Semi-physical simulation test method and platform for automatic driving and electronic equipment

Abstract

The embodiment of the invention provides a semi-physical simulation test method and platform for automatic driving, electronic equipment and a computer readable storage medium, and relates to the field of automatic driving. The method comprises the following steps: receiving a test instruction for a target test scene; a target test case matched with the target test scene is determined from a preset case library, the test case is constructed according to data when the vehicle runs in the corresponding real environment, and a control instruction of the vehicle in each time step in the virtual environment of the target test case is generated through an automatic driving algorithm; and updating data of each time step when the vehicle runs in the virtual environment according to the control instruction, determining a difference between the data of the vehicle in the virtual environment in each time step and the data of vehicle running in the real environment, and determining a test result of an automatic driving algorithm. According to the embodiment of the invention, a mine scene can be simulated more truly, and a test environment which is highly real and high in cost effectiveness is provided.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology. Specifically, the present application relates to a semi-physical simulation test platform, method, electronic device, computer-readable storage medium and computer program product for autonomous driving. Background Art

[0002] Existing testing methods for autonomous driving are mostly based on virtual testing or real vehicle testing, which have many problems.

[0003] The virtual test scenarios are too ideal and cannot truly reflect the actual control effects of autonomous vehicles, especially in open-pit mines where the road and environmental conditions are more severe. Actual vehicle testing involves building a site, drawing maps, running actual vehicles, etc., and directly testing the actual vehicle control algorithm, which may pose a risk of loss of control. It also requires a lot of manpower and material resources, greatly increasing the cost of testing. Summary of the invention

[0004] The embodiments of the present application provide a semi-physical simulation test platform, method, electronic device, computer-readable storage medium and computer program product for autonomous driving, which can solve the above-mentioned problems of the prior art. The technical solution is as follows: According to one aspect of an embodiment of the present application, a semi-physical simulation test method for autonomous driving is provided, the method comprising: receiving test instructions for a target test scenario; Determine a target test case matching the target test scenario from a preset test case library, wherein the test case library includes a plurality of test cases, and the test case is generated according to first sampling data when the vehicle is driving in a corresponding real environment; Iteratively executing a first operation based on the target test case by the autonomous driving algorithm until a test end condition is met, and determining a test result of the autonomous driving algorithm according to a first difference at each time step; The first operation includes: obtaining the second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step; The first difference is the difference between the first sampling data and the second sampling data at the corresponding time step.

[0005] In some optional embodiments, the second sampling data of the first time step of the vehicle in the virtual environment is rendered according to the test case; The second sampling data of the vehicle in the virtual environment at a non-first time step is rendered according to the test case and the control instruction and the second sampling data of the vehicle at a previous time step of the non-first time step.

[0006] In some optional embodiments, the method further comprises: Receiving first sampling data when the vehicle is traveling in a real environment sent by a vehicle-mounted terminal deployed on the vehicle; Determine a corresponding test scenario according to the first sampling data; If it is determined that the test case library has stored a test case matching the test scenario, updating the test case matching the test scenario according to the first sampling data; If it is determined that the first test case of the test scenario is not stored in the use case library, a test case matching the test scenario is generated according to the first sampling data.

[0007] In some optional embodiments, the method further comprises: A visualization interface is displayed, where the visualization interface is used to display at least one of the test instructions, the use case library, the second sampling data of at least one time step, and the test results.

[0008] In some optional implementations, the sampled data includes environmental information and vehicle state information of the vehicle in the corresponding environment, the environmental information includes at least position information and heading information, and the vehicle state information includes at least speed information; The first difference includes at least one of a position difference, a heading difference, and a speed difference.

[0009] In some optional embodiments, the test scenario is related to at least one of site information, vehicle speed level information, and road type; The site information of each test scenario is a mine.

[0010] According to another aspect of an embodiment of the present application, a semi-physical simulation test platform for autonomous driving is provided, the platform comprising: A cloud module, configured to receive a test instruction for a target test scenario, and determine a target test case matching the target test scenario from a preset test case library, wherein the test case library includes a plurality of test cases, and the test case is generated according to first sampling data when a vehicle is driving in a corresponding real environment; a computing module, configured to iteratively perform a first operation based on the test case through the autonomous driving algorithm until a test end condition is met, and determine a test result of the autonomous driving algorithm according to a first difference at each time step; The first operation includes: obtaining the second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step; The first difference is the difference between the first sampling data and the second sampling data at the corresponding time step.

[0011] In some optional implementations, it also includes a bottom layer simulation module; Wherein, the second sampling data of the first time step of the vehicle in the virtual environment is rendered by the underlying simulation module according to the test case; The second sampling data of the vehicle in the virtual environment at a non-first time step is rendered by the underlying simulation module according to the test case and the control instructions and second sampling data of the vehicle at a previous time step of the non-first time step.

