Virtual test method and device for automatic driving of unmanned mine card

Abstract

The invention discloses a virtual test method and device for automatic driving of an unmanned mine card, and belongs to the technical field of automatic driving, and the method comprises the steps: simulating the unmanned mine card and an operation environment thereof, and obtaining a virtual vehicle and a virtual operation scene; simulating communication between the virtual vehicle and the automatic driving control system to obtain a virtual communication environment; configuring the virtual vehicle and the virtual operation scene to obtain a virtual test environment; setting a test starting condition, a test ending condition and a test evaluation rule based on the virtual test environment; and controlling the virtual vehicle to complete a test process in the virtual test environment based on the virtual communication environment through the automatic driving control system, and outputting a test result according to a test evaluation rule. According to the invention, through full-process virtualization of creation, test and evaluation of test cases of a real environment and vehicle data, real-time online interaction of an unmanned mine card, an automatic driving control system, a cloud scheduling system and an operation scene can be realized, and test requirements are met.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and particularly to a virtual test method and device for the autonomous driving of unmanned mining trucks. Background Art

[0002] In recent years, unmanned mining trucks have been gradually introduced to the market and achieved large-scale commercial implementation. The functional testing and even system testing of unmanned mining trucks are crucial for the completion of the development of unmanned systems. At present, the main testing methods for unmanned mining trucks are still real vehicle testing and on-site debugging. The actual mining perception data is directly input into the perception algorithm as input for single perception testing or single regulation and control testing without perception input, and the fleet simulation testing mainly conducts process testing. However, this testing method has problems such as low testing efficiency, long testing cycle, poor test repeatability, low scenario coverage rate, high safety risk, and high testing cost. Therefore, virtual testing and simulation have become important solutions for the development and testing of unmanned mining trucks. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a virtual test method and device for the autonomous driving of unmanned mining trucks, which can simulate the complex and changeable scenarios of mines and the vehicle data of unmanned mining trucks, and realize virtual testing through interaction testing with the autonomous driving control system, overcoming many technical problems existing in traditional real vehicle testing.

[0004] To achieve the above purpose, the present invention is implemented by the following technical solutions: In the first aspect, the present invention provides a virtual test method for the autonomous driving of unmanned mining trucks, including: Simulating the unmanned mining truck and its operating environment respectively to obtain a virtual vehicle and a virtual operating scenario; Simulating the communication between the virtual vehicle and the autonomous driving control system to obtain a virtual communication environment; Configuring the virtual vehicle and the virtual operating scenario to obtain a virtual test environment; Setting test start conditions, test end conditions, and test evaluation rules based on the virtual test environment; Controlling the virtual vehicle to complete the test process in the virtual test environment based on the virtual communication environment through the autonomous driving control system, and outputting a test result according to the test evaluation rule.

[0005] Optionally, simulating the unmanned mining truck includes: Simulating the unmanned mining truck by constructing a body kinematic model and a vehicle dynamics model; The body kinematic model is created on a one-to-one basis according to the body size of the unmanned mining truck and is used to simulate the actions and pose changes of the unmanned mining truck; The vehicle dynamics model is modularly created based on the vehicle system and characteristic parameters of the unmanned mining truck, and is used to simulate the response status information of the unmanned mining truck.

[0006] Optionally, simulating the unmanned mining truck further includes: Simulating the unmanned mining truck by constructing a perception sensor model; The perception sensor model is used to simulate the perception information collected by the unmanned mining truck about itself and the surrounding environment.

[0007] Optionally, simulating the operating environment of the unmanned mining truck includes: Constructing a virtual map, including: obtaining image data and point cloud data of a real mine, and constructing a scene map of the virtual operating scenario according to the image data and the point cloud data; the scene map is used to reproduce the road network characteristics and road surface characteristics of the real mine, including a standard road map, a mine loading area map, a mine unloading area map, and a mine transportation road area map; Constructing virtual static elements, including: obtaining static element data of a real mine, and constructing virtual static elements of the virtual operating scenario according to the static element data; the virtual static elements are used to reproduce the physical characteristics and spatio-temporal characteristics of the static elements of the real mine; Constructing virtual dynamic elements, including: loading virtual dynamic elements with motion attributes and collision attributes in the virtual operating scenario, where the motion attributes include a motion trajectory and a motion logic, and the collision attributes include a collision body.

