Test scheduling method, system, device and medium for autonomous vehicle

Abstract

The application provides a test scheduling method, system, device and medium for an autonomous vehicle. The method comprises: obtaining autonomous driving information of a plurality of autonomous vehicles in a dynamic test field, wherein the autonomous vehicles comprise offline test vehicles and research and development test vehicles; determining a target vehicle to be scheduled in the plurality of autonomous vehicles based on the autonomous driving information and test requirements corresponding to the autonomous vehicles; dynamically generating a test scheduling instruction for the target vehicle based on the autonomous driving information and the test requirements corresponding to the target vehicle; if the target vehicle is an offline test vehicle, sending the test scheduling instruction to the target vehicle; and if the target vehicle is a research and development test vehicle, sending the test scheduling instruction to a test tool on the target vehicle. Through the application, the human resource consumption, operation and testing human cost are reduced, and the efficiency of test scheduling is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent electric vehicle manufacturing, and in particular to a test scheduling method, system, equipment and medium for autonomous vehicles. Background Technology

[0002] With the accelerated intelligent transformation of the electric vehicle industry, autonomous driving technology is becoming a research hotspot. Whether it's various unmanned vehicles with autonomous driving capabilities rolling off the production line, such as unmanned logistics vehicles, unmanned cleaning vehicles, unmanned patrol vehicles, and unmanned charging vehicles, or specially designed chassis used for research and testing, all require rigorous performance verification in dynamic testing grounds. As a key facility simulating real-world road environments, the importance of dynamic testing grounds is increasingly prominent, especially in ensuring the reliability of unmanned vehicles before they leave the factory and conducting long-term durability testing.

[0003] Currently, production line-ready test vehicles, equipped with advanced perception systems and autonomous driving algorithm platforms, are capable of autonomously navigating dynamic test tracks and identifying and avoiding dynamic obstacles, thus ensuring the safety of the testing process. However, test vehicles equipped with R&D test chassis lacking equivalent sensor configurations rely primarily on pre-set automatic tracking programs for navigation within the dynamic test track. When these vehicles need to use the dynamic test track simultaneously with production line-ready test vehicles, remote control is currently the primary method used to avoid potential collision risks, ensuring the safe operation of the test chassis and instructing it to avoid other vehicles in operation.

[0004] However, this model, which relies heavily on manual remote control, results in a huge consumption of human resources, significantly increases the labor costs of operations and testing, and also limits the efficiency of test scheduling. Summary of the Invention

[0005] This application provides a test scheduling method, system, equipment, and medium for autonomous vehicles, which reduces human resource consumption, operation, and testing labor costs, while also improving the efficiency of test scheduling.

[0006] Firstly, this application provides a test scheduling method for autonomous vehicles, applied to a scheduling platform. The test scheduling method for autonomous vehicles includes:

[0007] The autonomous driving information of multiple autonomous vehicles in the dynamic test field is obtained. The autonomous vehicles include off-line test vehicles and R&D test vehicles with test chassis installed. The R&D test vehicles are equipped with test fixtures and communicate with the scheduling platform through the test fixtures. The test fixtures are used to control the safe operation of the R&D test vehicles in the dynamic test field.

[0008] Based on autonomous driving information and the corresponding testing requirements of autonomous vehicles, target vehicles to be dispatched are identified from multiple autonomous vehicles.

[0009] Based on autonomous driving information and the corresponding test requirements of the target vehicle, test scheduling instructions are dynamically generated for the target vehicle. These test scheduling instructions are used to control the safe operation of the target vehicle in the dynamic test field.

[0010] If the target vehicle is a test vehicle, a test scheduling instruction is sent to the target vehicle; if the target vehicle is a research and development test vehicle, a test scheduling instruction is sent to the test fixtures on the target vehicle.

[0011] In one possible implementation, the autonomous driving information is location information. Correspondingly, based on the autonomous driving information and the test requirements corresponding to the target vehicle, test scheduling instructions for the target vehicle are dynamically generated, including:

[0012] Based on the target vehicle's location information, determine the relative distance between the target vehicle and the vehicle in front;

[0013] When the relative distance is less than or equal to a preset distance threshold, a test scheduling instruction is generated based on the test requirements.

[0014] In one possible implementation, it also includes:

[0015] Detect whether the target vehicle's operating status is abnormal;

[0016] When an abnormal operating status is detected, an immediate stop command is triggered for multiple autonomous vehicles in the dynamic test field.

[0017] In one possible implementation, the operating state is the operating trajectory state, and correspondingly, detecting whether the operating state of the target vehicle is abnormal includes:

[0018] By using vehicle-side geofencing, it is possible to detect whether the target vehicle's movement trajectory deviates from a preset trajectory. The preset trajectory is determined by the target vehicle's trajectory data obtained through the positioning system.