[0012] In some optional implementations, the cloud module is also used to: Receiving first sampling data when the vehicle is traveling in a real environment sent by a vehicle-mounted terminal deployed on the vehicle; Determine a corresponding test scenario according to the first sampling data; If it is determined that the test case library has stored a test case matching the test scenario, updating the test case matching the test scenario according to the first sampling data; If it is determined that the first test case of the test scenario is not stored in the use case library, a test case matching the test scenario is generated according to the first sampling data.

[0013] In some optional implementations, the test platform further includes: A visualization interface module is used to display a visualization interface, wherein the visualization interface is used to display at least one of the test instructions, the use case library, the second sampling data of at least one time step, and the test results.

[0014] In some optional implementations, the test platform further includes: A communication module, used for data transmission between the computing module, the visualization interface module, the cloud module and the underlying simulation module; The management module is used to collect data from the computing module, the cloud module and the underlying simulation module and transmit the data to the visualization interface module so that the visualization interface module displays a visualization interface.

[0015] According to another aspect of an embodiment of the present application, an electronic device is provided. The electronic device includes a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above method.

[0016] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0017] According to one aspect of an embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0018] The beneficial effects of the technical solution provided by the embodiment of the present application are: By receiving the test instructions for the target test scenario, the tester does not need to perform complex configurations, but only needs to input the target test scenario to start the test, which reduces the difficulty of getting started with the test. The target test case matching the target test scenario is determined from the preset case library. The case library includes multiple test cases, and the test case is generated according to the first sampling data of the vehicle when driving in the corresponding real environment. Since the test case is generated based on the real running data, the test scenario can be simulated more realistically, and at least the vehicle only needs to actually drive once in the real scenario to generate a test scenario corresponding to the real scenario, and some parameters of the test scenario are randomly changed. By updating the test scenario, a new test scenario can be obtained, thereby providing a highly realistic and cost-effective test environment. The autonomous driving algorithm iteratively executes the first operation based on the target test case until the test end condition is met. The test result of the autonomous driving algorithm is determined according to the first difference of each time step. The first operation includes: obtaining the second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, executing the control instruction to enter the next time step, and the first difference is the difference between the first sampling data and the second sampling data of the corresponding time step. The control and testing of the vehicle in the virtual environment can be effectively realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0020] Figure 1 A schematic diagram of the architecture of a semi-physical simulation test system for autonomous driving provided in an embodiment of the present application; Figure 2A schematic diagram of a process flow of a semi-physical simulation test method for autonomous driving provided in an embodiment of the present application; Figure 3 A schematic diagram of the relationship between rendering sampling data and computing control instructions provided in an embodiment of the present application; Figure 4 A schematic diagram of a process for updating a test case provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of a semi-physical simulation test platform for autonomous driving provided in an embodiment of the present application; Figure 6 A schematic diagram of the composition of a test case provided in an embodiment of the present application; Figure 7 A schematic diagram of the framework of the test platform provided in the embodiment of the present application; Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The embodiments of the present application are described below in conjunction with the drawings in the present application. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0022] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "an" and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application refer to that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude the implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the technical field. It should be understood that when we call an element "connected" or "coupled" to another element, the one element can be directly connected or coupled to the other element, or it can refer to that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used here may include wireless connection or wireless coupling. The term "and / or" used here indicates at least one of the items defined by the term, for example, "A and / or B" can be implemented as "A", or as "B", or as "A and B".

[0023] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0024] First, several terms involved in this application are introduced and explained: An autonomous driving system is a system that uses advanced communication, computer, network and control technologies to enable vehicles to drive automatically without human intervention, perceive the surrounding environment and make driving decisions. According to the different levels of autonomous driving technology, it can be divided into multiple levels, such as L0 (no automation), L1 (driving assistance), L2 (partial automation), L3 (conditional automation), L4 (high automation) and L5 (full automation).

[0025] Existing methods for autonomous driving simulation testing are mostly based on virtual testing or real vehicle testing, and there are many problems.

[0026] The virtual test scenarios are too ideal and cannot truly reflect the actual control effects of autonomous vehicles, especially in open-pit mines where road and environmental conditions are more severe. Relying solely on virtual simulated terrain cannot effectively fit the actual environment.

[0027] Actual vehicle testing involves building a site, drawing maps, running actual vehicles, etc., and directly testing the actual vehicle control algorithm, which may pose a risk of loss of control. It also requires a lot of manpower and material resources, greatly increasing the cost of testing.

[0028] Current testing methods for autonomous driving often lack sufficient flexibility and scalability, and are difficult to adapt to the changing mining environment.

[0029] The semi-physical simulation test method, device, electronic device, computer-readable storage medium and computer program product for autonomous driving provided in this application are intended to solve the above-mentioned technical problems of the prior art.

