Intelligent agent scheduling method and device of charging system, storage medium and program product

Abstract

The invention relates to an agent scheduling method and device of a charging system, a storage medium and a program product. The scheduling method comprises the following steps: a charging system network topology construction step: constructing a network topology; a centralized task allocation step: in response to the plurality of charging requests, modeling a task allocation problem into a cooperative game optimization model for the heterogeneous multi-agent system; a distributed path planning step: taking the distributed charging request as a target, and establishing a competition-cooperation game model based on a local communication fully connected graph constructed by utilizing dynamic topology; and a planning strategy design step: based on the game theory, solving the game models in the centralized task allocation step and the distributed path planning step by utilizing model predictive control until a Nash equilibrium solution sequence which enables a target function in a corresponding model predictive control optimization model to be minimum is converged, and outputting a planning control sequence in the prediction view as a control vector.

Description

Technical Field

[0001] The invention relates to an intelligent body scheduling method and scheduling device, a storage medium and a program product of a charging system. Background Art

[0002] In recent years, electric vehicles, as an environmentally friendly and sustainable means of transportation, have attracted widespread attention and achieved significant development around the world. Electric vehicles are mainly divided into pure electric vehicles, plug-in hybrid vehicles and hybrid vehicles. The key lies in the advancement of battery technology. With the development of lithium-ion battery technology, the range of electric vehicles has gradually increased, the charging time has gradually shortened, and the cost has gradually decreased. In addition, the efficiency of electric vehicles' motors and control systems are also constantly being optimized, thereby improving the overall performance and driving experience.

[0003] In the past few years, the electric vehicle market has shown a rapid growth trend, mainly due to the support of government policies, especially the policy promotion of environmental protection and carbon emission reduction. Many countries have formulated subsidy policies and regulations to promote the popularity of electric vehicles. Especially in regions such as Europe and China, the sales of electric vehicles have increased significantly and their market share has continued to expand. Automakers have also launched new electric models, and market competition has become increasingly fierce. For example, as a pioneer in the field of electric vehicles, Tesla has continuously launched new models with high performance and long driving range, leading the direction of market development.

[0004] However, as an important energy source for electric vehicles, the popularization and improvement of charging infrastructure is very necessary. To this end, it is particularly important to build an autonomous charging system that can efficiently respond to charging requests and effectively dispatch charging robots and mobile charging piles. Faced with the growing charging demand of users, multiple charging requests often appear in a parking lot in a short period of time, and a single charging robot and mobile charging pile are difficult to meet the demand. Therefore, deploying multiple mobile charging devices can improve the overall charging demand response efficiency. In order to ensure the efficient operation of the multi-charging robot system and avoid conflicts, it is necessary to design an efficient and harmonious intelligent scheduling strategy.

[0005] Traditional strategies for scheduling heterogeneous multi-agents are mostly designed based on corresponding rules according to actual application problems, mainly including priority rule scheduling strategy (Fellir, Fadoua, et al. "A multi-Agent based model for task scheduling in cloud-fog computing platform." 2020 IEEEinternational conference on informatics, IoT, and enabling technologies(ICIoT). IEEE, 2020.) and multi-agent path finding strategy (Atzmon, Dor, et al. "Generalizing multi-agent path finding for heterogeneous agents." Proceedingsof the International Symposium on Combinatorial Search. Vol. 11. No. 1.2020.). The above rule-based strategies mainly rely on fixed and static environmental states, and for nonlinear optimization problems, they often have the disadvantages of high computational and communication overheads.

[0006] With the development of optimization technology, advanced heuristic optimization algorithms have also been used in the field of heterogeneous multi-agent scheduling. Zhou et al. combined the distributed multi-objective evolutionary algorithm and the greedy algorithm (Zhou, Jing, et al. "Taskallocation for multi-agent systems based on distributed many-objectiveevolutionary algorithm and greedy algorithm." Ieee Access 8 (2020): 19306-19318.) to solve the optimal strategy for task allocation. However, the greedy algorithm lacks a global perspective when optimizing and cannot handle the impact of dynamic changes in the environment. Secondly, based on the leader-follower formula problem, Wang et al. used particle swarm optimization as an effective evolutionary technology for distributed gain optimization in multi-agent networks (Wang, Xin, Dongsheng Yang, and Shuang Chen. "Particle swarm optimizationbased leader-follower cooperative control in multi-agent systems." AppliedSoft Computing 151 (2024): 111130.), and based on algebraic graph theory, it ensures the stability of closed-loop dynamics under directed communication topology. Particle swarm is a heuristic algorithm with strong global search capability, but it is still easy to fall into local optimality when facing high-dimensional and complex heterogeneous multi-agent scheduling problems, and it will lead to high computational costs.

