Vehicle scheduling method and system based on complete information static game in mining area scene

Abstract

The invention discloses a vehicle scheduling method and system based on a complete information static game in a mining area scene, and belongs to the field of traffic information processing, and the method comprises the steps: S1, obtaining a high-precision map of the mining area scene, recognizing and screening out road sections with potential road right conflicts, and forming a conflict road ID set; s2, collecting dynamic state parameters of all unmanned mine cars and manned mine cars in the current mining area scene in real time; s3, for each unmanned mine car, judging whether a predetermined driving path of the unmanned mine car intersects with the conflict road ID set or not; if the intersection exists, executing S4, otherwise, continuously monitoring the state of the vehicle; s4, constructing a complete information static game model between the unmanned mine car and other mine cars on the conflict road section, and determining an optimal road right distribution scheme by solving Nash equilibrium; and S5, based on a game solving result, generating a corresponding vehicle control instruction, and issuing the vehicle control instruction to each mine car through MQTT or broadcast.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of traffic information processing, and particularly relates to a vehicle scheduling method and system based on complete information static game in a mining area scenario. BACKGROUND

[0002] Modern open-pit cement mines generally include six main operation processes of drilling, blasting, mining and loading, transportation, crushing and beneficiation. Among them, the transportation link mainly relies on various vehicles for material transfer, and its cost accounts for a large proportion in the overall production and operation structure of the mine. Therefore, how to optimize the vehicle transportation scheduling system through technical means to improve the overall efficiency of the transportation process has become a key direction for the mine to achieve cost reduction and efficiency improvement.

[0003] With the rapid development of modern science and technology, unmanned mine vehicles are gradually applied to actual material transportation tasks in open-pit cement mines due to their highly standardized operation mode and continuous operation without rest. However, the mine road network usually changes dynamically with the advancement of mining process, and generally has characteristics such as slope fluctuation, frequent curves, numerous intersections, and narrow roads with limited visibility. These complex geographical and environmental conditions can easily lead to path conflicts during vehicle operation, especially at intersections, merging sections and vehicle intersection areas, which poses significant safety hazards and low traffic efficiency.

[0004] In addition, there are often mixed operations of manned mine vehicles and unmanned mine vehicles in the production site of open-pit cement mines. Due to the essential difference in decision-making mechanisms between the two types of vehicles - human drivers rely on subjective judgment and experience, while unmanned systems make decisions based on algorithms and sensor data, they may adopt different coping strategies when facing path conflicts, which can easily lead to a lack of standardization in operation behavior and further exacerbate operational risks.

[0005] Therefore, under the current technical and application background, how to effectively identify potential conflict areas in mine road networks and establish a reasonable road right allocation mechanism has become a core problem that needs to be solved. Solving this problem not only helps to standardize vehicle behavior and reduce the probability of safety accidents, but also is a key means to improve the overall transportation efficiency of the mine and ensure production safety. SUMMARY

[0006] The present application proposes a vehicle scheduling method and system based on complete information static game in a mining area scenario, which effectively identifies potential road right conflict events in mine road networks and establishes a reasonable road right allocation mechanism.

[0007] To achieve the above technical purpose, the first object of the present application is to provide a vehicle scheduling method based on complete information static game in a mining area scenario, comprising: S1, acquire a high-precision map of a mine scene, identify and screen road sections with potential road right conflicts, and form a conflict road ID set; S2, real-time collection of dynamic state parameters of all unmanned mine vehicles and manned mine vehicles under the current mine scene; S3, for each unmanned mine vehicle, judge whether the predetermined driving path intersects with the conflict road ID set; if there is an intersection, execute S4, otherwise continue vehicle state monitoring; S4, construct a complete information static game model between the unmanned mine vehicle and other vehicles on the conflict road section, and determine the optimal road right allocation scheme by solving the Nash equilibrium; S5, based on the game solution result, generate corresponding vehicle control instructions, and issue them to each mine vehicle through MQTT or broadcast.

[0008] Preferably, S1 comprises: Analyzing the mine high-precision map, extracting the basic information of all roads, including road ID, road center line coordinates, and topological connection relationship; Based on the spatial relationship analysis of the road center line, the road sections with adjacent road center line points with a distance less than a preset threshold d_min are screened to form a preliminary conflict road candidate set and corresponding conflict points; Taking the identified conflict points as the center, expanding the boundary in both directions along the road until there is no overlapping or intersection area between the roads, and finally determining the complete conflict road ID set; Topological verification and road section division are performed on the conflict road set to clearly define the specific start and end positions of each conflict road section and the associated road ID mapping relationship.

