A vehicle-road cooperative simulation method and system for automatic driving scheduling joint debugging

Abstract

The application relates to the technical field of automatic driving scheduling, and discloses a vehicle-road cooperation simulation method and system for automatic driving scheduling joint debugging, wherein the method comprises the following steps: acquiring basic joint debugging data; constructing an initial joint debugging scene model; generating a joint debugging interaction context; performing protocol-level interaction analysis and dynamic path triggering processing; performing vehicle-road event coupling updating; and performing consistency checking and abnormal regression control. Compared with the prior art which relies on real vehicles to participate in scheduling joint debugging, especially in a complex port multi-vehicle cooperative operation environment, the technical problem that continuous scheduling verification cannot be realized is solved. According to the application, a protocol-level simulation interaction mechanism for a scheduling system is constructed, and a dynamic path triggering strategy based on path residual length is introduced, so that continuous interaction and cooperative operation of simulation vehicles and roadside equipment in a closed-loop joint debugging process are realized, and the scheduling system problem positioning capability is improved.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving scheduling technology, and in particular to a vehicle-road cooperative simulation method and system for autonomous driving scheduling and coordination. Background Technology

[0002] Currently, in closed or semi-closed operating scenarios such as ports and mining areas, autonomous vehicles typically rely on a dispatching system to uniformly control multi-vehicle task allocation, path planning, and operational coordination. Before system delivery, the interaction logic between the dispatching system and vehicle-side and roadside equipment needs to be verified through joint debugging. However, existing joint debugging methods mainly rely on real vehicles and testing in actual operating environments.

[0003] In the aforementioned methods, frequent interruptions in the joint debugging process are easily caused by factors such as work plan conflicts, unstable vehicle status, abnormal access of roadside equipment, and dynamic changes in work routes during actual operations. For example, in a multi-vehicle collaborative transportation scenario at a port, when some vehicles withdraw from operations due to chassis failure or scheduling conflicts, the overall joint debugging link is forced to stop, making it impossible to continuously verify the scheduling strategy. At the same time, in complex roadside environments, the uncertainty of weighbridge signals, hopper status, and traffic participant perception data further exacerbates the instability of the joint debugging process. Existing technologies are unable to continuously and repeatably verify scheduling strategies under multi-entity dynamic interaction conditions, and cannot fully meet the needs of efficient joint debugging and rapid iteration of autonomous driving scheduling systems in complex work scenarios.

[0004] Therefore, there is an urgent need for a joint debugging method that can still achieve collaborative interaction between multiple vehicles and roadside equipment, dynamic route updates, and continuous verification of scheduling behavior without relying on actual vehicles or being affected by on-site operating conditions, so as to improve the joint debugging efficiency, problem localization capability, and overall delivery stability of the scheduling system. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, the purpose of this invention is to propose a vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging. This method aims to solve the technical problem that existing technologies rely on the participation of real vehicles in scheduling and joint debugging, especially in the complex multi-vehicle cooperative operation environment of ports, where continuous scheduling verification cannot be achieved.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging.

[0007] The vehicle-road cooperative simulation method for autonomous driving scheduling and coordination includes: Step S10: Obtain basic joint debugging data of the target operation area, and based on the basic joint debugging data, use the simulation entity registration and protocol mapping construction mechanism to execute the initial joint debugging scenario construction task and output the initial joint debugging scenario model; Step S20: Based on the initial joint debugging scenario model, a multi-entity state-driven mechanism is used to execute the joint debugging interaction context generation task and output the joint debugging interaction context; Step S30: Based on the joint debugging interaction context, the scheduling response preprocessing task is executed using the protocol-level interaction parsing and dynamic path triggering mechanism, and the path task collaboration result is output; Step S40: Based on the path task collaboration results, a vehicle-road event coupling update mechanism is used to execute the joint simulation task and output the spatiotemporal evolution results of the joint debugging. Step S50: Perform consistency verification and anomaly regression control based on the spatiotemporal evolution results of the joint debugging, and output the joint debugging closed-loop control results.

[0008] Preferably, the initial joint debugging scenario model includes at least a set of simulation entities, road topology relationships, protocol mapping relationships, and initial state relationships of entities; the joint debugging interaction context includes at least the current state of each simulation entity, relationships of messages to be sent, task association relationships, and path request condition relationships; the path task coordination results include at least scheduling response relationships, task execution fragment relationships, and dynamic safe path relationships; the joint debugging spatiotemporal evolution results include at least multi-entity state evolution relationships, roadside event triggering relationships, and communication log association relationships; and the joint debugging closed-loop control results include at least consistency evaluation relationships, anomaly regression relationships, and driving relationships for the next joint debugging cycle.