[0007] Faced with the high-dimensional and complex relationships and dynamically changing environments of heterogeneous multi-agent systems, the adaptive ability and reward mechanism of reinforcement learning can handle them better. Zhang et al. proposed an improved Q-value mixing matrix, combined with Qatten's multi-head attention mechanism, which can adapt to heterogeneous robots running asynchronously in different scenarios (Zhang, Han, et al. "Heterogeneous Multi-Robot Cooperation with Asynchronous Multi-Agent Reinforcement Learning." IEEE Robotics and Automation Letters (2023)). However, reinforcement learning requires a large amount of training data and time to converge, and although specific reward mechanisms can be designed to deal with the heterogeneity of heterogeneous agents, it may still be difficult to achieve effective coordination and optimization. Summary of the invention

[0008] Technical issues to be solved In order to overcome the above-mentioned problems in the prior art, the present invention aims to provide a scheduling method and device that can quickly and accurately schedule a multi-agent system to respond and resolve decision conflicts when faced with multiple charging requests in a smart parking lot and a heterogeneous multi-agent control system of a charging robot and a mobile charging pile.

[0009] Technical Solution According to a first aspect of the present invention, an agent scheduling method for a charging system is provided, wherein the charging system has a plurality of agents, wherein the agents include a charging robot and a mobile charging pile, and the scheduling method includes: a charging system network topology construction step (S100), wherein a network topology is constructed for a parking lot physical system and a charging robot-mobile charging pile heterogeneous multi-agent system, wherein the network topology includes a static topology constructed based on parking lots, robot rails, and charging cars, and a dynamic topology constructed based on charging robots, mobile charging piles, and communication links therebetween; a centralized task allocation step (S200), wherein, in response to a plurality of charging requests, For heterogeneous multi-agent systems, the task allocation problem is modeled as a cooperative game optimization model to perform centralized task allocation; in the distributed path planning step (S300), a competition-cooperation game model is established based on a local communication fully connected graph constructed using dynamic topology with the allocated charging request as the target, so as to perform distributed real-time path planning control; in the planning strategy design step (S400), based on game theory and using model predictive control, the game models in the centralized task allocation step and the distributed path planning step are solved until they converge to a Nash equilibrium solution sequence that meets the conditions, and the planning control sequence within the prediction field of view is output as a control vector.

[0010] As a preferred solution, according to the intelligent agent scheduling method for the charging system of the present invention, in the centralized task allocation step, the task allocation problem is modeled as the following cooperative game optimization model: , in, N r and N c Respectively represent the number of charging robots and mobile charging piles in the system, N task Indicates the number of charging requests in the system at the current moment. Representing an Agent Assigned to perform tasks The first row of constraints represents that each charging request needs to be responded to by at most one and only one heterogeneous intelligent agent formation of charging robots and mobile charging piles, and the second row of constraints represents that each intelligent agent currently has only one charging task assignment. h(X) and g(X) represent equality or inequality constraints on power storage, vehicle requirements, and robot arm structure, respectively. u allocation represents the decision utility function.

[0011] As a preferred solution, according to the intelligent agent scheduling method for the charging system of the present invention, in the planning strategy design step, the cooperative game optimization model established in the centralized task allocation step is modified as follows to stabilize the allocated tasks: , in, N r and N c Respectively represent the number of charging robots and mobile charging piles in the system, N task Indicates the number of charging requests in the system at the current moment, Representing an Agent Assigned to perform tasks The first row of constraints means that each charging request needs to be responded to by at most one and only one heterogeneous intelligent agent formation of charging robots and mobile charging piles, respectively. The second row of constraints means that each intelligent agent currently has only one charging task assignment. h(X) and g(X) represent equality or inequality constraints on power storage, vehicle requirements, and robot arm structure. u Represents the decision utility function at the next moment.

[0012] As a preferred solution, according to the intelligent agent scheduling method of the charging system of the present invention, the Nash equilibrium solution of the cooperation-competition game model in the distributed path planning step is calculated to obtain the expression of the optimization problem as follows: , in, represents the strategy of agent i and other agents' strategies The decision utility function is composed of represents the correlation between agent i and agent j, and represents the equality and inequality constraints related only to the agent itself contained in the planning strategy design step, represents the joint constraints of the generalized Nash equilibrium that depend on the decisions of other subjects, including the collision constraints between the two agents, the task allocation constraints, etc., and includes the constraints related to the decisions of other agents in the optimization problem set up for agent i in the planning strategy design step, Furthermore, the optimization is iterated until it converges to a Nash equilibrium solution that satisfies the KKT condition.