[0030] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application. It should be noted that the following embodiments can refer to, draw on or combine with each other, and the same terms, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0031] For example, see Figure 1 , Figure 1 It is a schematic diagram of the architecture of the semi-physical simulation test system 100 for autonomous driving provided in an embodiment of the present application. In order to support the application of autonomous driving algorithm testing in a virtual scene, the terminal device 400 is connected to the server 200 through the network 300. The network 300 can be a wide area network or a local area network, or a combination of the two.

[0032] In some embodiments, taking the electronic device as the terminal device as an example, the semi-physical simulation test method for autonomous driving provided in the embodiments of the present application can be implemented by the terminal device alone. For example, when it is necessary to generate rain and snow special effects in a virtual scene (for example, the weather system controls the weather in the virtual scene to change from sunny to rainy), it can be achieved by Figure 1 The terminal device 400 shown in the figure separately obtains the test instructions displayed in the human-computer interaction interface of the client 410 (for example, a test application in a stand-alone version / offline mode), and determines a target test case matching the target test scenario from a preset use case library, wherein the use case library includes multiple test cases, and the test case is generated according to the first sampling data of the vehicle when driving in the corresponding real environment; the first operation is iteratively performed based on the target test case by the autonomous driving algorithm until the test end condition is met, and the test result of the autonomous driving algorithm is determined according to the first difference of each time step; wherein the first operation includes: obtaining the second sampling data and the first difference of the vehicle at the current time step in the virtual environment, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step; the first difference is the difference between the first sampling data and the second sampling data of the corresponding time step.

[0033] In other embodiments, the semi-physical simulation test method for autonomous driving provided in the embodiments of the present application can also be performed by Figure 1 The terminal device 400 and the server 200 shown in FIG. 4 are implemented in collaboration. For example, a client 410 (e.g., a network version of a test application) is running on the terminal device 400. When a semi-physical simulation test is required, the client 410 sends a test instruction for a target test scenario to the server 200 through the network 300, so that the server 200 determines a target test case matching the target test scenario from a preset case library, wherein the case library includes a plurality of test cases, and the test case is generated according to the first sampling data of the vehicle when driving in the corresponding real environment; the first operation is iteratively performed based on the target test case by the automatic driving algorithm until the test end condition is met, and the test result of the automatic driving algorithm is determined according to the first difference of each time step; wherein the first operation includes: obtaining the second sampling data and the first difference of the vehicle at the current time step in the virtual environment, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step; the first difference is the difference between the first sampling data and the second sampling data at the corresponding time step.

[0034] In some embodiments, the embodiments of the present application can be implemented with the help of cloud technology (Cloud Technology). Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network within a wide area network or a local area network to achieve data calculation, storage, processing, and sharing.

[0035] Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, and application technology based on the cloud computing business model. It can form a resource pool that can be used on demand and is flexible and convenient. Cloud computing technology will become an important support. The background services of the technical network system require a large amount of computing and storage resources.

[0036] For example, Figure 1 The server 200 shown in the figure can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network), and big data and artificial intelligence platforms. The terminal device 400 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited to this. The terminal device 400 and the server 200 can be directly or indirectly connected by wired or wireless communication, which is not limited in the embodiments of the present application.

[0037] In other embodiments, the terminal device 400 or the server 200 can implement the method for generating rain and snow special effects in the virtual scene provided by the embodiment of the present application by running a computer program. For example, the computer program can be a native program or software module in the operating system; it can be a native application (APP, Application), that is, a program that needs to be installed in the operating system to run, such as a game application (corresponding to the client 410 above); it can also be a small program, that is, a program that can be run only after being downloaded to a browser environment; it can also be a small program that can be embedded in any APP, such as a small program component embedded in a game application, wherein the small program component can be controlled to run or closed by the user. In short, the above-mentioned computer program can be an application, module or plug-in in any form.

[0038] The present application provides a semi-physical simulation test method for autonomous driving. Figure 2 As shown, the method includes: S101. Receive a test instruction for a target test scenario.

[0039] The embodiment of the present application may provide an operation interface for the tester to configure the target test scenario. The site of the target test scenario of the embodiment of the present application may be a mine, which covers the non-selectivity, timeliness and dynamics of geological conditions, the disturbance and destructiveness of the geological environment, the diversity of geological disasters, the diversity of mining methods, the particularity of the mining environment, and the wide distribution of locations. These characteristics together constitute the complexity and challenge of conducting autonomous driving tests in mines.

[0040] It should be noted that for the test scenario of the mine, the vehicle in the embodiment of the present application refers to a mine car. Mine car: Mainly used in specific scenarios such as mines and engineering projects, usually operating in non-road environments, such as narrow-gauge railways inside mines or rugged mine roads. These environments often have high requirements for the durability, carrying capacity and off-road performance of the vehicle. Compared with ordinary vehicles, mine cars are usually larger in size, wider in body, and more complicated to operate. The automatic driving algorithm for mine cars in the embodiment of the present application is different from the automatic driving algorithm for ordinary vehicles, and the differences are mainly reflected in the following aspects: 1. Differences in usage environment Mining cars are mainly used in specific scenarios such as mines and engineering projects. These environments are usually complex and changeable, including narrow mine tunnels, rugged roads, and possible obstacles and danger sources. The mining car autonomous driving algorithm needs to adapt to this complex environment and have strong perception, decision-making and execution capabilities to ensure the safe and efficient operation of the mining car.