[0019] Determine the duration for which the motion trajectory deviates from the preset trajectory;

[0020] If the duration is greater than or equal to the preset duration threshold, the running status is determined to be abnormal.

[0021] If the duration is less than the preset duration threshold, the running status is determined to be not abnormal.

[0022] In one possible implementation, the operating state is a heartbeat connection, and correspondingly, detecting whether the operating state of the target vehicle is abnormal includes:

[0023] Determine whether the heartbeat connection between the target vehicle and the dispatch platform, based on the message queue telemetry transmission protocol, has timed out;

[0024] If the heartbeat connection times out, the running status is determined to be abnormal.

[0025] If the heartbeat connection does not time out, the running status is determined to be not abnormal.

[0026] Secondly, this application provides a test scheduling system for autonomous vehicles, comprising:

[0027] The system includes a dispatch platform and multiple autonomous vehicles, including off-line test vehicles and R&D test vehicles equipped with test chassis. The off-line test vehicles communicate with the dispatch platform, while the R&D test vehicles are equipped with test fixtures and communicate with the dispatch platform through these fixtures.

[0028] The scheduling platform is used to acquire autonomous driving information of multiple autonomous vehicles in the dynamic test field, and to determine the target vehicle to be scheduled among the multiple autonomous vehicles based on the autonomous driving information and the corresponding test requirements of the autonomous vehicles.

[0029] The scheduling platform is also used to dynamically generate test scheduling instructions for the target vehicle based on autonomous driving information and the corresponding test requirements of the target vehicle; and if the target vehicle is a production test vehicle, it sends test scheduling instructions to the target vehicle; if the target vehicle is a research and development test vehicle, it sends test scheduling instructions to the test fixtures on the target vehicle.

[0030] Offline test vehicles are used to receive test scheduling instructions in order to control the safe operation of target vehicles in dynamic test fields;

[0031] The testing fixture is used to receive test scheduling instructions in order to control the safe operation of the target vehicle in the dynamic test field.

[0032] In one possible implementation, a wireless access point network with a density greater than or equal to a density threshold is deployed in the dynamic test field. The wireless access point network is used to ensure that the communication delay between the autonomous vehicle and the scheduling platform is less than or equal to the delay threshold, and that the communication interruption duration during the switching of wireless access points by the autonomous vehicle is less than a preset time threshold.

[0033] In one possible implementation, it also includes a manufacturing execution system that communicates with a scheduling platform to control the number and frequency of autonomous vehicles entering a dynamic test field.

[0034] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0035] The memory stores instructions that the computer executes;

[0036] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0037] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the first aspect and / or various possible embodiments of the first aspect.

[0038] Fifthly, this application provides a computer program product, including a computer program that, when executed, implements the first aspect and / or various possible implementations of the first aspect.

[0039] This application provides a test scheduling method, system, equipment, and medium for autonomous vehicles, relating to the field of intelligent electric vehicle manufacturing. The method is applied to a scheduling platform. The test scheduling method for autonomous vehicles includes: acquiring autonomous driving information from multiple autonomous vehicles in a dynamic test field, wherein the autonomous vehicles include off-line test vehicles and R&D test vehicles with test chassis installed. The R&D test vehicles are equipped with test fixtures, and the R&D test vehicles communicate and interact with the scheduling platform through the test fixtures, which are used to control the safe operation of the R&D test vehicles in the dynamic test field; determining the target vehicle to be scheduled from among the multiple autonomous vehicles based on the autonomous driving information and the corresponding test requirements of the autonomous vehicles; dynamically generating test scheduling instructions for the target vehicle based on the autonomous driving information and the corresponding test requirements of the target vehicle, which are used to control the safe operation of the target vehicle in the dynamic test field; if the target vehicle is an off-line test vehicle, sending a test scheduling instruction to the target vehicle; if the target vehicle is an R&D test vehicle, sending a test scheduling instruction to the test fixture on the target vehicle. This application solves the problem of collaborative operation of multiple types of vehicles in a dynamic test field through the dynamic scheduling logic of the scheduling platform. Specifically, the scheduling platform dynamically generates test scheduling instructions by collecting real-time autonomous driving information and testing needs from vehicles, and issues instructions precisely based on vehicle type, avoiding collision risks caused by resource conflicts or scheduling delays. This approach coordinates the differentiated control needs of the two types of vehicles through a unified scheduling logic, significantly improving the operational efficiency and safety of the test site. Furthermore, the entire process is conducted without human intervention, reducing human resource consumption, operational and testing labor costs, while also improving test scheduling efficiency. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] Figure 1A flowchart illustrating the test scheduling method for autonomous vehicles provided in this application embodiment. Figure 1 ;

[0042] Figure 2 This is a schematic diagram of the structure of a test scheduling system for autonomous vehicles provided in an embodiment of this application;

[0043] Figure 3 This application provides a communication and interaction scenario between an autonomous vehicle and a dispatch platform, as illustrated in the embodiments of this application.