[0013] As a preferred solution, according to the intelligent agent scheduling method of the charging system of the present invention, the charging system network topology construction step includes: Static topology building step (S110): building a static parking lot physical topology map based on relevant physical information of the parking lot. Among them, in the parking lot physical static topology, the vertex contains the following attributes: , in Represents the value of the parking space vertex in the static topology, Indicates whether there is any uncompleted charging request in the current parking space. Indicates the waiting time after the electric car owner in the current parking space places an order for charging. Represents the current time, represents the initial time when the charging request appears. On this basis, the edge value of the static topology is represented by the length of the rail between two vertices; The dynamic topology establishment step (S120) is used to represent the positional relationship and communication connectivity of the heterogeneous multi-agents of the charging robot and the mobile charging pile. The information contained in the vertices of the heterogeneous multi-agents includes the following attributes: , in, Indicates the current physical position of the agent in the parking lot coordinate system. Indicates the charging task to which the current agent is assigned; represents the energy consumption coefficient of the agent, represents the remaining power of the current agent; and Represents special properties related to the vertex type, Indicates the current route of the robot. Among them, the edge The communication strength is: , in, represents the actual distance between the two agents, Indicates the distance threshold for communication. When the distance is greater than the threshold, the communication link between the two is disconnected. "!" and "&" are logical operators, where "!" represents a negation operation and "&" represents an AND operation.

[0014] As a preferred solution, according to the intelligent agent scheduling method of the charging system of the present invention, the centralized task allocation construction step includes: The task set definition step (S210) defines the following task set: , The tasks It has the following properties: , in, Indicates the power requirement for the current charging task. Indicates the location of the charging port of the current mission vehicle. After the mission occurs, the camera directly above the parking space will identify the vehicle information to obtain Specific information; Indicates the priority of the current task. The higher the priority, the The smaller; Indicates the position of the vehicle in the parking space and the number of the vertex where the parking space is located in the static topology; Task allocation matrix definition step (S220): define the following task allocation matrix: ,in Representing an Agent Assigned to perform tasks The decision results: ; Utility function design step (S230), for each agent The utility function is designed, and the agent Execute the task The latter utility is defined as: , The joint utility function is defined as: , The decision utility function is: ; Constraint design step (S240): Design constraints for the charging robot, and use the inverse kinematics equation to solve the end effector target posture calculated based on the vehicle posture and the charging port position: , in, represents the inverse kinematics of the carried robotic arm, It means that the position equation of the end effector is calculated according to the current posture of the vehicle and the prior charging port position information to obtain the optimization model of the centralized cooperative game model of task allocation.

[0015] As a preferred solution, according to the intelligent agent scheduling method of the charging system of the present invention, the distributed path planning step includes: Participants and strategy definition step (S310), participants include A charging robot and Mobile charging piles, the strategy space includes: , in, a i It is a vector, and has two directions: positive and negative x and positive and negative y; The utility function design step (S320) designs the utility function, which includes: , in, They represent the competitive utility function and the cooperative utility function respectively.

[0016] As a preferred solution, according to the intelligent agent scheduling method of the charging system of the present invention, the utility function includes a cooperative utility function, and the cooperative utility function is designed to The group of agents connected by the communication link constructed nearby punishes the situation where the distance between two agents is close or they are moving in opposite directions. The cooperative utility function is as follows: , in, Representatives and An agent with a communication link.

[0017] As a preferred solution, according to the agent scheduling method of the charging system of the present invention, the utility function includes a competitive utility function, which is designed to stimulate each agent to complete the assigned task as quickly as possible and reduce the time difference between heterogeneous agents of the same task and the arrival at the task location. The competitive utility function is as follows: ,and The final system competition utility function is as follows: .

[0018] According to a second aspect of the present invention, there is provided an intelligent agent scheduling device for a charging system, wherein the charging system has a plurality of intelligent agents, wherein the intelligent agents include a charging robot and a mobile charging pile, and the scheduling device includes: a charging system network topology construction unit, which constructs a network topology for a parking lot physical system and a charging robot-mobile charging pile heterogeneous multi-agent system, wherein the network topology includes a static topology constructed based on parking lots, robot rails, and charging cars, and a dynamic topology constructed based on charging robots, mobile charging piles, and communication links therebetween; a centralized task allocation unit, which responds to a plurality of charging requests, For heterogeneous multi-agent systems, the task allocation problem is modeled as a cooperative game optimization model to perform centralized task allocation; the distributed path planning unit, with the assigned charging request as the goal, establishes a competition-cooperation game model based on the local communication fully connected graph constructed using dynamic topology to perform distributed real-time path planning control; and the strategy design unit, based on game theory, uses model predictive control to solve the game model established by the centralized task allocation unit and the distributed path planning unit until it converges to a Nash equilibrium solution sequence that meets the conditions, and outputs the planning control sequence within the prediction field of view as the control vector.

[0019] According to a third aspect of the present invention, there is provided a non-transitory storage medium storing a computer program, which, when executed by a processor, can implement the agent scheduling method for a charging system according to the first aspect of the present invention.