[0041] 2. Differences in functional requirements In addition to simulating the driving of the vehicle, the mine cart autonomous driving algorithm also needs to simulate automatic loading, unloading, driving, obstacle avoidance and collaborative operation with other mine carts.

[0042] 3. Differences in Algorithm Design Characteristics The mine car autonomous driving algorithm usually needs to consider factors such as the heavy load characteristics, driving speed and working environment of the mine car. When designing the algorithm, special attention should be paid to the stability and safety of the vehicle to ensure that the mine car can still maintain stable operation under heavy load and complex environment. The mine car autonomous driving algorithm also needs to have strong perception capabilities to deal with obstacles and dangers in the mine. This is usually achieved by fusing multiple sensor data (such as lidar, camera, millimeter wave radar, etc.).

[0043] In the automatic driving algorithm for the mine car, the embodiment of the present application pays more attention to the simulation of balance and stability than ordinary vehicles. For example, the accelerator cannot be stepped on repeatedly or the position of the accelerator cannot be changed suddenly when starting. When simulating the weight of the mine car, the weight and distribution of the goods are simulated in a fine-grained manner to avoid overloading and unbalanced loading, etc. It should be understood that the vehicles referred to in the subsequent embodiments of the present application can all refer to mine cars.

[0044] In some embodiments, in addition to selecting a location, the target test scene can also select vehicle information, weather information, etc. For example, a target test scene can be: a mountain range in Kunming, a medium-sized SUV (SUV model with a body length between 4600mm and 4800mm and a wheelbase between 2700mm and 2900mm) and rainy and snowy weather. This example uses vehicle length and wheelbase to represent vehicle information. In some embodiments, other information can also be used to represent it, such as the speed level. The speed level can reflect the road conditions of the site to a certain extent. The higher the speed level, the better the road conditions, and vice versa.

[0045] After the tester completes the configuration of the target test scenario, the system can generate test instructions for the target test scenario.

[0046] S102: Determine a target test case that matches the target test scenario from a preset test case library, wherein the test case library includes a plurality of test cases, and the test case is generated according to first sampling data when a vehicle is driving in a corresponding real environment.

[0047] The embodiment of the present application can generate multiple test cases in advance. Different from the existing simulation test that completely relies on the imagination of the cartographer to generate test cases, the test cases in the embodiment of the present application are all generated based on the first-used data when the vehicle is driving in a real environment. Since the test cases are generated based on real operating data, the test scenarios can be simulated more realistically, and at least the vehicle only needs to actually drive once in the real scenario to generate a test scenario corresponding to the real scenario, and the test scenario can be used to test different autonomous driving algorithms, thereby realizing the reuse of test scenarios.

[0048] In some embodiments, a new test scenario may be obtained by updating some parameters of the test scenario in a random manner, thereby providing a highly realistic and cost-effective test environment.

[0049] Specifically, the present application deploys an on-board terminal on the vehicle, and the on-board terminal performs real-time sampling when the vehicle is driving in a real environment. The first sampling information of the embodiment of the present application may include environmental information and vehicle status information. The environmental information may include road condition information and road type. In some embodiments, the road type includes U-turn, S-turn, straight line, herringbone, combination scene, etc.

[0050] The vehicle status information of the embodiment of the present application may include the distance between the vehicle and the vehicle next to it, vehicle speed, acceleration, real-time position, heading, etc., and may also include more fine-grained information, such as steering wheel angle, brake pedal opening, motor torque, gear position, handbrake status, etc., which is not specifically limited in the embodiment of the present application.

[0051] After obtaining the first sampling data of a vehicle during a driving process, the embodiment of the present application can further analyze the matching test scenario, so as to establish a correspondence between the test scenario and the test case after generating a test case based on the first sampling data.

[0052] The test case of the embodiment of the present application describes in detail the test environment information and vehicle status information. It can be understood that the vehicle status information described in the test case is the vehicle status information of the vehicle in the corresponding real environment. On the one hand, the autonomous driving algorithm can refer to the vehicle status information to output the control instructions of the vehicle in the virtual environment. On the other hand, the vehicle status information described in the test case can also be used as reference data for testing the autonomous driving algorithm.

[0053] After selecting the target test cases that match the target test scenarios from the use case library, the embodiment of the present application iteratively executes the first operation on the target test cases through the autonomous driving algorithm. The test termination condition of the embodiment of the present application may be that the vehicle reaches the end point in the virtual environment, or it may be the duration of not meeting / achieving the test requirements, or it may be any time when the tester believes that the test can be terminated. The embodiment of the present application does not make any specific limitation.