[0009] Preferably, the dynamic state parameters include: real-time speed V of the vehicle, positioning coordinates (x, y), heading angle θ, current road ID, and key path point sequence in the preset driving trajectory and corresponding driving road ID set.

[0010] Preferably, S4 comprises: First, construct a vehicle state vector; Then calculate the time cost, energy cost and safety cost; Finally, determine the optimal road right allocation scheme based on the Nash equilibrium condition.

[0011] The second object of the present application is to provide a vehicle scheduling system based on complete information static game in a mine scene, comprising: A conflict road identification module acquires a high-precision map of a mine scene, identifies and screens road sections with potential road right conflicts, and forms a conflict road ID set; A parameter acquisition module real-time collects dynamic state parameters of all unmanned mine vehicles and manned mine vehicles under the current mine scene; a logic judgment module, for each unmanned mine vehicle, judging whether the scheduled driving path intersects with the conflict road ID set; if there is an intersection, executing the distribution scheme generation, otherwise, continuously performing the vehicle state monitoring; a distribution scheme generation module, constructing a complete information static game model between the unmanned mine vehicle and other mine vehicles on the conflict road section, and determining an optimal road right distribution scheme by solving the Nash equilibrium; a scheduling module, generating corresponding vehicle control instructions based on the game solution result, and issuing the vehicle control instructions to each mine vehicle through MQTT or broadcast.

[0012] Preferably, the identification process of the conflict road identification module comprises: analyzing the mine area high-precision map to extract the basic information of all roads, including road ID, road center line coordinates, and topological connection relationship; based on the spatial relationship analysis of the road center line, screening out road sections with adjacent road center line point spacing less than a preset threshold d_min to form a preliminary conflict road candidate set and corresponding conflict points; taking the identified conflict points as the center, expanding the boundary along the road in both directions until there is no overlapping or intersection area between the roads, and finally determining the complete conflict road ID set; topologically checking and dividing the conflict road set to clearly define the specific start and end positions of each conflict road section and the associated road ID mapping relationship.

[0013] Preferably, the dynamic state parameters include: vehicle real-time speed V, positioning coordinates (x, y), heading angle θ, current road ID, and key path point sequence in the preset driving trajectory and corresponding driving road ID set.

[0014] Preferably, the generation process of the distribution scheme generation module comprises: firstly, constructing a vehicle state vector; then, calculating the time cost, energy cost and safety cost; finally, determining the optimal road right distribution scheme based on the Nash equilibrium condition.

[0015] A third object of the present application is to provide an information data processing terminal for implementing the above-mentioned vehicle scheduling method based on complete information static game in the mine area scenario.

[0016] A fourth object of the present application is to provide a computer program product comprising a computer program for executing the above-mentioned vehicle scheduling method based on complete information static game in the mine area scenario by a processor.

[0017] The fifth object of the present application is to provide a computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the vehicle scheduling method based on complete information static game in a mine scene as described above.

[0018] The advantages and positive effects of the present application are: The present application first realizes the automatic identification of road right conflict road sections based on the road network topology structure and traffic rule information of the high-precision map, can efficiently and accurately generate a potential road right conflict road ID set; on this basis, a complete information static game model is constructed, the dynamic parameters such as real-time state, speed, relative position, road priority of the vehicle are taken into account, and are quantified as the payoff function of each party in the game, and the road right ownership of the conflict road is rationally judged by solving the Nash equilibrium, so as to realize the intelligent decision of the right of way in the multi-vehicle mixed driving scene. The present application not only can significantly improve the overall traffic efficiency of the mixed mine car in the complex working environment, but also can effectively reduce the safety hidden danger caused by the lag or inconsistency of manual judgment, and enhance the reliability and safety of the system. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the schemes in the embodiments of the present application or the prior art, the present application will be further described below with reference to the drawings and embodiments.

