noted that in this embodiment, the calculation expression of the expected position information of the second infantry fighting vehicle 2 is:

[0227]

[0228] A07. Perform coordinate transformation on the expected position information of the second infantry fighting vehicle 2 to obtain the second expected position information of the infantry fighting vehicle 2;

[0229] It should be noted that in the embodiment of the present invention, the second expected position information of the infantry fighting vehicle 2 is (1.753521, 0.558452, 0);

[0230] A08. Determine the maneuvering speed of the infantry fighting vehicle 2, the initial position vector of the infantry fighting vehicle 2 the maneuvering direction unit vector of the infantry fighting vehicle 2 and the maneuvering time T of the fighting vehicle 2 2 ;

[0231] It should be noted that since the infantry fighting vehicle 1 decelerates to a speed of 40 km / h for safe cornering and travels at a constant speed, the infantry fighting vehicle 2 also adopts a speed reduction strategy for safe cornering and uses a speed of 40 km / h for cornering;

[0232] It should be noted that in this embodiment, the current position of the infantry fighting vehicle 2 in the Earth-Centered Earth-Fixed coordinate system ECEF is (-981812.37274, 5313343.36471, 3375925.26206). The unit vector of the maneuvering direction of the infantry fighting vehicle 2 within the current integration step length is corrected for the bend to (-0.983359, -0.18167, 0), and the integration step length is 0.1 second;

[0233] A09. Using the second multi-intelligent motion solution operator model, process the initial position vector of the infantry fighting vehicle 2, the speed information of the infantry fighting vehicle 2, the unit vector of the maneuvering direction of the infantry fighting vehicle 2, and the integration step length of the infantry fighting vehicle 2 to obtain the calculated position information of the second infantry fighting vehicle 2;

[0234] It should be noted that the calculation process of the calculated position information of the second combat vehicle 2 is as follows:

[0235]

[0236] A10. Perform coordinate transformation processing on the calculated position information of the second infantry fighting vehicle 2 to obtain the second calculated position information of the infantry fighting vehicle 2;

[0237] It should be noted that the second calculated position information of the infantry fighting vehicle 2 is (1.75352, 0.55845, 0);

[0238] A11. Using the second multi-intelligent motion solution operator model, process the initial position vector of the infantry fighting vehicle 2, the unit vector of the formation direction, and the spacing information to obtain the expected position information of the second infantry fighting vehicle 3;

[0239] It should be noted that the initial position vector of the infantry fighting vehicle 2 is (-981845.14813, 5313337.30965, 3375925.26206), s 间距 is 50 meters, the turning radius R of the bend is 21.83 meters, and the turning angle of the bend can be calculated Combined with the unit vector of the maneuvering direction of the infantry fighting vehicle 2 and the road information for orientation correction to ensure that the expected position of the infantry fighting vehicle 3 is within the bend, and it is obtained that is (0.983359, 0.18167, 0);

[0240] It should be noted that the calculation process of the expected position information of the second infantry fighting vehicle 3 is as follows:

[0241]

[0242] Using the second multi-intelligent motion solver model, process the initial position vector of the infantry fighting vehicle 3, the speed information of the infantry fighting vehicle 3, the unit vector of the maneuvering direction of the infantry fighting vehicle 3, and the integration step length of the infantry fighting vehicle 3 to obtain the calculated position information of the second infantry fighting vehicle 3 for processing;

[0243] It should be noted that the initial position vector of the infantry fighting vehicle 3 is (-981764.14669, 5313352.43653, 3375925.00911), the unit vector of the maneuvering direction of the infantry fighting vehicle 3 after curve correction is (-0.983359, -0.18167, 0), the integration step length of the infantry fighting vehicle 3 is 0.1 second, and the speed information of the infantry fighting vehicle 3 is the same as the speed information of the infantry fighting vehicle 1;

[0244] It should be noted that the calculation process of the calculated position information of the second infantry fighting vehicle 3 is as follows:

[0245]

[0246] A12. Perform conversion processing on the expected position information of the second infantry fighting vehicle 3 and the calculated position information of the second infantry fighting vehicle 3 to obtain the second expected position information of the infantry fighting vehicle 3 and the second calculated position information of the infantry fighting vehicle 3;

[0247] It should be noted that the second expected position information of the infantry fighting vehicle 3 is (1.753513, 0.558451, 0), and the second calculated position information of the infantry fighting vehicle 3 is (1.75351, 0.55845, 0).

[0248] It can be seen that by implementing the multi-agent motion modeling method described in the embodiments of the present invention and using the second multi-intelligent motion solver model to process the vehicle driving time information and the driving vehicle information set, the expected position information of the agent and the calculated position information of the agent are obtained, realizing high-precision prediction and simulation of the formation-keeping motion state of multi-agents under different environmental conditions, and improving the authenticity and application value of the simulation.