[0054] The iterative execution of the first operation in the embodiment of the present application refers to executing the first operation at each time step in the test process. The embodiment of the present application does not limit the length of the time step, for example, it can be 1 millisecond, 1 second, 3 seconds, etc.

[0055] The first operation of the embodiment of the present application includes: obtaining second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step.

[0056] The embodiment of the present application obtains second sampling information of the vehicle in the current time step in the virtual environment, that is, the environmental information and vehicle status information of the vehicle in the current time step in the virtual environment, analyzes the second sampling information through the automatic driving algorithm, determines the control instruction to be executed by the vehicle at the current time step, and then executes the control instruction to enter the next time step. The embodiment of the present application realizes control and testing of the vehicle in the virtual environment by iteratively executing the first operation.

[0057] It should be noted that the first difference in the embodiment of the present application refers to the difference between the first sampled data and the second sampled data at the corresponding time step. That is to say, at each time step, the embodiment of the present application compares the sampled data of the vehicle in the real environment and the virtual environment to obtain the difference between the vehicle under the control of the autonomous driving algorithm and the actual driving, and uses the difference to evaluate the autonomous driving algorithm.

[0058] The semi-physical simulation test method for autonomous driving provided in the embodiment of the present application, by receiving the test instructions for the target test scenario, realizes that the test personnel do not need to perform complex configuration, but only need to input the target test scenario to start the test, thereby reducing the difficulty of getting started with the test, and determining the target test case matching the target test scenario from a preset case library, the case library including multiple test cases, the test case being generated based on the first sampling data of the vehicle driving under the corresponding real environment, and because the test case is generated based on the real running data, the test scenario can be simulated more realistically, and at least only the vehicle needs to actually drive in the real scenario once to generate a test scenario corresponding to the real scenario, and part of the test scenario By updating the sub-parameters in a randomly changing manner, a new test scenario can be obtained, thereby providing a highly realistic and cost-effective test environment. The autonomous driving algorithm iteratively executes the first operation based on the target test case until the test end condition is met. The test result of the autonomous driving algorithm is determined according to the first difference of each time step. The first operation includes: obtaining the second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step. The first difference is the difference between the first sampling data and the second sampling data of the corresponding time step, which can effectively realize the control and testing of the vehicle in the virtual environment.

[0059] Based on the above embodiment, as an optional embodiment, the second sampling data of the first time step of the vehicle in the virtual environment is rendered according to the test case; The second sampling data of the vehicle in the virtual environment at a non-first time step is rendered according to the test case and the control instruction and the second sampling data of the vehicle in a previous time step of the non-first time step.

[0060] It should be noted that the test case includes the environmental information of the virtual environment. In the first time step, since the vehicle has not yet set off in the virtual environment, the vehicle state is considered to be empty, and the vehicle is located at the starting point of the virtual environment, so it is only necessary to render the second sampling data of the first time step based on the environmental information in the test case. The second sampling data of the first time step can also only include the environmental information of the vehicle in the virtual environment, such as positioning, weather, temperature, visibility, etc. Further, for non-first time steps, since the vehicle is already in motion, in addition to rendering the environmental information of the vehicle in the virtual environment, it is also necessary to render the vehicle state information, such as rendering the steering angle of the steering wheel, rendering the opening of the pedals, rendering the motor, rendering the gear controller, etc. and information related to the vehicle's driving.

[0061] See also Figure 3, which exemplarily shows a schematic diagram of the relationship between rendering sampling data and calculating control instructions in an embodiment of the present application. In general, the embodiment of the present application renders the second sampling data based on the test case, generates control instructions according to the second sampling data, and then acts on the test case according to the second sampling data and the control instructions to generate the second sampling data for the next time step. Specifically, for the first time step, the second sampling data of the first time step is first rendered according to the test case, and then the control instruction to be executed for the first time step is generated according to the second sampling information of the first time step, the control instruction is executed, and the second time step is entered. Then, in the second time step, according to the executed control instruction, the distance, direction and other information of the vehicle in the virtual environment are determined, and the position of the second time step is determined in combination with the first sampling data of the first time step (mainly environmental information), and so on. Further, the information that needs to be rendered at the position of the vehicle in the second time step is determined from the environmental information of the test case. For example, if it is determined according to the test case that there is a mud pit at the position of the vehicle, a mud pit needs to be rendered. The embodiment of the present application renders the second sampling data of the current time step according to the control instruction and the second sampling data of the previous time step, combined with the test case, and then the control instruction to be executed in the current time step is obtained through the automatic driving algorithm from the second sampling data of the current time step, and the test is completed by continuously iterating the time step.