[0020] Fig. 1 is the flow chart of the preferred embodiment of the present application; Fig. 2 is the conflict road schematic diagram in the preferred embodiment of the present application; Fig. 3 is the scheduling communication schematic diagram in the preferred embodiment of the present application. DETAILED DESCRIPTION

[0021] The technical schemes of the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. The described embodiments are only some examples of the present application, not all. Obviously, the embodiments of the present application shown in the drawings demonstrate the technical schemes with characteristics. Based on the embodiments of the present application, any other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0022] Please refer to Figs. 1 to 3 : A vehicle scheduling method based on complete information static game in a mine scene, specifically comprising: S1, obtaining the high-precision map of the mine scene, identifying and screening the road sections with potential road right conflict, and forming a conflict road ID set; The specific process includes: first, analyzing the high-precision map data of the mine site, using professional geographic information system (GIS) software or algorithm to extract the basic information of all roads, including road ID, road centerline coordinate sequence, topological connection relationship and other key data elements, to ensure the accuracy and integrity of the data; then, based on the spatial relationship of the road centerline, a detailed analysis is carried out, the Euclidean distance between adjacent road centerline points is calculated, and road segments with a distance less than a preset threshold d_min are selected, thereby forming a preliminary conflict road candidate set and the corresponding conflict point positions, which helps to quickly locate the potential conflict area; then, taking the identified conflict point as the core, the boundary range is expanded bidirectionally along the road, and the iteration calculation is carried out until there is no overlapping or intersection area between the roads, and finally the complete conflict road ID set is determined, and the boundary coordinates in the expansion process are recorded; finally, the conflict road set is strictly checked and the intelligent road section is divided, the connection relationship is verified by using the graph theory method, the specific start and end positions of each conflict road section and the mapping relationship with the associated road ID are determined, and detailed data is generated for subsequent decision-making.

[0023] S2, real-time acquisition of dynamic state parameters of all unmanned mine trucks and manned mine trucks under the current mine site scene; The dynamic state parameters include but are not limited to: real-time speed V of the vehicle, positioning coordinates (x, y), heading angle θ, current road ID, and key path point sequence in the preset driving trajectory and corresponding driving road ID set; in addition, real-time acceleration (divided into longitudinal acceleration ax and transverse acceleration ay), yaw rate ω, time stamp t for data synchronization, transverse offset distance d of the vehicle and the lane line, and road curvature ρ and slope α of the current driving direction.

[0024] S3, for each unmanned mine truck, judge whether the predetermined driving path intersects with the conflict road ID set; if there is an intersection, execute S4, otherwise continue to monitor the vehicle state; S4, a complete information static game model is constructed between the unmanned mine truck and other mine trucks on the conflict road section, and the optimal right allocation scheme is determined by solving the Nash equilibrium; specifically including: First, construct the vehicle state vector; Then calculate the time cost, energy cost and safety cost; Finally, determine the optimal right allocation scheme based on the Nash equilibrium condition.

[0025] For example: assuming that only two vehicles (vehicle A and vehicle B) approach the fork, define the system state: Vehicle state vector:

[0026] Where P is the position, i.e. (x, y); V is the velocity; a is the acceleration; is the load coefficient, ranging from [0, 1], 0 for empty load, 1 for full load; is the driving mode, 0 for manual driving, 1 for automatic driving; is the distance to the conflict point; Each vehicle has four states: accelerating, constant speed, decelerating, and stopping, i.e. Accelerating , Constant speed , Decelerating , Stopping

[0027] Continue to solve the payment function: The time cost component, the expected time of vehicle i (A or B) passing through the intersection:

[0028] Where the waiting time:

[0029] Time cost function:

[0030] Where, is the travel time weight, is the low speed penalty weight, and = 1; is the ideal passing speed, issued by the scheduling platform; is the minimum speed; Energy cost component; Energy consumption model based on vehicle dynamics:

[0031] Where: is the transmission efficiency.

[0032] Traction force calculation:

[0033] Where: is the air resistance; is the vehicle aerodynamic characteristics; is the wind area; is the friction coefficient; is the current slope, which can be provided by the positioning device; Total mass calculation:

[0034] Where: is the vehicle's own weight, is the maximum load. Therefore, the energy cost: .

[0035] Safety cost component TTC-based security assessment:

[0036] In the formula: The collision cost weight should be set to a very large value; For TTC sensitivity.

[0037] TTC (Time to Collision) calculation:

[0038] In the formula: It is set to 0.1 to prevent the divisor from being zero.