[0044] Figure 4 This is a schematic diagram of the cloud deployment scheme provided in the embodiments of this application;

[0045] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0046] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0047] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0048] Existing dynamic test track scheduling solutions primarily rely on manual intervention and basic automation technologies. For vehicles undergoing off-line testing, autonomous driving is achieved through a customer-provided autonomous driving platform, utilizing sensors such as radar and cameras to perceive the environment and avoid obstacles. However, this relies on customer interfaces and cloud communication, limiting its functionality to third-party platforms. For R&D test vehicles mounted on test chassis, lacking perception capabilities, they can only drive according to preset tracking programs, requiring manual control of their speed and path via remote control equipment to avoid collisions. When multiple vehicles are running simultaneously, dispatchers must manually allocate vehicle priorities, adjust speeds, or stop them, resulting in low efficiency.

[0049] To address the aforementioned issues, this application provides a method for test scheduling of autonomous vehicles. The method involves acquiring autonomous driving information from multiple autonomous vehicles within a dynamic test range through a scheduling platform. These autonomous vehicles include off-line test vehicles and R&D test vehicles equipped with test chassis. The R&D test vehicles are equipped with test fixtures and communicate with the scheduling platform through these fixtures. The test fixtures are used to control the safe operation of the R&D test vehicles within the dynamic test range. Based on the autonomous driving information and the corresponding test requirements of the autonomous vehicles, a target vehicle to be scheduled is determined from among the multiple autonomous vehicles. Based on the autonomous driving information and the test requirements corresponding to the target vehicle, a test scheduling instruction is dynamically generated for the target vehicle. If the target vehicle is an R&D test vehicle, the test scheduling instruction is sent to the test fixture on the target vehicle.

[0050] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0051] The execution entity of the test scheduling method for autonomous vehicles provided in this application embodiment can be a computing device such as a server or server cluster. The server can be a device such as a mobile phone, computer, or tablet.

[0052] Figure 1 A flowchart illustrating the test scheduling method for autonomous vehicles provided in this application embodiment. Figure 1 ,like Figure 1 As shown, this method is applied to a scheduling platform and includes:

[0053] S101. Obtain autonomous driving information of multiple autonomous vehicles in the dynamic test field. The autonomous vehicles include off-line test vehicles and R&D test vehicles with test chassis installed. The R&D test vehicles are equipped with test fixtures. The R&D test vehicles communicate and interact with the scheduling platform through the test fixtures. The test fixtures are used to control the safe operation of the R&D test vehicles in the dynamic test field.

[0054] The dynamic test track refers to a closed area used for vehicle off-line inspection or durability testing, supporting the collaborative operation of multiple vehicle types, such as off-line test vehicles and R&D test vehicles with installed test chassis. Optionally, the dynamic test track can be a closed test road within an unmanned vehicle manufacturing plant used for dynamic vehicle testing.

[0055] Autonomous driving information refers to the real-time operational status data reported by autonomous vehicles in dynamic testing environments, including location, speed, and battery level. For example, autonomous driving information may include vehicle location and speed data periodically reported by off-line test vehicles via HTTP and / or HTTPS protocols, and vehicle location and speed data periodically reported by R&D test vehicles via the MQTT protocol.

[0056] It's important to clarify that the test fixture is a pluggable hardware device integrating an RTK-GNSS antenna, an inertial navigation IMU, and a BCU. It can be installed and removed from the R&D test vehicle. It includes an autonomous driving system that controls the vehicle to execute test task scripts and can communicate with the scheduling platform and client. The client refers to a desktop application installed on a Windows computer. It provides users with an interactive interface for the vehicle testing process, can send user-issued commands to the scheduling platform, and can receive and visualize data from the scheduling platform and the test fixture.

[0057] S102. Based on autonomous driving information and the corresponding test requirements of autonomous vehicles, determine the target vehicle to be dispatched among multiple autonomous vehicles.

[0058] After acquiring autonomous driving information, the target vehicle to be dispatched is determined from multiple autonomous vehicles based on the autonomous driving information and the corresponding testing requirements of the autonomous vehicles. The testing requirements refer to the testing task requirements that the autonomous vehicles need to meet in the dynamic testing field, including endurance test duration, priority level, etc. For example, a vehicle being rolled out for testing may need to prioritize completing short-term dynamic testing tasks due to customer requirements.