[0020] According to a fourth aspect of the present invention, there is provided a computer program product, the computer program product comprising computer instructions, which when executed by a processor can implement the intelligent agent scheduling method for a charging system according to the first aspect of the present invention.

[0021] Beneficial technical effects The scheduling method of the charging system of the present invention can achieve better capture of the relationship between multiple intelligent agents based on the construction of a double-layer topology of static topology and dynamic topology by using cooperative game models and cooperative-competitive game models, and solve the Nash equilibrium for the optimal planning control decision in a way of optimizing and predicting the model predictive control.

[0022] Further features of the present invention will become apparent from the following description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart showing an agent scheduling method for a charging system; Figure 2 is a flow chart showing the steps of building a charging system network topology; Figure 3is a flow chart showing the steps of centralized task allocation; Figure 4 is a flow chart showing the steps of distributed path planning; Figure 5 is a schematic diagram schematically illustrating the establishment of a static topology; Figure 6 is a schematic diagram schematically illustrating dynamic topology establishment; Figure 7 is a schematic diagram showing task allocation and local trajectory planning control. DETAILED DESCRIPTION

[0024] Exemplary embodiments of the present invention are described in detail below with reference to the accompanying drawings. It should be noted that the relative arrangement of components, numerical expressions and numerical values ​​described in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0025] The scheduling method of the automatic charging system of the present invention can be implemented by a processor in the automatic charging system executing a computer program stored in a memory in the automatic charging system. As an alternative, the automatic charging system can also communicate with a server, and the processor in the server executes the computer program stored in the server and feeds back the program execution results to the automatic charging system in real time.

[0026] In the present invention, the term "unit" may refer to a software environment, a hardware environment, or a combination of software and hardware environments. In a software environment, the term "unit" refers to functionality, an application, a software module, a function, a routine, a set of instructions or a program that can be executed by a programmable processor (such as a microprocessor, a central processing unit (CPU) or a specially designed programmable device) or a controller. The memory contains instructions or programs, and when the CPU executes the instructions or programs, the CPU performs operations corresponding to the unit or function. In a hardware environment, the term "unit" refers to a hardware element, circuit, component, physical structure, system, module or subsystem. According to a specific embodiment, the term "unit" may include mechanical, optical or electrical components, or any combination thereof. The term "unit" may include active (such as transistors) or passive (such as capacitors) components. The term "unit" may include a semiconductor device having a substrate and other material layers with various conductive concentrations. It may include a CPU or a programmable processor that can execute a program stored in a memory to perform a specified function. The term "unit" may include a logic element (such as AND, OR) implemented by a transistor circuit or any other switching circuit. In the combination of software and hardware environment, the term "unit" or "circuit" refers to any combination of software and hardware environment as described above. In addition, the term "element", "component", "part" or "device" may also refer to a "circuit" integrated or not integrated with packaging materials.

[0027] Figure 1 is a flowchart for illustrating an agent scheduling method of a charging system according to an embodiment.

[0028] The following will refer to Figure 1 A flow chart illustrating an agent scheduling method for a charging system according to an embodiment.

[0029] First, in step S100, the charging system network topology is constructed. Specifically, the network topology is constructed for the parking lot physical system and the charging robot-mobile charging pile heterogeneous multi-agent system, and the network topology includes a static topology based on parking spaces, robot rails and charging cars, and a dynamic topology based on charging robots, mobile charging piles and the communication links between them.

[0030] The following will refer to Figure 2 The flowchart shown is used to illustrate the process of the charging system network topology construction step S100.

[0031] In step S110 , a static topology is established. Figure 5 The schematic diagram of static topology construction is shown schematically. Figure 5 In the figure, the solid circle indicates the parking space occupancy. Based on the relevant physical information of the parking lot, a static parking lot physical topology map is constructed, including the existing The vertex set consisting of parking spaces ; The guide rails of the suspended charging robot and mobile charging pile are used as the edge , a continuous rail edge is segmented using the parking space vertices, Indicates the vertex of the parking space and The guide rail part between them can be passed in both directions. All superscript s represent the relevant structure or value parameters in the static network topology. The physical static topology of the parking lot can be expressed as .

[0032] In the physical static topology of the parking lot, the vertices mainly contain the following attributes: , in It represents the waiting time after the electric car owner in the current parking space places a charging request. On this basis, the edge value of the static topology is represented by the length of the rail between two vertices.

[0033] In step S120 , a dynamic topology is established. Figure 6 The schematic diagram of dynamic topology construction is shown schematically. Dynamic topology is used to represent the position relationship and communication connectivity of heterogeneous multi-agents of charging robots and mobile charging piles. Mainly includes A charging robot and A vertex set of heterogeneous agents with mobile charging piles , where the type of vertex is described in the properties. Dynamic Topology The edge is different from the static topology. It represents whether the communication line is connected or not, that is, it will respond to the movement of the intelligent body and there will be changes in the dynamic topology structure.