[0039] Collision detection function:

[0040] In the formula: Set the distance according to the actual situation for a safe distance.

[0041] Therefore, based on the above calculations, the payment function for vehicle i is:

[0042] Weight constraints:

[0043] , , All adjustments will be made according to actual conditions, when the mine car is manned. It should be increased by 30%; Find the entire payment matrix: Payment Matrix

[0044] Therefore, the optimal response for vehicle A is:

[0045] vehicle Best response:

[0046] Nash equilibrium condition:

[0047] In the formula, For the optimal response function of vehicle A, For the optimal response function of vehicle B, Indicates the action chosen by vehicle A. Indicates the action chosen by vehicle B. For A, the payment under a given combination of actions For the equilibrium movement of vehicle A, For the equilibrium action of vehicle B the best response of A for given B balancing action, the best response of B for given A balancing action.

[0048] Therefore, the Nash equilibrium can be obtained: It can be concluded that the priority score of vehicle i is: In the formula: is the load coefficient, is the distance coefficient, is the distance sensitive coefficient, is the task coefficient, is the current task urgency, belonging to [0, 1], is the speed coefficient, is the speed sensitive coefficient, is the driving weight coefficient, is the driving mode of the ith vehicle.

[0049] S5, based on the game solution result, generate corresponding vehicle control instructions, and issue them to each mine car through MQTT or broadcast.

[0050] For example, the obtained control instructions are issued to the corresponding vehicle. If it is an unmanned mine car, the control instructions are issued to the vehicle end through MQTT. If it is a manned mine car, the control instructions are issued to the vehicle-mounted intelligent terminal, and the instructions are broadcasted.

[0051] A vehicle scheduling system based on complete information static game in a mine scene, comprising: A conflict road identification module obtains a high-precision map of the mine scene, identifies and filters road segments with potential road right conflicts to form a conflict road ID set. The specific identification process includes: Analyzing the high-precision map of the mine, extracting the basic information of all roads, including road ID, road centerline coordinate sequence, topological connection relationship and attribute data; Based on the spatial proximity analysis of the road centerline, the threshold discrimination method is used to filter out road segments with adjacent road centerline point distances less than the preset threshold d_min, and the preliminary conflict road candidate set and the spatial position of the corresponding conflict points are constructed; Taking the identified conflict points as the core, respectively expanding the boundary range along the two-way structure of each road, detecting the expansion termination condition through geometric overlap, until there is no overlapping or intersection area between roads, and finally determining the complete conflict road ID set and its spatial domain; Topological consistency verification and accurate division of conflict road set, clear specific start and end position, spatial geometric characteristics and mapping relationship between multiple road IDs of each conflict road segment, output structured conflict road segment information table.

[0052] ​A parameter collection module, which collects dynamic state parameters of all unmanned mine trucks and manned mine trucks in a current mine scene in real time; The dynamic state parameters include but are not limited to: real-time speed V of the vehicle, positioning coordinates (x, y), heading angle θ, current road ID, key path point sequence in the preset driving trajectory and the corresponding driving road ID set, lateral acceleration a_y, longitudinal acceleration a_x, yaw rate ω, timestamp t, wheel speed information, lateral offset d of the vehicle relative to the road, and estimated time to reach the next key point.

[0053] A logic judgment module, which judges, for each unmanned mine truck, whether the predetermined driving path of the unmanned mine truck intersects with the conflict road ID set; if there is an intersection, an allocation scheme is generated, otherwise the vehicle state monitoring is continuously performed; An allocation scheme generation module, which constructs a complete information static game model between the unmanned mine truck and other mine trucks on the conflict road section, and determines an optimal right-of-way allocation scheme by solving the Nash equilibrium; The generation process of the allocation scheme generation module includes: First, a vehicle state vector is constructed, including position, speed, acceleration, heading angle and other key parameters; Then, the time cost, energy cost and safety cost are calculated respectively; Finally, based on the Nash equilibrium condition, the optimal right-of-way allocation scheme of the system is determined by analyzing the interaction of strategies of each party through the multi-agent game framework.