[0009] Preferably, in step S30, for any autonomous vehicle simulation entity, the dynamic path triggering mechanism satisfies: ;in, This represents the remaining length of the safe path for the i-th autonomous vehicle simulation entity at time t. This indicates the total length of the current safe path issued by the scheduling system to the simulated autonomous vehicle at that moment. This indicates the distance traveled by the simulated autonomous vehicle along the current safe path at that moment; when the following conditions are met... Less than or equal to the preset path trigger threshold At that time, the autonomous vehicle simulation entity is triggered to initiate the next safe path request.

[0010] Preferably, in step S40, during the co-simulation process, the position update of any autonomous vehicle simulation entity satisfies: ; in, This represents the position of the i-th autonomous vehicle simulation entity at time t+Δt. This represents the position of the i-th autonomous vehicle simulation entity at time t. This represents the velocity of the i-th simulated autonomous vehicle at time t. Let Δt represent the acceleration of the i-th autonomous vehicle simulation entity at time t, and let Δt represent the simulation distance step.

[0011] Preferably, step S20, which involves using a multi-entity state-driven mechanism to generate the joint debugging interaction context based on the initial joint debugging scenario model and outputting the joint debugging interaction context, specifically includes: Step S201: Based on the initial joint debugging scenario model, construct the autonomous vehicle task joint debugging state machine, loader positioning and reporting state machine, scale signal switching state machine, hopper departure trigger state machine and roadside perception target reporting state machine; Step S202: Encapsulate the outgoing actions corresponding to the current state of each state machine using protocols to generate the message relationships to be sent; Step S203: Construct a joint debugging interaction context based on the relationship of the message to be sent, which includes the entity's current location, target work point, task execution stage, road section, and path triggering conditions.

[0012] Preferably, in step S202, in the step of encapsulating the outgoing actions corresponding to the current state of each state machine and generating the message relationship to be sent, a message structure is constructed for any outgoing action k. : ; in, Indicates the message identifier, Indicates the message type. Represents a timestamp. Indicates the message body. This represents the validation field. Indicates the direction of transmission and reception; The message types include at least vehicle initialization task request messages, vehicle location reporting messages, task status reporting messages, loader location reporting messages, scale signal messages, hopper departure messages, and roadside perception messages.

[0013] Preferably, step S40, which involves executing a joint simulation task based on the path task collaboration result using a vehicle-road event coupling update mechanism and outputting the spatiotemporal evolution results of the joint simulation, specifically includes: Step S401: Based on the dynamic safety path relationship and the task execution segment relationship, perform discrete long-distance motion updates on each vehicle simulation entity and generate vehicle state evolution relationships; Step S402: Based on the vehicle state evolution relationship and the preset rules for loader operation area, scale area triggering rule, hopper operation triggering rule and roadside perception coverage, a roadside event triggering relationship is formed; Step S403: Record the vehicle positioning report message, task status report message, loader positioning report message, scale signal message, hopper departure message and roadside perception message in a unified timeline to form a communication log association relationship, and generate the joint debugging spatiotemporal evolution result based on the vehicle status evolution relationship, the roadside event triggering relationship and the communication log association relationship.

[0014] This invention also provides a vehicle-road cooperative simulation system for autonomous driving scheduling and coordination, comprising: The initial joint debugging scenario construction module is used to acquire basic joint debugging data of the target operation area, and to execute the initial joint debugging scenario construction task based on the basic joint debugging data using a simulation entity registration and protocol mapping construction mechanism, and output the initial joint debugging scenario model. The joint debugging interaction context generation module is used to perform the joint debugging interaction context generation task based on the initial joint debugging scenario model using a multi-entity state-driven mechanism, and output the joint debugging interaction context. The path task collaboration processing module is used to execute scheduling response preprocessing tasks based on the joint debugging interaction context, using protocol-level interaction parsing and dynamic path triggering mechanism, and output path task collaboration results. The spatiotemporal evolution module is used to execute joint simulation tasks based on the path task coordination results using a vehicle-road event coupling update mechanism, and output the spatiotemporal evolution results. The joint debugging closed-loop control module is used to perform consistency verification and anomaly regression control based on the joint debugging spatiotemporal evolution results, output the joint debugging closed-loop control results, and feed back the driving relationship of the next joint debugging cycle in the joint debugging closed-loop control results to the joint debugging interactive context generation module to drive the closed-loop simulation execution of subsequent joint debugging cycles.