[0034] The information contained in the heterogeneous agent vertices includes: , in, Indicates the current physical position of the agent in the parking lot coordinate system. Indicates the charging task to which the current agent is assigned. A charging task is assigned to a charging robot and a mobile charging pile formation using the method described in step (2), and is represented by the number of the corresponding parking space vertex; Represents the energy consumption coefficient of the intelligent agent, which represents the electrical energy consumed per unit time. represents the remaining power of the current agent; and Represents special properties related to the vertex type. When the agent is a charging robot, it represents the relevant parameters of the robotic arm. When it is a mobile charging pile, it represents the maximum charging power that the charging pile can achieve. Indicates the current route of the robot.

[0035] Next, we design the edge value, i.e. the communication link. Define the vertex nearby The vertices in can establish communication with it, that is, there is an edge between the two; on this basis, considering the heterogeneous characteristics of dynamic topological vertices, a communication link will be established between the charging robot and the mobile charging pile assigned to the same vehicle charging task in step (2), and both communication links are undirected edges, and communication loss or delay is not considered. Finally, the edge is defined The communication strength is: , in, represents the actual distance between the two agents, Indicates the distance threshold for communication. When the distance is greater than the threshold, the communication link between the two is disconnected. Overall, the communication link in the dynamic topology only exists between homogeneous agents with a distance less than the threshold or heterogeneous agents with the same task.

[0036] Next, the process proceeds to step S200. In step S200, centralized task allocation is performed. In response to multiple charging requests, for a heterogeneous multi-agent system, the task allocation problem is modeled as a cooperative game optimization model to perform centralized task allocation.

[0037] The following will refer to Figure 3 Describe the centralized task allocation steps in detail.

[0038] In step S210, first define Task collection: , Among them, the task It has the following properties: , in Indicates the power requirement for the current charging task. Indicates the location of the charging port of the current task vehicle. When the task occurs (i.e. after the user initiates a charging request), the camera directly above the parking space identifies the vehicle information to obtain Specific information; Indicates the priority of the current task, which is mainly judged by the level of the user who initiated the charging request. The higher the priority, the The smaller; Represents the position of the vehicle in the parking space and the number of the vertex where the parking space is located in the static topology.

[0039] Then, in step S220, the task allocation matrix is ​​defined ,in, Representing an Agent Assigned to perform tasks The decision results: , Then, in step S230, a utility function is designed. Specifically, for each agent The utility function of the agent is designed. Execute the task The utility after is defined as: , Since each charging task requires a heterogeneous agent formation to complete, if there is a large arrival time difference between heterogeneous agents, it will cause resource waste. Therefore, the joint utility function is defined as: , In the agent number, the first part represents the charging robot, and the second part represents the mobile charging pile. The final decision utility function is as follows: , Finally, in step S240, the corresponding constraint conditions are designed according to the utility function and system topology designed above. First, it is necessary to ensure that the robot has enough power storage to go to the task assigned parking space. The condition is expressed by the following formula: , When designing constraints for mobile charging piles, the maximum power supported by the charging equipment carried by them must meet the requirements of the vehicle requesting charging. This condition is expressed by the following formula: , Constraints for the charging robot are designed. The robotic arm it carries needs to be able to use the parking space coordinates as the robotic arm base, and the inverse kinematics equation is used to solve the target pose of the end effector calculated based on the vehicle pose and the charging port position: , in represents the inverse kinematics of the carried robotic arm, It represents the position equation of the end effector calculated based on the current posture of the vehicle and the prior information of the charging port position. The optimization model of the centralized cooperative game model of task allocation is obtained: , Among them, constraint (a) ensures that each intelligent agent currently has at most one charging task assigned, constraint (b) ensures that each charging request is currently assigned at most one charging robot-mobile charging pile formation to respond, and constraints (c) and (d) mainly represent the three constraints defined above, which include power storage, charging request and the structural constraints of the robot arm itself.

[0040] After the centralized task allocation step is completed, the process proceeds to step S300.

[0041] In step S300, distributed path planning is performed. Specifically, with the allocated charging request as the target, a competition-cooperation game model is established based on a local communication fully connected graph constructed using a dynamic topology to perform distributed real-time path planning control.

[0042] The following will refer to Figure 4 Describe the distributed path planning steps in detail.

[0043] In step S310, participants and strategies are defined. Participants mainly include A charging robot and Mobile charging piles, the strategy space mainly includes: , in ai is a vector. Due to the limitation of the robot guide rail, there are only two directions: positive and negative x and positive and negative y.

[0044] In step S320, a utility function is designed. Specifically, the utility function is represented by the following formula: , in They represent the competitive utility function and the cooperative utility function respectively.