[0062] Based on the above embodiments, as an optional embodiment, see Figure 4 The embodiment of the present application further includes the step of updating the test cases in the test case library, specifically: S201, receiving first sampling data of a vehicle driving in a real environment sent by a vehicle-mounted terminal deployed on the vehicle; S202: Determine a corresponding test scenario according to the first sampling data; S203a, if it is determined that the test case library has stored a test case matching the test scenario, updating the test case matching the test scenario according to the first sampling data; S203b: If it is determined that the first test case of the test scenario is not stored in the use case library, generate a test case matching the test scenario according to the first sampling data.

[0063] In an embodiment of the present application, an on-board terminal is deployed in a vehicle. When the vehicle is driving in a real environment, the on-board terminal collects first sampling data of the vehicle while driving, and determines a corresponding test scenario based on the first sampling data. If it is determined that the use case library has stored a test case matching the test scenario, it means that a test case has been created for the test scenario before. In order to ensure the timeliness of the data, in an embodiment of the present application, the test case matching the test scenario in the use case library is updated with the most recently obtained first sampling data. If it is determined that the use case library has not yet stored a test case matching the test scenario, it means that the test scenario corresponding to the first sampling data is a brand new test scenario, so the test case matching the test scenario generated based on the first sampling data is stored in the use case library.

[0064] Based on the above embodiments, as an optional embodiment, in order to enable the tester to more intuitively grasp the dynamics of the test, the embodiment of the present application also includes: A visualization interface is displayed, where the visualization interface is used to display at least one of the test instructions, the use case library, the second sampling data of at least one time step, and the test results.

[0065] By providing a visual interface, displaying test instructions for testers to know the current test items, displaying a case library for testers to select related test cases, and displaying the second sampling data of only one time step for testers to know the environmental information and vehicle operation information of the vehicle in the virtual environment during the test, the embodiment of the present application provides a user-friendly interface for displaying key data and test effects of control algorithms during the test. The interface can be updated in real time to reflect the dynamic changes of the test.

[0066] Based on the above embodiments, as an optional embodiment, the test scenario is related to at least one of site information, vehicle speed level information and road type; the site information of each test scenario is a mine.

[0067] The present application embodiment provides a semi-physical simulation test platform for autonomous driving, such as Figure 5 As shown, the semi-physical simulation test platform for autonomous driving may include: a cloud module 201 and a computing module 202, wherein: A cloud module, configured to receive a test instruction for a target test scenario, and determine a target test case matching the target test scenario from a preset test case library, wherein the test case library includes a plurality of test cases, and the test case is generated according to first sampling data when a vehicle is driving in a corresponding real environment; The computing module is used to iteratively execute the first operation based on the test case through the autonomous driving algorithm until the test end condition is met, and determine the test result of the autonomous driving algorithm according to the first difference of each time step.

[0068] The first operation of the embodiment of the present application includes: obtaining the second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step, wherein the first difference is the difference between the first sampling data and the second sampling data at the corresponding time step.

[0069] The embodiment of the present application may provide an operation interface for the tester to configure the target test scenario. The site of the target test scenario of the embodiment of the present application may be a mine, which covers the non-selectivity, timeliness and dynamics of geological conditions, the disturbance and destructiveness of the geological environment, the diversity of geological disasters, the diversity of mining methods, the particularity of the mining environment, and the wide distribution of locations. These characteristics together constitute the complexity and challenge of conducting autonomous driving tests in mines.

[0070] In some embodiments, in addition to selecting a location, the target test scene can also select vehicle information, weather information, etc. For example, a target test scene can be: a mountain range in Kunming, a medium-sized SUV (SUV model with a body length between 4600mm and 4800mm and a wheelbase between 2700mm and 2900mm) and rainy and snowy weather. This example uses vehicle length and wheelbase to represent vehicle information. In some embodiments, other information can also be used to represent it, such as the speed level. The speed level can reflect the road conditions of the site to a certain extent. The higher the speed level, the better the road conditions, and vice versa.

[0071] After the tester completes the configuration of the target test scenario, the system can generate test instructions for the target test scenario.

[0072] The cloud module of the embodiment of the present application is responsible for collecting and storing the first sampled data of the vehicle in the real environment, including environmental parameters, vehicle status, etc. The cloud service is used to collect and store actual vehicle operation data, and the test case library is regularly updated to reflect the latest changes in the mine environment. The cloud module has data encryption and secure storage functions to protect the integrity and privacy of the data.

[0073] The embodiment of the present application can generate multiple test cases in advance. Different from the existing simulation test that completely relies on the imagination of the cartographer to generate test cases, the test cases in the embodiment of the present application are all generated based on the first-used data when the vehicle is driving in a real environment. Since the test cases are generated based on real operating data, the test scenarios can be simulated more realistically, and at least the vehicle only needs to actually drive once in the real scenario to generate a test scenario corresponding to the real scenario, and the test scenario can be used to test different autonomous driving algorithms, thereby realizing the reuse of test scenarios.

[0074] In some embodiments, a new test scenario may be obtained by updating some parameters of the test scenario in a random manner, thereby providing a highly realistic and cost-effective test environment.