[0015] The present invention also provides a vehicle-road cooperative simulation device for autonomous driving scheduling and joint debugging, comprising: a memory, a processor, and a vehicle-road cooperative simulation program for autonomous driving scheduling and joint debugging stored in the memory and executable on the processor. When the vehicle-road cooperative simulation program for autonomous driving scheduling and joint debugging is executed by the processor, a vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging is implemented.

[0016] The present invention also provides a computer program product, including a vehicle-road cooperative simulation program for autonomous driving scheduling and joint debugging, wherein the vehicle-road cooperative simulation program for autonomous driving scheduling and joint debugging implements the vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging when executed by a processor.

[0017] The beneficial effects of this invention are as follows: By constructing a protocol-level vehicle-road cooperative simulation mechanism for scheduling systems, this invention integrates autonomous vehicles, loaders, and roadside equipment into the same joint debugging closed loop. Based on a multi-entity state-driven and dynamic path triggering mechanism, it realizes continuous task execution and path updates in the simulation environment, thereby completing scheduling joint debugging verification without relying on real vehicles. This effectively avoids the problem of frequent interruptions in joint debugging caused by factors such as operation conflicts and equipment abnormalities in the prior art, and significantly improves the continuity and execution efficiency of scheduling joint debugging.

[0018] This invention introduces a vehicle-road event coupling update mechanism and a consistency assessment and anomaly regression control mechanism based on joint debugging logs. This enables the tracking of the spatiotemporal evolution of the scheduling execution process and the automatic identification of joint debugging deviations. It can also automatically construct regression data and drive the next joint debugging cycle when anomalies occur. This solves the problems of difficulty in reproducing joint debugging problems and reliance on human experience in the prior art, and significantly improves the accuracy of problem location, regression verification efficiency and overall delivery stability of the scheduling system. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the first embodiment of a vehicle-road cooperative simulation method for autonomous driving scheduling and coordination according to the present invention.

[0021] Figure 2 This is a schematic diagram of the equipment for a vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging according to the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Example 1: As Figure 1 The diagram shown is a flowchart of the first embodiment of the vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging of the present invention. The first embodiment of the vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging of the present invention is presented.

[0024] In the first embodiment, the vehicle-road cooperative simulation method for autonomous driving scheduling and coordination includes: Step S10: Obtain basic joint debugging data of the target operation area, and based on the basic joint debugging data, use the simulation entity registration and protocol mapping construction mechanism to execute the initial joint debugging scenario construction task and output the initial joint debugging scenario model; It should be noted that the "basic joint debugging data" refers to the data set used to construct the initial joint debugging scenario model and support the entire subsequent scheduling joint debugging process. It includes not only static structural information describing the working environment but also dynamic rule information describing scheduling interaction rules and entity behavior constraints. Specifically, the basic joint debugging data includes, but is not limited to: high-precision map data and road topology data describing the spatial structure of the working area; vehicle basic parameter data and roadside equipment parameter data characterizing the physical attributes of vehicles and equipment; scheduling communication protocol templates to ensure consistency between simulation interaction and actual production; task operation rule data constraining task execution logic; and initial position and initial state data of each simulation entity to determine the initial distribution of simulation entities. All of the above data types are organized through a unified data structure, enabling data from different sources and of different types to be used collaboratively within the same simulation framework, thereby forming an initial joint debugging scenario model with complete semantic expression capabilities.

[0025] It is understandable that by implementing a simulation entity registration and protocol mapping construction mechanism on the basic joint debugging data, a basic joint debugging model that is consistent with the actual operating system in terms of structure and interaction can be built in the simulation environment. This allows each simulation entity to operate according to the communication logic of the real system during subsequent processes such as executing task requests, path acquisition, and status reporting. Therefore, continuous driving and feedback verification of the scheduling system's behavior can be achieved without relying on actual vehicles and equipment, significantly improving the controllability and stability of the joint debugging process, while avoiding simulation distortion problems caused by missing entities or inconsistent data.