[0045] For the cooperative utility function, the abstract concept of "congestion" is introduced. The group of agents connected by the communication links constructed nearby punishes the situation where the distance between two agents is too close or they are moving in opposite directions, so that the heterogeneous multi-agent system with small-range communication capabilities can cooperate to achieve local obstacle avoidance. The following cooperation utility function is designed: , in, Representatives and Agents with communication links, but not heterogeneous agents with the same charging task. The design of the cooperative utility function is designed for local obstacle avoidance.

[0046] For the competitive utility function, on the basis of the cooperative utility function, it is easy to obtain that all agents choose the stopping strategy to optimize the cooperative utility function, which leads to the failure of task response. Therefore, the competitive utility function is designed to stimulate each agent to complete the assigned task as quickly as possible, and on this basis, the time difference between heterogeneous agents with the same task and arriving at the task location can be reduced, which is expressed as follows: , The final system competition utility function is expressed as follows: , Then, the process enters step S400. In step S400, a planning strategy is designed. Specifically, based on game theory, the game model in the centralized task allocation step and the distributed path planning step is solved by using model predictive control until it converges to a Nash equilibrium solution sequence that meets the conditions, and the planning control sequence within the prediction field of view is output as a control vector.

[0047] The following will refer to Figure 7 Step S400 is described. Figure 7 It is a schematic diagram showing task allocation and local trajectory planning control. Considering the stability of the assigned tasks, the cooperative game optimization model is modified to obtain the following centralized task allocation cooperative game optimization model: , The Nash equilibrium solution of the cooperative-competitive game model is calculated. Set up the following optimization problem: , The establishment of the competition and cooperation game model can help the intelligent agent avoid possible collisions on the path while ensuring that it can quickly reach the target location. The equality constraint is defined as , inequality constraints , the constraints involving other agents are On this basis, we obtain the intelligent agent The optimal strategy is , the optimal strategy of the remaining agents is defined as , thus defining the generalized Nash equilibrium as: , In the optimization problem, the objective function of each agent depends only on its own strategy optimization. However, due to the existence of a competitive game model, the strategies of other agents right In order to capture this feature, the optimal strategy of the remaining robots is added to the objective function as a sensitive term, thus obtaining the following formula: , in, Based on intelligent Strategic Agent The utility of the optimal strategy, is the identification parameter of the relationship between robots: , The established model is a static game, that is, the agent When making the optimal decision, the decisions of other agents cannot be perceived. However, due to the existence of the communication link, the final decision of the previous moment can be known. Therefore, while solving the problem of one agent, the strategies of other agents in the previous iteration are frozen and used, and the Gauss-Sidal iterative best response method is used to calculate the approximate Nash equilibrium. In the k-iterative optimization, use The first-order Taylor expansion of the neighborhood is approximated as: , in is a constant term, , using the KarushKuhn Tucker (KKT) condition and simple deduction, we get the following formula: , in Denote the Lagrange multipliers associated with the constraints involving other agents, and the final expression of the optimization problem of distributed local path planning is obtained as: , in, represents the strategy of agent i and other agents' strategies The decision utility function is composed of represents the correlation between agent i and agent j, and represents the equality and inequality constraints contained in step S400 that are only related to the agent itself, It represents the joint constraints of the generalized Nash equilibrium that depend on the decisions of other subjects, including collision constraints between two agents, task allocation constraints, etc., and includes the constraints related to the decisions of other agents in the optimization problem set up for agent i in step S400.

[0048] At this point, the iterative optimization continues until it converges to a Nash equilibrium solution that satisfies the KKT conditions.

[0049] The scheduling method of the charging system of the present invention can achieve better capture of the relationship between multiple intelligent agents based on the construction of a double-layer topology of static topology and dynamic topology by using cooperative game models and cooperative-competitive game models, and solve the Nash equilibrium for the optimal planning control decision in a way of optimizing and predicting the model predictive control.

[0050] Other embodiments The embodiments of the present invention may also be implemented by reading out and executing computer executable instructions (e.g., one or more programs) recorded on a storage medium (which may also be more completely referred to as a "non-transitory computer-readable storage medium") to perform one or more functions in the above-mentioned embodiments, and / or a computer of a system or device including one or more circuits (e.g., an application-specific integrated circuit (ASIC)) for performing one or more functions in the above-mentioned embodiments, and the embodiments of the present invention may be implemented by, for example, a method in which the computer of the system or device reads out and executes the computer executable instructions from the storage medium to perform one or more functions in the above-mentioned embodiments, and / or controls the one or more circuits to perform one or more functions in the above-mentioned embodiments. The computer may include one or more processors (e.g., a central processing unit (CPU), a microprocessing unit (MPU)), and may include a network of separate computers or separate processors to read out and execute the computer executable instructions. The computer executable instructions may be provided to the computer, for example, from a network or the storage medium. The storage medium may include, for example, one or more of a hard disk, a random access memory (RAM), a read-only memory (ROM), a memory of a distributed computing system, an optical disk (such as a compact disc (CD), a digital versatile disc (DVD), or a Blu-ray Disc (BD)™), a flash memory device, a memory card, and the like.