[0249] In another optional embodiment, in the above step S324, the processing of the expected position information of the agent and the calculated position information of the agent to obtain the simulation result information includes:

[0250] S3241. Obtain real-time environmental data information;

[0251] S3242. Calculate the difference value between the real-time environmental data information and the calculated position information of the agent to obtain the first position difference information;

[0252] It should be noted that the difference value calculation means performing a subtraction calculation;

[0253] S3243, determine whether the first position difference information is less than a preset first difference value threshold to obtain a first position difference judgment result;

[0254] It should be noted that the first difference value threshold represents the vehicle vertical position threshold, which limits the vehicle to be above the ground plane;

[0255] It should be noted that in this embodiment, the first difference value threshold is set to 0;

[0256] S3244, when the first position difference judgment result is negative, update the intelligent agent's calculated position information to the real-time environment data information, and execute S3245;

[0257] When the first position difference judgment result is positive, execute S3245;

[0258] S3245, calculate the difference value between the intelligent agent's expected position information and the intelligent agent's calculated position information to obtain second position difference information;

[0259] S3246, determine whether the second position difference information is less than a second difference value threshold to obtain a second position difference judgment result;

[0260] It should be noted that the second difference value threshold represents the vehicle horizontal position threshold;

[0261] It should be noted that in this embodiment, the second difference value threshold is set to the width of Guanting Avenue, that is, 15 meters;

[0262] S3247, when the second position difference judgment result is positive, obtain simulation result information;

[0263] When the second position difference judgment result is negative, update the intelligent agent's expected position information to the intelligent agent's calculated position information to obtain simulation result information;

[0264] It should be noted that the simulation result information represents the intelligent agent's calculated position information displayed in the simulation interface.

[0265] It can be seen that by implementing the multi-intelligent agent motion modeling method described in the embodiments of the present invention, the intelligent agent's calculated position information is feedback-adjusted using the basic environment dynamic database, realizing high-precision prediction and simulation of the multi-intelligent agent's formation-keeping motion state under different environmental conditions, and improving the authenticity and application value of the simulation.

[0266] Embodiment 2

[0267] Please refer to Figure 3 , Figure 3It is a schematic structural diagram of a multi-agent motion modeling device based on the environment disclosed in an embodiment of the present invention. Among them, Figure 3 The described device can be applied to a multi-agent motion analysis and evaluation system, such as a local server or a cloud server for a multi-agent motion analysis and evaluation system, etc., which is not limited in the embodiments of the present invention. Such as Figure 3 As shown, the system may include:

[0268] A data acquisition module 101, a management model construction module 102, and a simulation processing module 103;

[0269] The data acquisition module 101 is used to acquire task requirement information;

[0270] The management model construction module 102 is used to construct a multi-agent dynamic environment management model;

[0271] The simulation processing module 103 is used to process the task requirement information based on the multi-agent dynamic environment management model to obtain simulation result information.

[0272] Embodiment III

[0273] Please refer to Figure 4 , Figure 4 It is a schematic structural diagram of a multi-agent motion modeling device based on the environment disclosed in an embodiment of the present invention. Among them, Figure 4 The described device can be applied to a multi-agent motion analysis and evaluation system, such as a local server or a cloud server for a multi-agent motion analysis and evaluation system, etc., which is not limited in the embodiments of the present invention. Such as Figure 4 As shown, the device may include:

[0274] A memory 202 storing executable program code;

[0275] A processor 201 coupled to the memory 202;

[0276] The processor 201 calls the executable program code stored in the memory 202 to execute the steps in the method for multi-agent motion modeling based on the environment described in Embodiment I.

[0277] Embodiment IV

[0278] An embodiment of the present invention discloses a computer-readable storage medium, which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps in the method for multi-agent motion modeling based on the environment described in Embodiment I.

[0279] Embodiment V

[0280] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the environment-based multi-agent motion modeling method described in Embodiment 1.

[0281] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative effort.

[0282] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc memories, a magnetic disk memory, a tape memory, or any other computer-readable medium capable of carrying or storing data.

[0283] Finally, it should be noted that: The multi-agent motion modeling method and device based on the environment disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than limiting them; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-agent motion modeling method based on environment, characterized in that: The method comprises: S1, obtain task requirement information; S2, building a multi-agent dynamic environment management model; S3, based on the multi-agent dynamic environment management model, processing the task requirement information to obtain simulation result information.

2. The environment-based multi-agent motion modeling method according to claim 1, characterized in that: The construction of a multi-agent dynamic environment management model includes: S21, obtaining motion input interface requirement information of the intelligent agent; S22, obtaining the position status output interface requirement information of the agent; S23, acquiring movement route information of the intelligent agent based on the basic environment dynamic database; S24, constructing a multi-agent dynamic environment management model based on the motion input interface requirement information, the position state output interface requirement information and the agent motion route information.