[0026] It should be understood that, compared to the traditional joint debugging method that relies on the direct participation of actual vehicles and on-site equipment, this step, by uniformly modeling and mapping the operating environment, entity attributes, and communication rules, centralizes the interaction relationships originally scattered across the vehicle end, roadside end, and dispatch system into a single simulation model. This allows the joint debugging process to break free from dependence on the physical equipment status and on-site operating conditions. In the traditional method, once a vehicle malfunction, operational conflict, or roadside equipment anomaly occurs, the joint debugging process is forced to stop, and the problem is difficult to reproduce. However, the initial joint debugging scenario model constructed in this step can continuously reproduce multiple operating states in a controlled environment, making the verification of dispatch strategies continuous and repeatable, significantly improving joint debugging efficiency and problem localization capabilities.

[0027] For example, in a port autonomous driving transportation scenario, the yard area, loading and unloading area, weighing area, and transportation channel can be abstracted into a road topology with nodes and connections. Multiple autonomous heavy trucks are registered as autonomous vehicle simulation entities, configured with initial parking positions and task states. Simultaneously, on-site loaders are registered as loader simulation entities to simulate dynamic position changes during loading and unloading collaboration. Weighing equipment and hopper equipment are abstracted into weighing and hopper simulation entities respectively to simulate weighing, unloading, and loading / unloading trigger signals. Furthermore, roadside sensing equipment is abstracted into roadside sensing device simulation entities to simulate the detection and reporting of traffic participants. Based on this, by mapping fields in the scheduling communication protocol template, various requests and reporting information generated by the above simulation entities in the simulation environment can directly interface with the scheduling system. This allows for continuous verification of multi-vehicle scheduling logic, path planning strategies, and roadside collaboration mechanisms without the need for actual vehicle participation. The verification results are consistent with actual operations and have reference value.

[0028] Step S20: Based on the initial joint debugging scenario model, a multi-entity state-driven mechanism is used to execute the joint debugging interaction context generation task and output the joint debugging interaction context; It should be noted that the "multi-entity state-driven mechanism" refers to a processing mechanism that uses the operational states of various simulated entities as the driving source to dynamically organize and update the interactive information required during the joint debugging process. The simulated entities include at least autonomous vehicle simulation entities, loader simulation entities, weighbridge simulation entities, hopper simulation entities, and roadside sensing device simulation entities; each type of simulation entity corresponds to a state machine model to describe its state transition relationships during the joint debugging process. The state machine includes at least initial state, operating state, interactive state, and feedback state, and is further subdivided into task request state, path request state, location reporting state, signal trigger state, or sensing reporting state according to the business characteristics of different entities. Based on the state machine model, the state of each simulated entity at the current moment is uniformly analyzed, and combined with the road topology relationships, task rule constraints, and protocol mapping relationships in the initial joint debugging scenario model, a joint debugging interaction context describing the global interaction relationships at the current joint debugging moment is generated.

[0029] It is understandable that by adopting a multi-entity state-driven mechanism, local state information originally scattered across different entities can be uniformly mapped to the same context structure, enabling the scheduling system to obtain complete and consistent interactive input information at any given time. The joint debugging interaction context not only includes the current position, current task status, and running stage of each simulation entity, but also the relationships of messages to be sent related to scheduling interactions, path request triggering conditions, and the associations between entities. Therefore, when subsequently executing scheduling interactions and path requests, unified processing can be directly performed based on the joint debugging interaction context, avoiding the problems of redundant calculations or inconsistent states from multiple data sources, thereby improving the stability and execution efficiency of the scheduling interaction process. For example, in a port multi-vehicle collaborative transportation scenario, when a self-driving vehicle simulation entity is in the path execution stage and its remaining path length is close to a threshold, its state will enter the path request triggering state; simultaneously, a loader simulation entity located in the same area may be in an operational state, a weighbridge simulation entity may be in a state where weighing is permitted, and a roadside sensing device simulation entity is reporting information about surrounding traffic participants. Through the multi-entity state-driven mechanism, the states of the different entities at the same time can be integrated into a joint debugging interaction context, and corresponding message relationships to be sent and path request conditions can be generated. This enables the scheduling system to allocate paths and adjust tasks based on complete scene information, thereby realizing collaborative scheduling verification between multiple vehicles and roadside equipment and avoiding scheduling deviations caused by incomplete information or asynchronous states.