[0054] For example: assuming that only two vehicles (vehicle A and vehicle B) approach the fork, the system state is defined as: Vehicle state vector:

[0055] In the formula: P is the position, i.e. (x, y); V is the speed; a is the acceleration; is the load coefficient, ranging from 0 to 1, 0 is empty, and 1 is heavy load; is the driving mode, 0 is manned driving, and 1 is automatic driving; is the distance to the conflict point; Each vehicle has four states: acceleration, constant speed, deceleration and parking, i.e. Acceleration , Constant speed , Deceleration , Parking

[0056] Continue to solve the payment function: Time cost component: the expected time of vehicle i (A or B) passing through the fork:

[0057] where the waiting time:

[0058] Time cost function:

[0059] where, is the travel time weight, is the low speed penalty weight, and has = 1; is the ideal passing speed, issued by the scheduling platform; is the minimum speed; Energy consumption cost component; Energy consumption model based on vehicle dynamics:

[0060] where: is the transmission efficiency.

[0061] Traction force calculation:

[0062] where: is the air resistance; is the vehicle aerodynamic characteristics; is the frontal area; is the friction coefficient; is the current slope, which can be provided by positioning equipment; Total mass calculation:

[0063] where: is the vehicle's own weight, is the maximum load. Therefore, the energy consumption cost: .

[0064] Safety cost component Safety evaluation based on TTC:

[0065] where: is the collision cost weight, which should take a very large value; is the sensitivity of TTC.

[0066] TTC (Time to Collision) calculation:

[0067] where: is 0.1 to prevent the divisor from being 0.

[0068] Conflict detection function:

[0069] where: Safety distance, according to the actual settings.

[0070] Thus, according to the above calculation, the payment function of vehicle i is:

[0071] Weight constraint:

[0072] , , According to the actual adjustment, when the mine car is manned, 30% should be added; The entire payment matrix is obtained: Payment matrix

[0073] Therefore, the best response of vehicle A is:

[0074] The best response of vehicle :

[0075] Nash equilibrium condition:

[0076] Where, is the best response function of vehicle A, is the best response function of vehicle B, denotes the action chosen by A vehicle, denotes the action chosen by B vehicle, is the payment of A under a given action combination, is the equilibrium action of vehicle A, is the equilibrium action of vehicle B is the best response of A given B equilibrium action, is the best response of B given A equilibrium action.

[0077] Thus the Nash equilibrium can be obtained:

[0078] It can be concluded that the priority score of vehicle i is: ; Where: is the load coefficient, is the distance coefficient, is the distance sensitive coefficient, is the task coefficient, is the current task urgency, belonging to [0, 1], is the speed coefficient, is the speed sensitive coefficient, is the driving weight coefficient, is the i-th vehicle driving mode.

[0079] The scheduling module generates corresponding vehicle control instructions based on the game solution result, and sends the instructions to each mine vehicle through MQTT or broadcast.

[0080] For example, the obtained control instructions are sent to the corresponding vehicle. If it is an unmanned mine vehicle, the instructions are sent to the vehicle end through MQTT. If it is a manned mine vehicle, the instructions are sent to the vehicle-mounted intelligent terminal for instruction broadcast.

[0081] An information data processing terminal is used to implement the vehicle scheduling method based on complete information static game in the mine area scenario.

[0082] A computer program product includes a computer program, characterized in that the computer program is executed by a processor to implement the vehicle scheduling method based on complete information static game in the mine area scenario.

[0083] A computer-readable storage medium includes instructions that, when executed on a computer, cause the computer to perform the vehicle scheduling method based on complete information static game in the mine area scenario.

[0084] In the above embodiments, all or part of them can be realized by software, hardware, firmware or any combination thereof. When all or part of them are realized in the form of a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL) or wireless (such as infrared, wireless, microwave, etc.)) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more available media sets. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media (such as solid state disks (SSD)) and the like.

[0085] The above merely describes the preferred embodiments of the present application, and it should be pointed out that, for those skilled in the art, several improvements and refinements can be made without departing from the principles of the present application, and these improvements and refinements should also be considered as falling within the protection scope of the present application.

Claims

1. A vehicle scheduling method based on static game theory with complete information in a mining area scenario, characterized in that, include: S1. Obtain a high-precision map of the mining area, identify and filter out road segments with potential right-of-way conflicts, and form a set of conflicting road IDs; S2. Real-time collection of dynamic status parameters of all unmanned and manned mining trucks in the current mining area scenario; S3. For each unmanned mining truck, determine whether its planned driving path intersects with the set of conflicting road IDs; if there is an intersection, execute S4; otherwise, continue monitoring the vehicle status. S4. Construct a static game model with complete information between unmanned mining trucks and other mining trucks on conflict sections, and determine the optimal right-of-way allocation scheme by solving the Nash equilibrium. S5. Based on the game theory solution, generate corresponding vehicle control commands and send them to each mining truck via MQTT or broadcast.