[0008] Optionally, simulating the operating environment of the unmanned mining truck further includes: Constructing virtual meteorological elements, including: loading virtual meteorological elements with level attributes, weather attributes, and lighting attributes in the virtual operating scenario, where the weather attributes include rainy days, foggy days, and snowy days, and the lighting attributes include sunny days, few clouds, cloudy days, overcast days, and the lighting intensity at the current time.

[0009] Optionally, the automatic driving control system includes a control algorithm, a perception algorithm, and a planning algorithm; The perception algorithm is used to perform fusion processing on the perception information of the virtual vehicle; The planning algorithm is used to make action decisions and path planning according to the perception information after fusion processing; The control algorithm is used to generate control instructions according to the action decision result and the path planning result, and control the virtual vehicle.

[0010] Optionally, the virtual test includes a single-vehicle virtual test and a fleet scheduling virtual test; The virtual test of the vehicle includes: a single virtual vehicle completing the test process under the control of its automatic driving control system; The virtual test of the fleet scheduling includes: multiple virtual vehicles completing the test process under the control of their automatic driving control systems, and during the test process, the cloud scheduling system is combined to uniformly schedule the operation status of all virtual vehicles.

[0011] In a second aspect, the present invention provides an electronic device, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the above method.

[0012] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

[0013] In a fourth aspect, the present invention provides a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of the above method are implemented.

[0014] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The virtual test method and device for the automatic driving of unmanned mining trucks provided by the present invention realize the full process virtualization of test case creation, testing, and evaluation of unmanned mining trucks based on real environments and vehicle data by virtualizing the modeling of unmanned mining trucks and their operating environments and setting test conditions, enabling real-time online interaction among unmanned mining trucks, automatic driving control systems, cloud scheduling systems, and operating scenarios, and improving the test efficiency of unmanned mining trucks. Through virtualized modeling, dangerous and marginal scenarios of unmanned mining truck mine transportation can be efficiently created and reconstructed, improving the coverage rate of unmanned mining truck test scenarios; compared with the traditional real vehicle test method, the test workload is greatly reduced, the test cost is reduced, the test efficiency is improved, and the test cycle is shortened. Description of the Drawings

[0015] Figure 1 It is a schematic flowchart of the virtual test method for the automatic driving of unmanned mining trucks provided by the embodiments of the present invention. Detailed Embodiments

[0016] The present invention will be further described below with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be used to limit the protection scope of the present invention.

[0017] Embodiment 1:

[0018] As Figure 1As shown in the figure, an embodiment of the present invention provides a virtual test method for the autonomous driving of unmanned mining trucks, including the following steps: Step S1: Simulate the unmanned mining truck and its operating environment respectively to obtain a virtual vehicle and a virtual operating scenario.

[0019] (1) Specifically, in this embodiment, the simulation of the unmanned mining truck includes: 1) Simulate the unmanned mining truck by constructing a body kinematic model and a vehicle dynamics model to simulate the motion characteristics and dynamic characteristics of the actual vehicle, including vehicle (lateral, longitudinal, vertical) control and response state information such as starting, accelerating, decelerating, steering, braking, and vibration. Specifically, it includes two parts: a body kinematic model and a vehicle dynamics model.

[0020] The body kinematic model is created on a one-to-one basis according to the body size of the unmanned mining truck, and is used to simulate the actions and pose changes of the unmanned mining truck. The body kinematic model is driven by the response state information output by the vehicle dynamics model.

[0021] The vehicle dynamics model is created modularly based on the vehicle system and characteristic parameters of the unmanned mining truck, and is used to simulate the response state information of the unmanned mining truck. The vehicle system includes but is not limited to: power transmission system, braking system, steering system, suspension system, body system, and tire system.