[0075] Specifically, the present application deploys an on-board terminal on the vehicle, and the on-board terminal performs real-time sampling when the vehicle is driving in a real environment. The first sampling information of the embodiment of the present application may include environmental information and vehicle status information. The environmental information may include road condition information and road type. In some embodiments, the road type includes U-turn, S-turn, straight line, herringbone, combination scene, etc.

[0076] The vehicle status information of the embodiment of the present application may include the distance between the vehicle and the vehicle next to it, vehicle speed, acceleration, real-time position, heading, etc., and may also include more fine-grained information, such as steering wheel angle, brake pedal opening, motor torque, gear position, handbrake status, etc., which is not specifically limited in the embodiment of the present application.

[0077] After obtaining the first sampling data of a vehicle during a driving process, the embodiment of the present application can further analyze the matching test scenario, so as to establish a correspondence between the test scenario and the test case after generating a test case based on the first sampling data.

[0078] The test case of the embodiment of the present application describes in detail the test environment information and vehicle status information. It can be understood that the vehicle status information described in the test case is the vehicle status information of the vehicle in the corresponding real environment. On the one hand, the autonomous driving algorithm can refer to the vehicle status information to output the control instructions of the vehicle in the virtual environment. On the other hand, the vehicle status information described in the test case can also be used as reference data for testing the autonomous driving algorithm.

[0079] The computing module of the embodiment of the present application is responsible for running the autonomous driving algorithm, which includes but is not limited to perception and positioning, path planning, obstacle avoidance, trajectory tracking control, etc. This module should have high-performance computing capabilities to process complex algorithms and large amounts of data.

[0080] After selecting the target test cases that match the target test scenarios from the use case library, the embodiment of the present application iteratively executes the first operation on the target test cases through the autonomous driving algorithm. The test termination condition of the embodiment of the present application may be that the vehicle reaches the end point in the virtual environment, or it may be the duration of not meeting / achieving the test requirements, or it may be any time when the tester believes that the test can be terminated. The embodiment of the present application does not make any specific limitation.

[0081] The iterative execution of the first operation in the embodiment of the present application refers to executing the first operation at each time step in the test process. The embodiment of the present application does not limit the length of the time step, for example, it can be 1 millisecond, 1 second, 3 seconds, etc.

[0082] The first operation of the embodiment of the present application includes: obtaining second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step.

[0083] The embodiment of the present application obtains second sampling information of the vehicle in the current time step in the virtual environment, that is, the environmental information and vehicle status information of the vehicle in the current time step in the virtual environment, analyzes the second sampling information through the automatic driving algorithm, determines the control instruction to be executed by the vehicle at the current time step, and then executes the control instruction to enter the next time step. The embodiment of the present application realizes control and testing of the vehicle in the virtual environment by iteratively executing the first operation.

[0084] It should be noted that the first difference in the embodiment of the present application refers to the difference between the first sampled data and the second sampled data at the corresponding time step. That is to say, at each time step, the embodiment of the present application compares the sampled data of the vehicle in the real environment and the virtual environment to obtain the difference between the vehicle under the control of the autonomous driving algorithm and the actual driving, and uses the difference to evaluate the autonomous driving algorithm.

[0085] The semi-physical simulation test platform for autonomous driving provided in the embodiment of the present application, by receiving test instructions for target test scenarios, realizes that the test personnel do not need to perform complex configurations, but only need to input the target test scenario to start the test, thereby reducing the difficulty of getting started with the test, and determining the target test case matching the target test scenario from a preset case library, the case library including multiple test cases, the test case being generated based on the first sampling data of the vehicle driving under the corresponding real environment, and because the test case is generated based on real operating data, the test scenario can be simulated more realistically, and at least the vehicle only needs to actually drive once in the real scenario to generate a test scenario corresponding to the real scenario, and part of the test scenario By updating the sub-parameters in a randomly changing manner, a new test scenario can be obtained, thereby providing a highly realistic and cost-effective test environment. The autonomous driving algorithm iteratively executes the first operation based on the target test case until the test end condition is met. The test result of the autonomous driving algorithm is determined according to the first difference of each time step. The first operation includes: obtaining the second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step. The first difference is the difference between the first sampling data and the second sampling data of the corresponding time step, which can effectively realize the control and testing of the vehicle in the virtual environment.

[0086] Based on the above embodiments, as an optional embodiment, the semi-physical simulation test platform further includes a bottom layer simulation module; Wherein, the second sampling data of the first time step of the vehicle in the virtual environment is rendered by the underlying simulation module according to the test case; The second sampling data of the vehicle in the virtual environment at a non-first time step is rendered by the underlying simulation module according to the test case and the control instructions and second sampling data of the vehicle at a previous time step of the non-first time step.