2. The vehicle scheduling method based on static game theory with complete information in a mining area scenario according to claim 1, characterized in that, S1 includes: Analyze the high-precision map of the mining area and extract the basic information of all roads, including road ID, road centerline coordinates, and topological connections. Based on the spatial relationship analysis of road centerlines, road segments with a distance between adjacent road centerline points less than a preset threshold d_min are selected, forming a preliminary candidate set of conflicting roads and corresponding conflict points. Using the identified conflict points as the center, the boundary is extended in both directions along the road until there are no overlapping or intersecting areas between the roads, and finally the complete set of conflicting road IDs is determined. Perform topological verification and segment division on the set of conflicting roads to clarify the specific start and end locations of each conflicting road segment and the mapping relationship of associated road IDs.

3. The vehicle scheduling method based on static game theory with complete information in a mining area scenario according to claim 1, characterized in that, The dynamic state parameters include: vehicle real-time speed V, positioning coordinates (x, y), heading angle θ, current road ID, and a sequence of key path points in the preset driving trajectory and a set of corresponding driving road IDs.

4. The vehicle scheduling method based on complete information static game theory in a mining area scenario according to claim 1, characterized in that, S4 include: First, construct the vehicle state vector; Then calculate the time cost, energy cost, and security cost; Finally, the optimal right-of-way allocation scheme is determined based on the Nash equilibrium condition.

5. A vehicle dispatching system based on static game theory with complete information in a mining area, characterized in that, include: The conflict road identification module acquires a high-precision map of the mining area, identifies and filters out road segments with potential right-of-way conflicts, and forms a set of conflict road IDs. The parameter acquisition module collects the dynamic status parameters of all unmanned and manned mining trucks in the current mining area scenario in real time. The logic judgment module determines whether the planned driving path of each unmanned mining truck intersects with the set of conflicting road IDs; if there is an intersection, the allocation scheme is generated; otherwise, vehicle status monitoring continues. The allocation scheme generation module constructs a static game model with complete information between unmanned mining trucks and other mining trucks on conflict sections, and determines the optimal right-of-way allocation scheme by solving the Nash equilibrium. The scheduling module generates corresponding vehicle control commands based on the game theory solution and sends them to each mining truck via MQTT or broadcast.

6. The vehicle dispatching system based on static game theory with complete information in a mining area scenario as described in claim 5, characterized in that, The conflict road identification module's identification process includes: Analyze the high-precision map of the mining area and extract the basic information of all roads, including road ID, road centerline coordinates, and topological connections. Based on the spatial relationship analysis of road centerlines, road segments with a distance between adjacent road centerline points less than a preset threshold d_min are selected, forming a preliminary candidate set of conflicting roads and corresponding conflict points. Using the identified conflict points as the center, the boundary is extended in both directions along the road until there are no overlapping or intersecting areas between the roads, and finally the complete set of conflicting road IDs is determined. Perform topological verification and segment division on the set of conflicting roads to clarify the specific start and end locations of each conflicting road segment and the mapping relationship of associated road IDs.

7. The vehicle dispatching system based on complete information static game theory in a mining area scenario according to claim 5, characterized in that, The dynamic state parameters include: vehicle real-time speed V, positioning coordinates (x, y), heading angle θ, current road ID, and a sequence of key path points in the preset driving trajectory and a set of corresponding driving road IDs.

8. The vehicle dispatching system based on complete information static game theory in a mining area scenario according to claim 5, characterized in that, The generation process of the allocation scheme generation module includes: First, construct the vehicle state vector; Then calculate the time cost, energy cost, and security cost; Finally, the optimal right-of-way allocation scheme is determined based on the Nash equilibrium condition.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it is a vehicle scheduling method based on static game theory with complete information in a mining area scenario as described in any one of claims 1-4.

10. A computer-readable storage medium comprising instructions, when executed on a computer, causing the computer to perform the vehicle scheduling method based on a static game of complete information in a mining scenario as described in any one of claims 1-4.

Images