[0051] The embodiments of the present invention may also be implemented by providing software (program) for executing the functions of the above embodiments to a system or device via a network or various storage media, and a computer or a central processing unit (CPU) or a microprocessing unit (MPU) of the system or device reads and executes the program.

[0052] While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments.The scope of the following claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.

Claims

1. An intelligent agent scheduling method for a charging system, wherein the charging system has multiple intelligent agents, the intelligent agents include charging robots and mobile charging piles, and the scheduling method includes: The charging system network topology construction step (S100) constructs a network topology for the parking lot physical system and the charging robot-mobile charging pile heterogeneous multi-agent system, wherein the network topology includes a static topology based on parking lots, robot rails, and charging cars, and a dynamic topology based on charging robots, mobile charging piles, and communication links between them; A centralized task allocation step (S200), in response to multiple charging requests, for a heterogeneous multi-agent system, modeling the task allocation problem as a cooperative game optimization model to perform centralized task allocation; The distributed path planning step (S300) takes the allocated charging request as the target, establishes a competition-cooperation game model based on the local communication fully connected graph constructed by using the dynamic topology, and performs distributed real-time path planning control; The planning strategy design step (S400) is based on game theory and utilizes model predictive control to solve the game models in the centralized task allocation step and the distributed path planning step until they converge to a Nash equilibrium solution sequence that minimizes the objective function in the corresponding model predictive control optimization model, and outputs the planning control sequence within the prediction field of view as a control vector.

2. The scheduling method according to claim 1, wherein: In the centralized task allocation step, the task allocation problem is modeled as the following cooperative game optimization model: ， in, N r and N c Respectively represent the number of charging robots and mobile charging piles in the system, N task Indicates the number of charging requests in the system at the current moment. Representing an Agent Assigned to perform tasks The first row of constraints means that each charging request needs to be responded by at most one and only one heterogeneous intelligent agent formation of charging robot and mobile charging pile, respectively. The second row of constraints means that each intelligent agent currently has only one charging task assignment. h(X) and g(X) represent the equality or inequality constraints on power storage, vehicle demand and robot arm structure, respectively. u allocation represents the decision utility function.

3. The scheduling method according to claim 1, wherein: In the planning strategy design step, the cooperative game optimization model established in the centralized task allocation step is modified as follows to make the allocation task stable: ， in, N r and N c Respectively represent the number of charging robots and mobile charging piles in the system, N task Indicates the number of charging requests in the system at the current moment, Representing an Agent Assigned to perform tasks The first row of constraints means that each charging request needs to be responded to by at most one and only one heterogeneous intelligent agent formation of charging robots and mobile charging piles, respectively. The second row of constraints means that each intelligent agent currently has only one charging task assignment. h(X) and g(X) represent equality or inequality constraints on power storage, vehicle requirements, and robot arm structure. u Represents the decision utility function at the next moment.

4. The scheduling method according to claim 1, wherein: The Nash equilibrium solution of the cooperation-competition game model in the distributed path planning step is calculated, and the expression of the optimization problem is obtained as follows: ， in, represents the strategy of agent i and other agents' strategies The decision utility function is composed of represents the correlation between agent i and agent j, and represents the equality and inequality constraints related only to the agent itself contained in the planning strategy design step, represents the joint constraints of the generalized Nash equilibrium that depend on the decisions of other subjects, which include the collision constraints between the two agents, the task allocation constraints, and the constraints related to the decisions of the remaining agents in the optimization problem set up for agent i in the planning strategy design step. Furthermore, the optimization is iterated until it converges to a Nash equilibrium solution that satisfies the KKT condition.

5. The scheduling method according to claim 1, wherein: The steps to build the charging system network topology include: Static topology building step (S110): building a static parking lot physical topology map based on relevant physical information of the parking lot. Among them, in the parking lot physical static topology, the vertex contains the following attributes: ， in Represents the value of the parking space vertex in the static topology, Indicates whether there is any uncompleted charging request in the current parking space. Indicates the waiting time after the electric car owner in the current parking space places an order for charging. Represents the current time, represents the initial time when the charging request appears. On this basis, the edge value of the static topology is represented by the length of the rail between two vertices; The dynamic topology establishment step (S120) is used to represent the positional relationship and communication connectivity of the heterogeneous multi-agents of the charging robot and the mobile charging pile. The information contained in the vertices of the heterogeneous multi-agents includes the following attributes: ， in Represents the value contained in the vertex in the dynamic topology, Indicates that the current vertex belongs to a charging robot or a mobile charging pile. Indicates the current physical position of the agent in the parking lot coordinate system. Indicates the charging task to which the current agent is assigned; represents the energy consumption coefficient of the agent, represents the remaining power of the current agent; and Represents special properties related to the vertex type, Indicates the current route of the robot. Among them, the edge The communication strength is: ， in, represents the actual distance between the two agents, Indicates the distance threshold for communication. When the distance is greater than the threshold, the communication link between the two is disconnected.