[0059] Optionally, after acquiring the autonomous driving information of the autonomous vehicles, and considering the specific requirements of each test task to be performed in the dynamic test field—for example, a test task requiring a high-priority endurance test duration, or a test vehicle needing to complete a short-term dynamic detection task due to customer requirements—the most suitable target vehicle to be scheduled can be accurately identified from multiple autonomous vehicles. This process ensures the effective use of test resources and prioritizes test needs that are urgent or critical.

[0060] S103. Based on autonomous driving information and the corresponding test requirements of the target vehicle, dynamically generate test scheduling instructions for the target vehicle. The test scheduling instructions are used to control the safe operation of the target vehicle in the dynamic test field.

[0061] After identifying the target vehicle to be dispatched via S102, the dispatching platform dynamically generates a detailed and precise set of test dispatch instructions based on the specific autonomous driving information of the autonomous vehicle and the corresponding test requirements. This set of test dispatch instructions is not statically preset but generated in real time to maximize adaptability to the real-time status of the target vehicle and the dynamic changes in the test scenario, ensuring that the autonomous vehicle can safely and efficiently execute test tasks within the dynamic test range.

[0062] Furthermore, the test scheduling instructions include, but are not limited to: target speed curves, steering instructions, braking control parameters, lane keeping strategies, and rules on how to interact with other dynamic elements in the test track under specific circumstances.

[0063] This step, through precise test scheduling commands, ensures vehicle safety in complex testing environments and accurately collects data that meets test requirements.

[0064] S104. If the target vehicle is a test vehicle, a test scheduling instruction is sent to the target vehicle; if the target vehicle is a research and development test vehicle, a test scheduling instruction is sent to the test fixtures on the target vehicle.

[0065] After generating the test scheduling instruction, the instruction is sent to the corresponding target vehicle based on the target vehicle type. Specifically, if the target vehicle is a production test vehicle, the test scheduling instruction is sent to the target vehicle; if the target vehicle is a research and development test vehicle, the test scheduling instruction is sent to the test fixtures on the target vehicle.

[0066] This application's embodiments solve the problem of coordinated operation of multiple vehicle types in a dynamic test field through the dynamic scheduling logic of the scheduling platform. Specifically, the scheduling platform dynamically generates test scheduling instructions by collecting real-time autonomous driving information and test requirements of vehicles, and accurately issues instructions based on vehicle type, avoiding collision risks caused by resource conflicts or scheduling delays. This method coordinates the differentiated control needs of two types of vehicles through a unified scheduling logic, significantly improving the operational efficiency and safety of the test field. Furthermore, the entire process is conducted without human intervention, thus reducing human resource consumption, operational and testing labor costs, and improving test scheduling efficiency.

[0067] Based on the above embodiments, the autonomous driving information is location information. Correspondingly, based on the autonomous driving information and the test requirements corresponding to the target vehicle, test scheduling instructions for the target vehicle are dynamically generated, including: determining the relative distance between the target vehicle and the preceding vehicle based on the location information of the target vehicle; when the relative distance is less than or equal to a preset distance threshold, generating test adjustment instructions based on the test requirements.

[0068] In this embodiment, the distance between the target vehicle and the vehicle in front is dynamically calculated. When the distance is less than or equal to a preset distance threshold, such as less than or equal to 4 meters, this embodiment does not blindly execute general braking. Instead, it makes a logical judgment based on the specific test requirements of the target vehicle. If the current test requirements allow close following or perception assessment at a specific speed, a vehicle speed limit command is generated to finely adjust the vehicle speed, thereby maintaining the continuity of the test as much as possible while ensuring safety. If the test requirements determine that the current distance has exceeded the safety limit or does not meet the specific static test conditions, a stop command is generated to achieve forced braking. This realizes real-time warning and personalized intervention for potential collision risks during the test.

[0069] Furthermore, when the distance is greater than a preset distance threshold, such as more than 4 meters, the dispatch platform will send a vehicle driving instruction to the target vehicle. In other words, when the distance is greater than the preset distance threshold, the dispatch platform will not interfere with the driving of the target vehicle, and the target vehicle will drive according to the preset trajectory.

[0070] For example, in a dynamic test track, N autonomous vehicles travel in the same direction along approximately the same route. Due to differences in road segment settings and project variations, the corresponding speeds differ. To ensure driving safety, we need to maintain a safe distance between each autonomous vehicle. Since it's in the same direction, we only need to ensure a safe distance between the following vehicles and the vehicles in front. Assuming there are four autonomous vehicles A, B, C, and D entering the test track in an orderly fashion, A only needs to maintain a safe distance from D, B from A, C from B, and D from C. This safe distance is the preset distance threshold described above.

[0071] This embodiment of the application, through its configuration, enables the safety control logic to be deeply decoupled from and matched on demand with complex autonomous driving testing tasks. This effectively protects the hardware safety of expensive test vehicles and sensor equipment while significantly improving scenario adaptability and scheduling flexibility during autonomous driving testing. Furthermore, the above embodiment also achieves dynamic obstacle avoidance between vehicles by comparing real-time location data with distance thresholds.