[0022] 2) The perception sensors involved in the unmanned mining truck include five types: cameras, lidars, millimeter-wave radars, GPS, and IMUs. Simulate the perception sensors of the unmanned mining truck by constructing a perception sensor model; the perception sensor model is used to simulate the perception information collected by the unmanned mining truck about itself and the surrounding environment. The perception information includes but is not limited to: camera image data, lidar point cloud data, millimeter-wave radar target list data, GPS positioning data, and IMU vehicle attitude data.

[0023] (2) The simulation of the operating environment of the unmanned mining truck includes: 1) Construct a virtual map, including: obtaining image data and point cloud data of the real mine through oblique photography and real vehicle lidar scanning, and constructing a scene map of the virtual operating scenario according to the image data and point cloud data; the scene map is used to reproduce the road network characteristics and road surface characteristics of the real mine, including a standard road map, a mine loading area map, a mine unloading area map, and a mine transportation road area map. The standard road map includes but is not limited to straight roads, curved roads, ramps, intersections, and parking spaces with good road surfaces. The mine maps (mine loading area map, mine unloading area map, and mine transportation road area map) are 1:1 reconstructed three-dimensional map cut models of the real mine, including but not limited to rough roads in the mine, deformable soft soil roads, truck parking areas, obstacle roads, dynamically updatable waste dumping areas, and dynamically updatable areas for materials to be loaded, etc.

[0024] 2) Construct virtual static elements, including: obtaining the static element data of the real mine, and constructing the virtual static elements of the virtual operation scenario according to the static element data; the virtual static elements are used to reproduce the physical characteristics and spatio-temporal characteristics of the static elements of the real mine. The static element data includes, but is not limited to: videos, pictures, tables, documents, and digital methods such as image processing, 3D modeling, mesh repair, and mesh stitching are used to reproduce the physical characteristics (such as shape, size, mass, stiffness) and spatio-temporal characteristics (such as position, heading angle, attitude, illumination) of the static target elements, including but not limited to the stationary vehicles unique to the mine such as mining trucks, rollers, graders, water sprinklers, fuel tankers, pickups, etc., other static objects such as tumbleweeds, ruts, pits, plastic bags, cardboard boxes, tires, etc., as well as standing human models and stationary animal models.

[0025] 3) Construct virtual dynamic elements, including: loading virtual dynamic elements with motion attributes and collision attributes in the virtual operation scenario, where the motion attributes include motion trajectories and motion logics, and the collision attributes include collision bodies. Specifically, it includes typical dynamic vehicles in the mine, other moving objects (such as moving tumbleweeds, plastic bags, etc.), pedestrians, and moving animals. The processing of dynamic vehicles includes model import, adding collision bodies, adding wheel rolling pairs, mounting NPC scripts, and uploading model resources. The processing of dynamic pedestrians includes model import, mounting NPC scripts, adding collision bodies, adding animations, and resource upload. The initial positions, orientations, and speeds of the dynamic elements must be configurable.

[0026] 4) Construct virtual meteorological elements, including: loading virtual meteorological elements with level attributes, weather attributes, and illumination attributes in the virtual operation scenario, where the weather attributes include rainy days, foggy days, and snowy days, and the illumination attributes include sunny days, few clouds, cloudy days, overcast days, and the illumination intensity at the time.

[0027] The setting of the virtual meteorological elements needs to be based on the premise that the unmanned mining truck can perform operations. According to the level attributes and weather attributes, it can include: light rain, moderate rain, heavy rain; light fog, heavy fog, thick fog, strong thick fog; light snow, snow, moderate snow, heavy snow. In the actual application process, the staff can also specifically adjust the level attributes, weather attributes, and illumination attributes as needed for better testing.

[0028] Step S2: Simulate the communication between the virtual vehicle and the autonomous driving control system to obtain a virtual communication environment.