6. The scheduling method according to claim 1, wherein: The steps of centralized task allocation include: The task set definition step (S210) defines the following task set: ， The tasks It has the following properties: ， in, Indicates the power requirement for the current charging task. Indicates the location of the charging port of the current mission vehicle. After the mission occurs, the camera directly above the parking space will identify the vehicle information to obtain Specific information; Indicates the priority of the current task. The higher the priority, the The smaller; Indicates the position of the vehicle in the parking space and the number of the vertex where the parking space is located in the static topology; Task allocation matrix definition step (S220): define the following task allocation matrix: ,in Representing an Agent Assigned to perform tasks The decision results: ； Utility function design step (S230), for each agent The utility function is designed, the agent Execute the task The latter utility is defined as: ， The joint utility function is defined as: ， The decision utility function is: ； in, x prj and y prj Indicates the coordinate position of task j, x i0 ,y i0 represents the coordinate position of the charging robot in the heterogeneous agent formation, x i1 ,y i1 represents the location of the mobile charging pile in the heterogeneous agent formation, u represents the joint utility function of heterogeneous agent formation i when performing task j, i includes charging robot i0 and mobile charging pile i1, P i Indicates the priority of the current task. b i Indicates the remaining power of the current agent. c i represents the energy consumption coefficient of the agent, v i0 , v i1 represents the current speed of the charging robot i0 and the mobile charging pile i1 in the heterogeneous agent formation, Constraint design step (S240): Design constraints for the charging robot, and use the inverse kinematics equation to solve the end effector target posture calculated based on the vehicle posture and the charging port position: ， in, represents the inverse kinematics of the carried robotic arm, It means that the position equation of the end effector is calculated according to the current posture of the vehicle and the prior information of the charging port position to obtain the optimization model of the centralized cooperative game model of task allocation. p targrt Indicates the 6-dimensional position and posture information of the charging port. s i Represents special properties related to the vertex type, x prj ,, y prj Represents the position information of the jth vertex in the overall topology Represents the position of the vehicle in the parking space and the number of the vertex where the parking space is located in the static topology.

7. The scheduling method according to claim 1, wherein: The distributed path planning steps include: Participants and strategy definition step (S310), participants include A charging robot and Mobile charging stations, the strategy space includes: ， in a i It is a vector, and has two directions: positive and negative x and positive and negative y; The utility function design step (S320) is to design a planning utility function, which includes: ， in, They represent the competitive utility function and the cooperative utility function respectively.

8. The scheduling method according to claim 6, wherein: The utility function includes a cooperative utility function designed to The group of agents connected by the communication link constructed nearby punishes the situation where the distance between two agents is close or they are moving in opposite directions. The cooperative utility function is as follows: ， in, Representatives and An agent with a communication link.

9. The scheduling method according to claim 6, wherein: The utility function includes a competitive utility function, which is designed to stimulate each agent to complete the assigned task as quickly as possible and reduce the time difference between heterogeneous agents of the same task and the time difference in arriving at the task location. The competitive utility function is as follows: ,and The final system competition utility function is as follows: 。 10. An intelligent agent scheduling device for a charging system, the charging system having a plurality of intelligent agents, the intelligent agents including a charging robot and a mobile charging pile, the scheduling device comprising: The charging system network topology construction unit builds the network topology for the parking lot physical system and the charging robot-mobile charging pile heterogeneous multi-agent system. The network topology includes a static topology based on parking spaces, robot rails and charging cars, and a dynamic topology based on charging robots, mobile charging piles and the communication links between them. A centralized task allocation unit, which responds to multiple charging requests, models the task allocation problem as a cooperative game optimization model for a heterogeneous multi-agent system to perform centralized task allocation; The distributed path planning unit takes the assigned charging request as the target and establishes a competition-cooperation game model based on the local communication fully connected graph constructed using dynamic topology to perform distributed real-time path planning control; as well as The planning strategy design unit, based on game theory and using model predictive control, solves the game model established by the centralized task allocation unit and the distributed path planning unit until it converges to a Nash equilibrium solution sequence that meets the conditions, and outputs the planning control sequence within the prediction field of view as a control vector.

11. A non-temporary storage medium storing a computer program, which, when executed by a processor, can implement the control method for heterogeneous multi-agent collaborative operations according to any one of claims 1 to 9.

12. A computer program product, comprising computer instructions, which, when executed by a processor, can implement the intelligent agent scheduling method for a charging system according to any one of claims 1-9.

Images