[0072] Furthermore, based on the dynamic real-time calculation of the relative distance between the target vehicle and the vehicle in front, and the comparison with a preset distance threshold to establish the first layer of spatial safety fence, the current driving speed of the target vehicle can be further introduced for comprehensive evaluation. This allows the embodiments of this application to not only perceive static distance risks, but also accurately assess transient collision risks based on kinetic energy and braking distance.

[0073] Based on the above embodiments, the test scheduling method for autonomous vehicles provided in this application further includes: detecting whether the operating state of the target vehicle is abnormal; and triggering an immediate stop command for multiple autonomous vehicles in the dynamic test field when the operating state is detected to be abnormal.

[0074] In this embodiment, during the entire test scheduling process, it is also necessary to detect in real time whether the operating status of the target vehicle is abnormal, and when an abnormal operating status is detected, trigger an immediate stop command for multiple autonomous vehicles in the dynamic test field.

[0075] In one example, the running state is the running trajectory state. Correspondingly, detecting whether the running state of the target vehicle is abnormal includes: detecting whether the target vehicle's motion trajectory state deviates from a preset trajectory through a vehicle-side geofence, wherein the preset trajectory is determined by the trajectory data of the target vehicle obtained through the positioning system; determining the duration of the motion trajectory deviating from the preset trajectory; if the duration is greater than or equal to a preset duration threshold, determining that the running state is abnormal; if the duration is less than the preset duration threshold, determining that the running state is not abnormal.

[0076] In this example, the positioning system refers to a hardware or software system used to acquire real-time vehicle location information. For example, a positioning system combining an RTK-GNSS antenna and an inertial navigation IMU can provide vehicle location data with centimeter-level accuracy. In research and development test vehicles, the positioning system is integrated into the test fixtures.

[0077] By generating preset trajectories through a positioning system, the problem of path deviation caused by the lack of environmental awareness in R&D test vehicles is solved. For example, under the constraint of preset trajectories, R&D test vehicles can automatically travel along designated routes, reducing the need for manual intervention, while real-time verification of trajectory data further improves driving safety.

[0078] Furthermore, by using vehicle-side geofencing, the movement trajectory of the target vehicle is compared with a preset trajectory. Vehicle-side geofencing refers to a virtual boundary set up on the autonomous vehicle to detect whether the autonomous vehicle deviates from the preset trajectory.

[0079] If the motion trajectory is detected to deviate from the preset trajectory by more than a set threshold, the duration of the deviation is determined. If the duration is greater than or equal to the preset duration threshold, the target vehicle's operating state is considered to be abnormal; otherwise, the target vehicle's operating state is considered not to be abnormal.

[0080] Optionally, the motion trajectory status of the target vehicle can be detected in real time through the vehicle-side geofence. If the motion status deviates from the preset trajectory by more than 25 centimeters and the duration is 500ms, the target vehicle is considered to be in an abnormal state, triggering an immediate stop command for multiple autonomous vehicles in the dynamic test field.

[0081] The specific implementation method for triggering the immediate stop command of multiple autonomous vehicles in the dynamic test field can be as follows: the target vehicle controls itself to stop immediately, and the target vehicle will also upload its own abnormal state as event information to the dispatch platform. After receiving the event information, the dispatch platform will control the other vehicles in the dynamic test field to stop immediately.

[0082] The above example addresses the collision risk caused by vehicles deviating from their trajectory through vehicle-side geofence detection.

[0083] In another example, the running status is a heartbeat connection. Correspondingly, detecting whether the running status of the target vehicle is abnormal includes: determining whether the heartbeat connection between the target vehicle and the dispatch platform based on the message queue telemetry transmission protocol has timed out; if the heartbeat connection timed out, determining that the running status is abnormal; if the heartbeat connection did not time out, determining that the running status is not abnormal.

[0084] In this example, determining whether the operating status is abnormal is done by checking if the heartbeat connection between the target vehicle and the dispatch platform, based on the Message Queuing Telemetry Transport (MQTT) protocol, has timed out. Specifically, if the heartbeat connection times out, the operating status is determined to be abnormal; if the heartbeat connection does not time out, the operating status is determined to be normal.

[0085] Once the operating state is determined to be abnormal, an immediate stop command is triggered for multiple autonomous vehicles within the dynamic test track. The specific implementation of triggering this command can be as follows: the target vehicle stops itself immediately, and the scheduling platform, upon confirming the abnormal operating state, controls the other vehicles within the dynamic test track to stop immediately.