[0030] Step S30: Based on the joint debugging interaction context, the scheduling response preprocessing task is executed using the protocol-level interaction parsing and dynamic path triggering mechanism, and the path task collaboration result is output; It should be noted that the "protocol-level interaction parsing and dynamic path triggering mechanism" refers to a processing mechanism that, in the simulation environment, standardizes, encapsulates, sends, and parses the relationships of messages to be sent in the joint debugging interaction context according to the communication protocol actually used by the scheduling system, and dynamically determines the path request triggering conditions based on the vehicle's operating status. Specifically, protocol-level interaction parsing refers to encoding and sending vehicle initialization task request messages, vehicle location reporting messages, task status reporting messages, loader location reporting messages, scale signal messages, hopper departure messages, and roadside perception messages according to a predetermined communication protocol format, and parsing and semantically restoring the task allocation results, path distribution results, and control response results returned by the scheduling system. The dynamic path triggering mechanism refers to, for the autonomous vehicle simulation entity, determining in real time whether to initiate the next path request based on its current path execution status and remaining path length. The path triggering condition can be determined through the relationship between the remaining path length and a preset threshold, thereby achieving automatic triggering and continuous updating of path request behavior.

[0031] Understandably, protocol-level interaction parsing ensures consistency between the simulation environment and the actual scheduling system in terms of data format, field meaning, and interaction flow. This allows simulated vehicles to exhibit the same interactive behavior as real vehicles when executing task requests, acquiring paths, and providing status feedback. Simultaneously, the dynamic path triggering mechanism automatically determines the timing of path requests based on the real-time status of the vehicle during operation, eliminating reliance on fixed-period triggering or manual intervention in path acquisition, thereby improving the timeliness and rationality of path updates. Therefore, the path-task collaboration result can simultaneously reflect the scheduling system's response decisions and the vehicle's current task execution status, providing accurate and continuous input for subsequent joint simulations. For example, in a port autonomous driving transportation scenario, when a simulated autonomous vehicle is performing a loading and unloading transportation task and its current path is nearing its destination or the remaining path length is below a preset threshold, the system automatically generates a path request message based on the dynamic path triggering mechanism and sends it to the scheduling system through protocol-level interaction. The scheduling system returns a new path point sequence and task execution instructions based on the current global operation status. After parsing the response result, the simulation system updates the vehicle's task execution segment and path information, forming the path-task collaboration result. At the same time, the status information of other vehicles and roadside equipment is also reported synchronously through protocol-level interaction, enabling the scheduling system to make decisions under the condition of complete global information, thereby realizing the collaborative path scheduling verification among multiple vehicles and multiple devices.

[0032] Step S40: Based on the path task collaboration results, a vehicle-road event coupling update mechanism is used to execute the joint simulation task and output the spatiotemporal evolution results of the joint debugging. It should be noted that the "vehicle-road event coupling update mechanism" refers to a processing mechanism that, during the simulation process, uniformly associates and models the vehicle's operational behavior with the changes in the state of roadside equipment, and synchronously updates the states of multiple entities according to time progression. "Vehicle-road events" include spatial events triggered by vehicle movement and signal events triggered by changes in the state of roadside equipment. Spatial events include at least vehicle entry into or exit from a specific area, vehicle approaching a target work point, and vehicle completion of task segments. Signal events include at least weighbridge loading / unloading signals, hopper loading / unloading trigger signals, and detection and reporting events of traffic participants by roadside sensing equipment. During joint simulation, the dynamic safe path relationship and task execution segment relationship from the path task collaboration results are used as input. Through discrete time step progression, the position, speed, and task state of the simulated autonomous vehicle entity are updated. Simultaneously, based on the updated spatial position of the vehicle and the spatial distribution relationship of the roadside equipment, corresponding roadside events are triggered, and the changes in vehicle state are coupled with changes in roadside events, thus forming a unified spatiotemporal evolution process.

[0033] It should be understood that, compared to traditional techniques that only independently simulate vehicle trajectories or roadside signals, this step establishes a coupling relationship between vehicle behavior and roadside events, enabling the simulation process to realistically reflect the interaction logic in multi-entity collaborative operation scenarios. In traditional methods, the lack of a unified spatiotemporal correlation between vehicles and roadside equipment can easily lead to simulation results that fail to accurately reflect the decision-making effectiveness of the scheduling system in complex scenarios. This step, by synchronously updating vehicle status and roadside events at the same time reference, makes the input information of the scheduling system more complete and consistent, thereby improving the accuracy and reliability of scheduling strategy verification. For example, during port transportation operations, when a simulated autonomous vehicle travels along a dynamic safety path and enters the weighing area, the system triggers a weighing signal based on its current position and spatial relationship with the weighing area, and simultaneously generates a weighing state switching event. When the vehicle completes weighing and leaves the weighing area, a weighing signal is triggered. Simultaneously, when the vehicle reaches the hopper operation area and completes loading and unloading, a hopper departure signal is triggered. Furthermore, if the vehicle enters the coverage area of ​​roadside sensing equipment during its operation, the corresponding roadside sensing equipment simulated entity generates and reports traffic participant detection results. Through the coupled updates of these multiple events and vehicle movement processes, continuous and complete spatiotemporal evolution results can be formed, enabling the scheduling system to obtain inputs highly consistent with actual operations in the simulation environment, thereby achieving effective verification of complex vehicle-road cooperative scheduling behaviors.