[0029] This embodiment conducts virtual testing for autonomous driving. The autonomous driving of the unmanned mining truck depends on the autonomous driving control system. Therefore, it is necessary to build a communication channel between the virtual vehicle and the autonomous driving control system to achieve the autonomous driving of the virtual vehicle.

[0030] Specifically, in this embodiment, the autonomous driving control system includes a control algorithm, a perception algorithm, and a planning algorithm; The perception algorithm is used to fuse and process the perception information of the virtual vehicle; The planning algorithm is used to make action decisions and path planning based on the perception information after fusion processing; The control algorithm is used to generate control instructions according to the action decision result and the path planning result, and control the virtual vehicle.

[0031] Step S3: Configure the virtual vehicle and the virtual operation scenario to obtain a virtual test environment.

[0032] Step S4: Set the test start condition, test end condition, and test evaluation rules based on the virtual test environment.

[0033] Set the test start condition and test end condition. For example, set the coordinate threshold of the virtual vehicle and the speed threshold of the virtual vehicle as the trigger condition for starting the use case, and set whether the virtual vehicle reaches the target area or the upper limit of the test duration as the test end condition.

[0034] Specifically, in this embodiment, the virtual test includes single-vehicle virtual test and fleet scheduling virtual test.

[0035] The single-vehicle virtual test includes: a single virtual vehicle completing the test process under the control of its autonomous driving control system.

[0036] In the single-vehicle virtual test, the autonomous driving control system sends control instructions, and the vehicle dynamics model of the virtual vehicle in the virtual test environment receives control instructions such as throttle, steering, braking, and gear and runs in the virtual map. The perception sensor models (cameras, lidars, millimeter-wave radars) configured on the unmanned mining truck perceive environmental information and generate raw data, which are sent to the perception algorithm of the autonomous driving control system in real time through ROS for fusion processing. The planning algorithm receives the perception fusion result output by the perception algorithm for decision-making and trajectory planning. The control algorithm receives the planned path and trajectory output by the planning algorithm and converts them into control instructions to be output to the vehicle dynamics model. The control algorithm also receives the vehicle state data feedback output by the virtual GPS / IMU model installed on the mining truck body model for control instruction correction, realizing the perception-regulation-control closed-loop virtual test. In this mode, autonomous obstacle avoidance and parking tests, autonomous obstacle bypassing driving tests, autonomous following vehicle tests, autonomous oncoming vehicle deceleration tests, retaining wall adaptive docking tests, excavator-truck cooperation tests, etc. can be carried out.

[0037] The single-vehicle virtual test can be used to conduct separate perception algorithm tests or regulation and control algorithm tests: In the perception algorithm test mode, only the perception algorithm module needs to be connected, and the vehicle kinematic model can move based on a preset trajectory. Further, control commands are output from the keyboard to the vehicle dynamics model to drive the vehicle kinematic model to move. In this mode, static obstacle perception tests, dynamic obstacle perception tests, rough / soft soil road surface perception tests, etc. can be carried out.

[0038] In the planning and control algorithm test mode, only the planning algorithm and the control algorithm need to be connected. Longitudinal speed following tests on straight roads, lateral trajectory following tests on curves, uphill and downhill speed following tests, rough road surface trajectory following tests, etc. can be carried out.

[0039] The virtual test of fleet scheduling includes: multiple virtual vehicles complete the test process under the control of their autonomous driving control systems. During the test process, the cloud scheduling system is combined to uniformly schedule the operation status of all virtual vehicles.

[0040] Compared with the single vehicle virtual test, the virtual test of fleet scheduling has one more scheduling task. This is mainly because the mine includes a loading area, an unloading area, and a transportation road area. In the loading area, the cloud scheduling system needs to schedule the entry and exit operations of the driverless mining trucks, such as the coordinates, orientations, etc. of the loading positions of each driverless mining truck; while in the unloading area, the cloud scheduling system assigns the unloading point coordinates, orientations, etc. to each driverless mining truck, and in the transportation road area, the driving path information is first sent by the cloud scheduling system to the driverless mining truck, and the driverless mining truck adjusts according to its autonomous driving control system during the actual driving process.