[0086] This example determines subsequent operations by judging whether the heartbeat connection between the target vehicle and the dispatch platform based on the message queue telemetry transmission protocol has timed out. This can improve the real-time performance of test dispatch instructions when there is communication delay or interruption, thereby reducing the risk of collision caused by the vehicle deviating from the trajectory.

[0087] Furthermore, this application embodiment also provides a test scheduling system for autonomous vehicles corresponding to the test scheduling method for autonomous vehicles. Specifically, the test scheduling system for autonomous vehicles includes: a scheduling platform and multiple autonomous vehicles, including off-line test vehicles and R&D test vehicles equipped with test chassis. The off-line test vehicles communicate and interact with the scheduling platform, and the R&D test vehicles are equipped with test fixtures and communicate and interact with the scheduling platform through the test fixtures. The scheduling platform is used to acquire autonomous driving information of multiple autonomous vehicles in a dynamic test field, and to determine the target vehicle to be scheduled among the multiple autonomous vehicles based on the autonomous driving information and the corresponding test requirements of the autonomous vehicles. The scheduling platform is also used to dynamically generate test scheduling instructions for the target vehicle based on the autonomous driving information and the corresponding test requirements of the target vehicle. If the target vehicle is an off-line test vehicle, a test scheduling instruction is sent to the target vehicle; if the target vehicle is an R&D test vehicle, a test scheduling instruction is sent to the test fixture on the target vehicle. The off-line test vehicle is used to receive the test scheduling instructions to control the safe operation of the target vehicle in the dynamic test field. The test fixture is used to receive the test scheduling instructions to control the safe operation of the target vehicle in the dynamic test field. The specific principles have been explained in detail in the previous embodiments, so the embodiments of this application will not be repeated here.

[0088] The aforementioned scheduling platform is a scheduling service deployed on a server. It communicates with the Manufacturing Execution System (MES), clients, and test fixtures to coordinate the joint operation of off-line inspection vehicles and R&D test vehicles in the dynamic test field.

[0089] Traditional WiFi networks are prone to access point (AP) switching during vehicle movement, leading to communication delays or interruptions and affecting the real-time performance of test scheduling commands. To address this issue, in some examples, the system provided in this application deploys an access point network with a density greater than or equal to a density threshold within the dynamic test field. This access point network ensures that the communication delay between the autonomous vehicle and the scheduling platform is less than or equal to the delay threshold, and that the communication interruption duration during access point switching by the autonomous vehicle is less than a preset time threshold. The density threshold, delay threshold, and preset time threshold can be set according to actual conditions; for example, the density threshold can be set to one access point every 50 meters, the delay threshold to 50ms, and the preset time threshold to 50ms.

[0090] This example demonstrates how deploying a high-density AP network within a dynamic test range ensures that autonomous vehicles remain connected to the optimal AP while in motion, preventing communication interruptions caused by AP switching. For instance, when a research and development test vehicle moves from AP1 to AP2, the high-density AP network provides a seamless switchover, ensuring the real-time issuance of test scheduling instructions.

[0091] The existing test scheduling system is not linked with MES, and cannot dynamically adjust the number and frequency of autonomous vehicles in the dynamic test field according to the needs of the production line, resulting in low resource utilization of the dynamic test field.

[0092] In some examples, to address the low resource utilization of dynamic test ranges, embodiments of this application link the manufacturing execution system with the test scheduling system. It is understood that the aforementioned test scheduling system also includes a manufacturing execution system communicatively connected to the scheduling platform, used to control the number and frequency of autonomous vehicles entering the dynamic test range.

[0093] It is understandable that after the off-line test vehicle enters the dynamic test field, the MES system notifies the dispatch platform, which receives control from the dispatch platform through the customer self-driving interface, and then drives away from the dynamic test field after completing the dynamic test in a fully unmanned manner.

[0094] Figure 2 This is a schematic diagram of the structure of a test scheduling system for autonomous vehicles provided in an embodiment of this application. Figure 2 As shown, to achieve vehicle control of the vehicles undergoing offline testing, the customer's intelligent driving service needs to connect to the customer's intelligent driving open platform. This open platform must support receiving test scheduling commands, such as start and stop controls, via HTTP and / or HTTPS protocols. Simultaneously, the open platform should be able to collect real-time data from the vehicles undergoing offline testing via the MQTT protocol and report the collected data and events.

[0095] After the test fixtures are installed, the R&D test vehicle is connected to the dynamic test field WiFi intranet using the test fixtures, and the data collected from the R&D test vehicle is sent via MQTT in ProtoBuf format.