3. The environment-based multi-agent motion modeling method according to claim 1, characterized in that: The step of processing the task requirement information based on the multi-agent dynamic environment management model to obtain simulation result information includes: S31, analyzing and processing the task requirement information to obtain motion request information; The movement request information includes departure point information, destination point information, travel route information, travel formation information and task time information; S32, based on the multi-agent dynamic environment management model, processing the motion request information to obtain simulation result information.

4. The environment-based multi-agent motion modeling method according to claim 3 is characterized in that: The step of processing the motion request information based on the multi-agent dynamic environment management model to obtain simulation result information includes: S321, using the travel route information to match the basic environment dynamic database to obtain road information and terrain information; S322, calculating movement time information using the road information, the terrain information and the agent performance information; S323, based on the multi-agent dynamic environment management model, the motion time information and the agent performance information are solved and processed to obtain the agent solved position information; S324, processing the calculated position information of the intelligent agent to obtain simulation result information.

5. The environment-based multi-agent motion modeling method according to claim 4, characterized in that: The method of solving the motion time information and the agent performance information based on the multi-agent dynamic environment management model to obtain the agent solved position information includes: S3231, obtaining the marching formation information; S3232, parsing the traveling formation information to obtain a total value of vehicles in the traveling formation; S3233, using the multi-agent dynamic environment management model to obtain a moving vehicle information set; S3234, based on the multi-agent dynamic environment management model, using the multi-agent adaptive motion solution model, the moving vehicle information set and the total value of the moving fleet vehicles are processed to obtain the agent expected position information and the agent solved position information.

6. The environment-based multi-agent motion modeling method according to claim 5, characterized in that: The method of processing the moving vehicle information set and the total value of the moving vehicle fleet by using the multi-agent adaptive motion solution model based on the multi-agent dynamic environment management model to obtain the agent expected position information and the agent solution position information includes: S32341, obtain current time information; S32342, using the current time information, calculating and obtaining the vehicle travel time information; S32343, calculating and processing the vehicle travel time information and the travel vehicle information set to obtain vehicle position information; S32344, using the vehicle position information to match the basic environment dynamic database to obtain current road status information; S32345, determining whether the current road state information value is equal to a first preset value, and obtaining a first road state determination value; S32346, when the first road state judgment value is yes, based on the first multi-intelligent motion solver model, the vehicle driving time information and the driving vehicle information set are processed to obtain the agent expected position information and the agent solved position information; When the first road state judgment value is no, executing S32347; S32347, determining whether the current road state information value is equal to a second preset value, and obtaining a second road state determination value; When the second road state judgment value is yes, based on the second multi-intelligent motion solver model, the vehicle travel time information and the travel vehicle information set are processed to obtain the agent expected position information and the agent solved position information; When the second road state judgment value is no, executing S32348; S32348, determining whether the current road state information value is equal to a third preset value, and obtaining a third road state determination value; When the third road state judgment value is yes, based on the first multi-agent motion solver model, the vehicle travel time information and the travel vehicle information set are processed to obtain the agent expected position information and the agent solved position information; When the third road state judgment value is no, executing S32349; S32349, obtain current road obstacle information, and update the current road obstacle information to the basic environment dynamic database, and execute S321.

7. The environment-based multi-agent motion modeling method according to claim 6, characterized in that: The first multi-intelligent motion solver model expression is: in, represents the expected position of the i-th vehicle; represents the solved position of the i-th vehicle; represents the initial position vector of the i-th vehicle, represents the unit vector of the maneuvering direction of the i-th vehicle, V represents the maneuvering speed; T i represents the maneuvering time of the i-th vehicle; i represents the vehicle index in the said marching formation; Represents the unit vector of the formation direction; S 间距 Indicates the spacing between formations; The second multi-intelligent motion solver model expression is: in, represents the expected position of the i-th vehicle; represents the calculated position of the i-th vehicle; V represents the maneuvering speed; represents the maneuvering direction unit vector of the i-th vehicle; ΔT i represents the integration step of the i-th vehicle; a represents the initial value of the integration; b represents the end value of the integration.

8. An environment-based multi-agent motion modeling device, characterized in that: The device comprises: a data acquisition module, a management model building module and a simulation processing module; The data acquisition module is used to acquire task requirement information; The management model building module is used to build a multi-agent dynamic environment management model; The simulation processing module is used to process the task requirement information based on the multi-agent dynamic environment management model to obtain simulation result information.

9. An environment-based multi-agent motion modeling device, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the environment-based multi-agent motion modeling method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which, when called, are used to execute the environment-based multi-agent motion modeling method as described in any one of claims 1-7.

Images