[0034] Step S50: Perform consistency verification and anomaly regression control based on the spatiotemporal evolution results of the joint debugging, and output the joint debugging closed-loop control results.

[0035] It should be noted that the "consistency verification and anomaly regression control" refers to a processing mechanism that, during simulation and joint debugging, quantitatively evaluates the degree of matching between the path and task execution results issued by the scheduling system and the simulation execution results, and automatically constructs regression data to drive the next round of joint debugging when deviations are detected. Consistency verification includes at least three aspects: path execution consistency, task state consistency, and message timing consistency. Path execution consistency is used to evaluate the degree of deviation between the actual vehicle trajectory and the path issued by the scheduling system; task state consistency is used to evaluate whether the state transition during task execution conforms to the scheduling instructions; and message timing consistency is used to evaluate whether the time relationship between requests and responses meets preset timing constraints. Anomaly regression control refers to extracting vehicle state data, roadside event data, and communication log data within a certain time window before and after the anomaly occurs from the spatiotemporal evolution results of the joint debugging when any consistency index falls below a preset threshold, constructing an anomaly regression dataset, and generating a targeted joint debugging control strategy based on this dataset to drive replay verification or strategy correction in subsequent simulation cycles.

[0036] Understandably, by verifying the consistency of the spatiotemporal evolution results of the joint debugging process, the original problem identification process, which relied on manual observation and experience-based judgment, can be transformed into a data-driven automated analysis process. This allows the system to detect scheduling execution deviations in real time during operation. Simultaneously, through an anomaly regression control mechanism, key influencing factors can be quickly located after a problem occurs, and relevant data can be structured and organized, providing a direct basis for problem reproduction and scheduling strategy optimization. Therefore, the closed-loop control results of the joint debugging process not only reflect the execution quality of the current joint debugging process but also provide clear control inputs for the next round of joint debugging, achieving continuous optimization of the simulation joint debugging process.

[0037] It should be understood that, compared to traditional methods that rely on manual log checks and problem reproduction, this step introduces consistency assessment and automatic regression mechanisms, enabling the integration process to have self-checking and self-repair capabilities. In traditional methods, when path deviations or task execution anomalies occur during integration, it often requires manual analysis of large amounts of logs and repeated testing under specific conditions, which is inefficient and yields unstable results. This step, however, uses a unified spatiotemporal evolution data model to capture and replay anomalies, allowing problems to be stably reproduced in a controlled environment. Furthermore, a closed-loop control mechanism continuously optimizes the scheduling strategy, thereby significantly improving integration efficiency and system reliability.

[0038] For example, in a port multi-vehicle scheduling scenario, when a simulated autonomous vehicle deviates from the scheduled path during execution, the system detects that this deviation exceeds a preset threshold using a path execution consistency index. At this point, an anomaly regression control process is automatically triggered. The system extracts the vehicle's trajectory data before and after the anomaly, task status changes, and scheduling interaction logs within the corresponding time period from the spatiotemporal evolution results of the joint debugging, constructing an anomaly regression dataset. Subsequently, the system uses this dataset to replay and verify the scheduling system, or adjusts the path triggering strategy and scheduling parameters, and executes the joint debugging simulation again to verify whether the problem has been corrected. Through this process, scheduling problems can be quickly located and repeatedly verified without relying on a real vehicle environment, improving the overall efficiency of system joint debugging and optimization.