[0041] Relative to the single vehicle virtual test and the virtual test of fleet scheduling, the single vehicle test evaluation rules and the fleet scheduling test evaluation rules can be set accordingly.

[0042] Single vehicle test evaluation rules, for example: Single perception algorithm test cases, based on the perception results output by the perception algorithm, including but not limited to parameters such as the size, distance, speed, orientation, etc. of the perceived target objects (dynamic and static elements), and the upper limit of the deviation between the actual size or state parameter true value of the target object is used as the passing condition for the test case.

[0043] Single planning and control algorithm test cases, based on the lateral distance deviation, absolute distance deviation, speed deviation, upper limit of the docking position deviation, and time used between the actual driving trajectory and the planned trajectory as the passing condition for the test case.

[0044] The evaluation rules for single function test cases are based on the passing conditions specified in the single perception algorithm test and the single planning and control algorithm test cases, combined with whether there is a collision, whether the target position is reached, and whether the operation task is completed as the passing conditions.

[0045] Fleet scheduling test evaluation rules, for example: a) Bicycle formation test evaluation rules: Under the scheduling of the cloud dispatching system, the bicycle completes the full-process tasks of loading - transportation - unloading, and the entire route needs to include at least 3 interference simulation scenarios involving dynamic and static elements, and the types of dynamic and static elements are not less than 3. If the main vehicle under test successfully completes a single-cycle full-process test, it is considered passed; if there is one collision, it is considered failed.

[0046] Furthermore, single-cycle efficiency evaluation or fuel consumption evaluation can be added. The evaluation indicators are single-cycle time and single-cycle cumulative fuel consumption. Exceeding the defined single-cycle time threshold or single-cycle cumulative fuel consumption threshold is considered failed. Further still, an index interval can be defined for interpolation scoring.

[0047] b) The evaluation rules for multi-vehicle multi-formation tests, multi-vehicle multi-formation tests, manned and unmanned mixed formation tests, fixed vehicle dispatching tests, and dynamic vehicle dispatching tests are based on the bicycle formation test evaluation rules. For each formation's single-cycle test, test scenarios such as multi-main vehicle passing by, multi-main vehicle following, waiting for entry and exit, multi-main vehicle intersection, and multi-main vehicle passing through intersections are added. Furthermore, the evaluation indicators are increased to include formation operation efficiency (not limited to single-cycle time of the formation, daily earthwork volume transported, and daily number of transport trips), and formation cumulative fuel consumption (single-cycle cumulative fuel consumption of the formation, daily cumulative fuel consumption).

[0048] Step S5: Through the autonomous driving control system, control the virtual vehicle to complete the test process in the virtual test environment based on the virtual communication environment, and output the test result according to the test evaluation rules.

[0049] Based on the front-end interface, the execution status of virtual test cases can be viewed in real time, including the passability evaluation results of in-operation, passed, and failed cases. Furthermore, the scoring results based on quantitative evaluation indicators can be viewed.

[0050] In summary, the embodiments of the present invention can simulate complex and changeable scenarios in mines, and realize the dynamic interaction of unmanned mining trucks, mining operation environments, autonomous driving control systems, and cloud dispatching systems, meeting the online scenario simulation test requirements of single-vehicle tests and fleet tests. Compared with traditional real-vehicle tests, it has great advantages.

[0051] Embodiment 2:

[0052] Based on the virtual test method for autonomous driving of unmanned mining trucks provided in Embodiment 1, an embodiment of the present invention provides an electronic device, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the above method.

[0053] Embodiment 3:

[0054] Based on the virtual test method for the autonomous driving of unmanned mining trucks provided in Embodiment 1, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the above method are implemented.

[0055] Embodiment 4:

[0056] Based on the virtual test method for the autonomous driving of unmanned mining trucks provided in Embodiment 1, an embodiment of the present invention provides a computer program product, including a computer program / instructions. When the computer program / instructions are executed by a processor, the steps of the above method are implemented.