[0096] Furthermore, the communication and interaction scenarios between autonomous vehicles and the dispatch platform can be found in [reference needed]. Figure 3 , Figure 3 This application provides a communication and interaction scenario between an autonomous vehicle and a dispatch platform, as illustrated in an embodiment. Figure 3As shown, the scheduling platform sends task and test scheduling instructions to the communication unit on the autonomous vehicle through a specified communication protocol. The communication unit is responsible for receiving and executing these instructions, while also reporting necessary data. The protocol types include: A) Login / Registration: Establishing a communication connection with the scheduling platform; B) High-Frequency Real-Time Data Reporting: Periodically reporting real-time data such as the autonomous vehicle's position and speed; C) Low-Frequency Non-Real-Time Data Reporting: Periodically reporting data with low real-time requirements, such as battery level; D) Vehicle Control Instructions: Executing test scheduling instructions such as start, stop, and drive at a specified speed; E) Instruction Response: Receiving and confirming all downlink test scheduling instructions; F) Event Reporting: Reporting status information such as task completion and fault alarms.

[0097] It should be noted that the communication unit of the R&D test vehicle is a test fixture.

[0098] The aforementioned communication interaction is based on Figure 4 A cloud-based deployment solution. Figure 4 This is a schematic diagram of the cloud deployment scheme provided in an embodiment of this application. Figure 4 As shown, the dynamic test site's WiFi intranet deploys R&D test vehicles, MES, and PC client tools. Locally, nginx pro serves as the front-end entry point and traffic distributor, an eMQX cluster handles message processing, a scheduling platform cluster manages the core scheduling logic, and a database (db) serves as data storage. These components work together to form a complete and scalable localized operating system. Furthermore, the scheduling platform cluster communicates with the customer's intelligent driving open platform via an open network.

[0099] In summary, it can be understood that the embodiments of this application design a cloud scheduling scheme by combining test chassis automatic tracking driving technology. The scheme receives the real-time location of all off-line test vehicles and R&D test vehicles in the dynamic test field, calculates and sends test scheduling instructions to the test tooling in the R&D test vehicles to avoid collisions between R&D test vehicles and other vehicles. At the same time, it interacts with the MES system of the factory control production line to control the number and frequency of production line vehicles entering the dynamic test field.

[0100] In other words, this application embodiment coordinates the automatic tracking of customer's off-line test vehicles and R&D test vehicles in the dynamic test field through a scheduling platform. This ensures that multiple autonomous vehicles can operate simultaneously in the dynamic test field without colliding with each other. Given limited site resources, this approach guarantees both production line turnover and sufficient space for long-term durability testing of off-line test vehicles. Furthermore, the automatic tracking method replaces manual remote control for durability testing, saving manpower, as a single person can monitor all autonomous vehicles in the dynamic test field.

[0101] Furthermore, this application's embodiments are applicable to dynamic testing ground scenarios in unmanned vehicle manufacturing plants, where two types of vehicles operate simultaneously: off-line inspection vehicles equipped with customer autonomous driving algorithms (possessing perception capabilities) and R&D testing vehicles requiring manual remote control (relying on automatic tracking programs). The scheduling platform is deployed on a server, communicating with the autonomous vehicles via a high-density AP network, receiving real-time data such as the autonomous vehicle's location and status, and linking with the factory production line through the MES system. Within the testing ground, autonomous vehicles interact with the scheduling platform via HTTP / HTTPS or MQTT protocols to issue commands and report data. This scenario requires addressing core issues such as multi-vehicle collaborative scheduling, communication latency control, and rapid response to abnormal states.

[0102] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device 500 provided in this application embodiment may include: a processor 501, and a memory 502 communicatively connected to the processor, wherein:

[0103] The memory stores instructions that the computer executes;

[0104] The processor executes computer execution instructions stored in memory to implement the method described in the foregoing method embodiments.

[0105] It should be understood that processor 501 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the application can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor. Memory 502 may include high-speed random access memory (RAM), and may also include non-volatile memory (NVM), such as at least one disk storage device, or a USB flash drive, external hard drive, read-only memory, disk, or optical disc, etc.

[0106] Optionally, the electronic device 500 may also include a communication interface 503. In specific implementations, if the communication interface 503, memory 502, and processor 501 are implemented independently, they can be interconnected via a bus to complete communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.

[0107] Optionally, in a specific implementation, if the communication interface 503, memory 502, and processor 501 are integrated on a single integrated circuit, then the communication interface 503, memory 502, and processor 501 can communicate through an internal interface.

[0108] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the methods described in any of the foregoing embodiments.

[0109] It is understood that the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0110] An exemplary computer-readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be a component of the processor. The processor and the computer-readable storage medium can reside in an ASIC. Alternatively, the processor and the computer-readable storage medium can exist as discrete components in an electronic device.

[0111] The integrated modules implemented as software functional modules described above can be stored in a computer-readable storage medium. These software functional modules, stored in a computer-readable storage medium, include several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application.