[0039] Example 2: Furthermore, the present invention provides a vehicle-road cooperative simulation system for autonomous driving scheduling and coordination, employing a vehicle-road cooperative simulation method for autonomous driving scheduling and coordination as described in the above embodiments, which can solve the technical problem of vehicle-road cooperative simulation for autonomous driving scheduling and coordination. The beneficial effects of the vehicle-road cooperative simulation system for autonomous driving scheduling and coordination provided by the present invention are the same as those of the vehicle-road cooperative simulation method for autonomous driving scheduling and coordination provided in the above embodiments, and other technical features of the vehicle-road cooperative simulation system for autonomous driving scheduling and coordination are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0040] Example 3: This invention provides a vehicle-road cooperative simulation device for autonomous driving scheduling and coordination. Please refer to... Figure 2 A vehicle-road cooperative simulation device for autonomous driving scheduling and coordination includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the vehicle-road cooperative simulation method for autonomous driving scheduling and coordination described in Embodiment 1 above. The vehicle-road cooperative simulation device for autonomous driving scheduling and coordination in this embodiment of the invention may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. This vehicle-road cooperative simulation device for autonomous driving scheduling and coordination is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the invention. A vehicle-road cooperative simulation device for autonomous driving scheduling and coordination may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the vehicle-road cooperative simulation device for autonomous driving scheduling and coordination. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An I / O interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows a vehicle-road cooperative simulation device for autonomous driving scheduling and coordination to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows a vehicle-road cooperative simulation device for autonomous driving scheduling and coordination with various systems, it should be understood that implementation of or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0041] Example 4: This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle-road cooperative simulation method for autonomous driving scheduling and coordination described above. The computer program product provided by this invention can solve the technical problem of vehicle-road cooperative simulation for autonomous driving scheduling and coordination. Compared with the prior art, the beneficial effects of the computer program product provided by this invention are the same as those of the vehicle-road cooperative simulation method for autonomous driving scheduling and coordination provided in the above embodiments, and will not be repeated here.

[0042] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this invention.

[0043] It should be understood that the various parts disclosed in this invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0044] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A vehicle-road cooperative simulation method for autonomous driving scheduling and coordination, characterized in that, The methods include: Step S10: Obtain basic joint debugging data of the target operation area, and based on the basic joint debugging data, use the simulation entity registration and protocol mapping construction mechanism to execute the initial joint debugging scenario construction task and output the initial joint debugging scenario model; Step S20: Based on the initial joint debugging scenario model, a multi-entity state-driven mechanism is used to execute the joint debugging interaction context generation task and output the joint debugging interaction context; Step S30: Based on the joint debugging interaction context, the scheduling response preprocessing task is executed using the protocol-level interaction parsing and dynamic path triggering mechanism, and the path task collaboration result is output; Step S40: Based on the path task collaboration results, a vehicle-road event coupling update mechanism is used to execute the joint simulation task and output the spatiotemporal evolution results of the joint debugging. Step S50: Perform consistency verification and anomaly regression control based on the spatiotemporal evolution results of the joint debugging, and output the joint debugging closed-loop control results.

2. The vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging as described in claim 1, characterized in that, The initial joint debugging scenario model includes at least a set of simulation entities, road topology relationships, protocol mapping relationships, and initial state relationships of entities; the joint debugging interaction context includes at least the current state of each simulation entity, message relationships to be sent, task association relationships, and path request condition relationships. The path task coordination results include at least scheduling response relationships, task execution fragment relationships, and dynamic safe path relationships; The spatiotemporal evolution results of the joint debugging include at least the multi-entity state evolution relationship, the roadside event triggering relationship, and the communication log association relationship; The results of the joint debugging closed-loop control include at least the consistency assessment relationship, the anomaly regression relationship, and the driving relationship for the next joint debugging cycle.

3. The vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging as described in claim 1, characterized in that, In step S30, for any autonomous vehicle simulation entity, the dynamic path triggering mechanism satisfies: ;in, This represents the remaining length of the safe path for the i-th autonomous vehicle simulation entity at time t. This indicates the total length of the current safe path issued by the scheduling system to the simulated autonomous vehicle at that moment. This indicates the distance traveled by the simulated autonomous vehicle along the current safe path at that moment; when the following conditions are met... Less than or equal to the preset path trigger threshold At that time, the autonomous vehicle simulation entity is triggered to initiate the next safe path request.

4. The vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging as described in claim 1, characterized in that, In step S40, during the co-simulation process, the position update of any autonomous vehicle simulation entity satisfies: ； in, This represents the position of the i-th autonomous vehicle simulation entity at time t+Δt. This represents the position of the i-th autonomous vehicle simulation entity at time t. This represents the velocity of the i-th simulated autonomous vehicle at time t. Let Δt represent the acceleration of the i-th autonomous vehicle simulation entity at time t, and let Δt represent the simulation distance step.