[0057] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0059] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the specified functions in Figure 1One process or multiple processes and / or boxes Figure 1 Steps of the functions specified in one box or multiple boxes.

[0061] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A virtual testing method for autonomous driving of an unmanned mining truck, characterized in that: include: The unmanned mining truck and its operating environment are simulated to obtain a virtual vehicle and a virtual operating scene; Simulating the communication between the virtual vehicle and the automatic driving control system to obtain a virtual communication environment; Configuring the virtual vehicle and the virtual operation scene to obtain a virtual test environment; Setting test start conditions, test end conditions and test evaluation rules based on the virtual test environment; The automatic driving control system controls the virtual vehicle to complete the test process in the virtual test environment based on the virtual communication environment, and outputs the test results according to the test evaluation rules.

2. The virtual testing method for autonomous driving of unmanned mining trucks according to claim 1 is characterized in that: The simulation of unmanned mining trucks includes: The unmanned mining truck is simulated by constructing the vehicle body kinematics model and vehicle dynamics model; The vehicle body kinematic model is created based on the one-to-one body size of the unmanned mining truck and is used to simulate the movement and posture changes of the unmanned mining truck; The vehicle dynamics model is modularly created based on the vehicle system and characteristic parameters of the unmanned mining truck, and is used to simulate the response state information of the unmanned mining truck.

3. The virtual testing method for autonomous driving of unmanned mining trucks according to claim 1 is characterized in that: The simulation of unmanned mining trucks also includes: Simulate the unmanned mining truck by building a perception sensor model; The perception sensor model is used to simulate the unmanned mining truck to collect perception information about itself and its surrounding environment.

4. The virtual testing method for autonomous driving of unmanned mining trucks according to claim 1 is characterized in that: The simulation of the operating environment of the unmanned mining truck includes: Constructing a virtual map, including: acquiring image data and point cloud data of a real mine, and constructing a scene map of the virtual operation scene according to the image data and the point cloud data; the scene map is used to reproduce the road network characteristics and road surface characteristics of the real mine, including a standard road map, a mine loading area map, a mine unloading area map, and a mine transportation road area map; Constructing virtual static elements, including: acquiring static element data of a real mine, and constructing virtual static elements of the virtual operation scene according to the static element data; the virtual static elements are used to reproduce the physical characteristics and spatiotemporal characteristics of the static elements of the real mine; Constructing a virtual dynamic element includes: loading a virtual dynamic element having motion attributes and collision attributes in the virtual operation scene, wherein the motion attributes include motion trajectories and motion logics, and the collision attributes include collision bodies.

5. The virtual testing method for autonomous driving of unmanned mining trucks according to claim 1 is characterized in that: The simulation of the operating environment of the unmanned mining truck also includes: Constructing a virtual meteorological element includes: loading a virtual meteorological element with level attributes, weather attributes and lighting attributes in the virtual operation scene, wherein the weather attributes include rainy days, foggy days and snowy days, and the lighting attributes include sunny days, few clouds, cloudy days, overcast days and the light intensity at the time.

6. The virtual testing method for autonomous driving of unmanned mining trucks according to claim 1 is characterized in that: The autonomous driving control system includes a control algorithm, a perception algorithm and a planning algorithm; The perception algorithm is used to perform fusion processing on the perception information of the virtual vehicle; The planning algorithm is used to make action decisions and path planning based on the fused perception information; The control algorithm is used to generate control instructions according to the action decision results and the path planning results, and control the virtual vehicle.

7. The virtual testing method for autonomous driving of unmanned mining trucks according to claim 1 is characterized in that: The virtual test includes a single vehicle virtual test and a fleet scheduling virtual test; The single-vehicle virtual test includes: a single virtual vehicle completes a test process under the control of its automatic driving control system; The fleet scheduling virtual test includes: a plurality of the virtual vehicles complete a test process under the control of their automatic driving control systems, and during the test process, the operating status of all the virtual vehicles is uniformly scheduled in conjunction with a cloud scheduling system.

8. An electronic device, characterized in that: including processor and storage medium; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images