[0112] This application also provides a computer program product, including a computer program that, when executed, implements the method described in any of the foregoing embodiments.

[0113] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0114] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0115] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as these combinations of technical features do not contradict each other, they should be considered within the scope of this specification.

[0116] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0117] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A test scheduling method for an autonomous vehicle, characterized by, The test scheduling method for autonomous vehicles, applied to a scheduling platform, includes: The system acquires autonomous driving information from multiple autonomous vehicles within a dynamic test site. These autonomous vehicles include off-line test vehicles and R&D test vehicles equipped with test chassis. The R&D test vehicles are equipped with test fixtures and communicate with the scheduling platform through these fixtures. The test fixtures are used to control the safe operation of the R&D test vehicles within the dynamic test site. Based on the autonomous driving information and the corresponding test requirements of the autonomous driving vehicles, the target vehicle to be dispatched among the multiple autonomous driving vehicles is determined. Based on the autonomous driving information and the test requirements corresponding to the target vehicle, a test scheduling instruction for the target vehicle is dynamically generated. The test scheduling instruction is used to control the safe operation of the target vehicle in the dynamic test field. If the target vehicle is a production test vehicle, the test scheduling instruction is sent to the target vehicle; if the target vehicle is a research and development test vehicle, the test scheduling instruction is sent to the test fixtures on the target vehicle.

2. The method of claim 1, wherein, The autonomous driving information is location information. Correspondingly, the step of dynamically generating test scheduling instructions for the target vehicle based on the autonomous driving information and the test requirements corresponding to the target vehicle includes: Based on the location information of the target vehicle, determine the relative distance between the target vehicle and the vehicle in front; When the relative distance is less than or equal to a preset distance threshold, the test scheduling instruction is generated based on the test requirements.

3. The method according to claim 1 or 2, characterized in that, Also includes: Detect whether the operating status of the target vehicle is abnormal; When an abnormal operating state is detected, an immediate stop command is triggered for multiple autonomous vehicles within the dynamic test site.

4. The method according to claim 3, characterized in that, The operating state refers to the operating trajectory state. Correspondingly, detecting whether the operating state of the target vehicle is abnormal includes: By using a vehicle-side geofence, it is detected whether the movement trajectory of the target vehicle deviates from a preset trajectory, wherein the preset trajectory is determined by the trajectory data of the target vehicle obtained by the positioning system. Determine the duration for which the motion trajectory deviates from the preset trajectory; If the duration is greater than or equal to a preset duration threshold, the operating state is determined to be an abnormal state. If the duration is less than a preset duration threshold, the operating state is determined to be not an abnormal state.

5. The method according to claim 3, characterized in that, The operating state is a heartbeat connection; correspondingly, detecting whether the operating state of the target vehicle is abnormal includes: Determine whether the heartbeat connection between the target vehicle and the dispatch platform based on the message queue telemetry transmission protocol has timed out; If the heartbeat connection times out, the operating state is determined to be an abnormal state; If the heartbeat connection does not time out, the operating state is determined to be not abnormal.

6. A test scheduling system for autonomous vehicles, characterized in that, include: The system includes a dispatch platform and multiple autonomous vehicles, comprising production test vehicles and R&D test vehicles equipped with test chassis. The production test vehicles communicate with the dispatch platform, and the R&D test vehicles are equipped with test fixtures, which communicate with the dispatch platform. The scheduling platform is used to acquire autonomous driving information of multiple autonomous vehicles in the dynamic test field, and to determine the target vehicle to be scheduled among the multiple autonomous vehicles based on the autonomous driving information and the test requirements corresponding to the autonomous vehicles. The scheduling platform is also used to dynamically generate test scheduling instructions for the target vehicle based on the autonomous driving information and the test requirements corresponding to the target vehicle; and if the target vehicle is a production test vehicle, the test scheduling instructions are sent to the target vehicle; if the target vehicle is a research and development test vehicle, the test scheduling instructions are sent to the test fixtures on the target vehicle. The off-line test vehicle is used to receive the test scheduling instruction in order to control the safe operation of the target vehicle in the dynamic test field; The testing fixture is used to receive the test scheduling instructions in order to control the safe operation of the target vehicle in the dynamic test field.

7. The system according to claim 6, characterized in that, The dynamic test site is equipped with a wireless access point network with a density greater than or equal to a density threshold. The wireless access point network is used to ensure that the communication delay between the autonomous vehicle and the scheduling platform is less than or equal to the delay threshold, and that the communication interruption duration during the switching of the wireless access point by the autonomous vehicle is less than a preset time threshold.

8. The system according to claim 6, characterized in that, Also includes: The manufacturing execution system, which is connected in communication with the scheduling platform, is used to control the number and frequency of the autonomous vehicles entering the dynamic test field.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-5.

Images