5. The vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging as described in claim 1, characterized in that, Step S20, which involves generating a joint debugging interaction context based on the initial joint debugging scenario model using a multi-entity state-driven mechanism and outputting the joint debugging interaction context, specifically includes: Step S201: Based on the initial joint debugging scenario model, construct the autonomous vehicle task joint debugging state machine, loader positioning and reporting state machine, scale signal switching state machine, hopper departure trigger state machine and roadside perception target reporting state machine; Step S202: Encapsulate the outgoing actions corresponding to the current state of each state machine using protocols to generate the message relationships to be sent; Step S203: Construct a joint debugging interaction context based on the relationship of the message to be sent, which includes the entity's current location, target work point, task execution stage, road section, and path triggering conditions.

6. The vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging as described in claim 5, characterized in that, In step S202, during the step of encapsulating the outgoing actions corresponding to the current state of each state machine into protocols and generating the message relationship to be sent, a message structure is constructed for any outgoing action k. : ； in, Indicates the message identifier, Indicates the message type. Represents a timestamp. Indicates the message body. This represents the validation field. Indicates the direction of transmission and reception; The message types include at least vehicle initialization task request messages, vehicle location reporting messages, task status reporting messages, loader location reporting messages, scale signal messages, hopper departure messages, and roadside perception messages.

7. The vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging as described in claim 2, characterized in that, Step S40, which involves executing a joint simulation task based on the path task coordination results using a vehicle-road event coupling update mechanism and outputting the spatiotemporal evolution results of the joint simulation, specifically includes: Step S401: Based on the dynamic safety path relationship and the task execution segment relationship, perform discrete long-distance motion updates on each vehicle simulation entity and generate vehicle state evolution relationships; Step S402: Based on the vehicle state evolution relationship and the preset rules for loader operation area, scale area triggering rule, hopper operation triggering rule and roadside perception coverage, a roadside event triggering relationship is formed; Step S403: Record the vehicle positioning report message, task status report message, loader positioning report message, scale signal message, hopper departure message and roadside perception message in a unified timeline to form a communication log association relationship, and generate the joint debugging spatiotemporal evolution result based on the vehicle status evolution relationship, the roadside event triggering relationship and the communication log association relationship.

8. A vehicle-road cooperative simulation system for autonomous driving scheduling and coordination, applied to the vehicle-road cooperative simulation method for autonomous driving scheduling and coordination as described in any one of claims 1 to 7, characterized in that, The vehicle-road cooperative simulation system for autonomous driving scheduling and coordination includes: The initial joint debugging scenario construction module is used to acquire basic joint debugging data of the target operation area, and to execute the initial joint debugging scenario construction task based on the basic joint debugging data using a simulation entity registration and protocol mapping construction mechanism, and output the initial joint debugging scenario model. The joint debugging interaction context generation module is used to perform the joint debugging interaction context generation task based on the initial joint debugging scenario model using a multi-entity state-driven mechanism, and output the joint debugging interaction context. The path task collaboration processing module is used to execute scheduling response preprocessing tasks based on the joint debugging interaction context, using protocol-level interaction parsing and dynamic path triggering mechanism, and output path task collaboration results. The spatiotemporal evolution module is used to execute joint simulation tasks based on the path task coordination results using a vehicle-road event coupling update mechanism, and output the spatiotemporal evolution results. The joint debugging closed-loop control module is used to perform consistency verification and anomaly regression control based on the joint debugging spatiotemporal evolution results, output the joint debugging closed-loop control results, and feed back the driving relationship of the next joint debugging cycle in the joint debugging closed-loop control results to the joint debugging interactive context generation module to drive the closed-loop simulation execution of subsequent joint debugging cycles.

9. A vehicle-road cooperative simulation device for autonomous driving scheduling and coordination, characterized in that, The vehicle-road cooperative simulation device for autonomous driving scheduling and joint debugging includes: a memory, a processor, and a vehicle-road cooperative simulation program for autonomous driving scheduling and joint debugging stored in the memory and executable on the processor. When the vehicle-road cooperative simulation program for autonomous driving scheduling and joint debugging is executed by the processor, it implements a vehicle-road cooperative simulation method for autonomous driving scheduling and joint debugging as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a vehicle-road cooperative simulation program for autonomous driving scheduling and coordination. When the vehicle-road cooperative simulation program for autonomous driving scheduling and coordination is executed by the processor, it implements a vehicle-road cooperative simulation method for autonomous driving scheduling and coordination as described in any one of claims 1 to 7.

Images