[0087] It should be noted that the test case includes the environmental information of the virtual environment. In the first time step, since the vehicle has not yet set off in the virtual environment, the vehicle state is considered to be empty, and the vehicle is located at the starting point of the virtual environment, so it is only necessary to render the second sampling data of the first time step based on the environmental information in the test case. The second sampling data of the first time step can also only include the environmental information of the vehicle in the virtual environment, such as positioning, weather, temperature, visibility, etc. Further, for non-first time steps, since the vehicle is already in motion, in addition to rendering the environmental information of the vehicle in the virtual environment, it is also necessary to render the vehicle state information, such as rendering the steering angle of the steering wheel, rendering the opening of the pedals, rendering the motor, rendering the gear controller, etc. and information related to the vehicle's driving.

[0088] The underlying simulation module of the embodiment of the present application includes an embedded device, a test case library and a chassis simulation module, which simulates dynamic changes in the mining environment through high-precision devices and actuators. The embedded device is used to receive test cases sent by the cloud module, and parse specific test cases according to the data in the test case library, and issue specific test operation feedback. The test case library contains test cases for various mining scenarios, and each test case describes in detail parameters such as environmental conditions and vehicle status. The composition diagram of the test case is shown in the figure below. Figure 6 As shown in the figure, road conditions, vehicle speed, road type, etc. are the types of test cases. The specific test data is composed of data from each module in the database, including perception data, planning data, chassis data, positioning data, map data, prediction data, supervision data and V2V data. The planning data is the trajectory data given by the decision planning algorithm, the prediction data is the trajectory prediction data given by the prediction algorithm, and the supervision data is the supervision data for all modules, including the data reported by each module to the management module.

[0089] The chassis simulation module is used to receive control instructions from the computing module and simulate the physical behavior of the vehicle, such as steering, acceleration, braking, etc., to provide a test environment close to reality.

[0090] Based on the above embodiments, as an optional embodiment, the cloud module is also used for: Receiving first sampling data when the vehicle is traveling in a real environment sent by a vehicle-mounted terminal deployed on the vehicle; Determine a corresponding test scenario according to the first sampling data; If it is determined that the test case library has stored a test case matching the test scenario, updating the test case matching the test scenario according to the first sampling data; If it is determined that the first test case of the test scenario is not stored in the use case library, a test case matching the test scenario is generated according to the first sampling data.

[0091] In an embodiment of the present application, an on-board terminal is deployed in a vehicle. When the vehicle is driving in a real environment, the on-board terminal collects first sampling data of the vehicle while driving, and determines a corresponding test scenario based on the first sampling data. If it is determined that the use case library has stored a test case matching the test scenario, it means that a test case has been created for the test scenario before. In order to ensure the timeliness of the data, in an embodiment of the present application, the test case matching the test scenario in the use case library is updated with the most recently obtained first sampling data. If it is determined that the use case library has not yet stored a test case matching the test scenario, it means that the test scenario corresponding to the first sampling data is a brand new test scenario, so the test case matching the test scenario generated based on the first sampling data is stored in the use case library.

[0092] The embodiment of the present application links the vehicle-mounted terminal and the cloud. The vehicle-mounted terminal runs real scenarios and provides test data with real data and diverse scenarios. It combines with the cloud module to transmit data back and parse it into specific test cases to ensure continuous updating of test data to adapt to changes in real scenarios, thereby ensuring the timeliness and diversity of test cases.

[0093] Based on the above embodiments, as an optional embodiment, the platform further includes: A visualization interface module is used to display a visualization interface, wherein the visualization interface is used to display at least one of the test instructions, the use case library, the second sampling data of at least one time step, and the test results.

[0094] The visualization interface module of the embodiment of the present application provides a user-friendly interface for displaying key data during the test and the execution effect of the autonomous driving algorithm, and the interface can be updated in real time to reflect the dynamic changes of the test.

[0095] Based on the above embodiments, as an optional embodiment, the platform further includes: The communication module is used for data transmission between the computing module, the visualization interface module, the cloud module and the underlying simulation module. The module supports high-speed and stable data communication to ensure the real-time and accuracy of the test.

[0096] The management module is used to collect data from the computing module, cloud module and underlying simulation module and transmit them to the visualization interface module so that the visualization interface module can display a visualization interface. The module collects specific operating status data and other information from all modules for visualization.

[0097] See also Figure 7, which exemplarily shows a framework diagram of the test platform of an embodiment of the present application. As shown in the figure, the test platform of the embodiment of the present application includes a cloud module, a communication module, a computing module, an underlying simulation module, a visual interface module and a management module.

[0098] The cloud module, communication module, computing module, and underlying simulation module of the embodiment of the present application display all information that needs to be visualized through the visualization interface module through the management module. At the same time, specific test start operations can be performed through the visualization interface module, and test instructions for specific test scenarios can be issued.

[0099] When testing, the visual interface module sends test instructions for the target test scenario offline, and the computing module obtains the data of each module required for control, including perception positioning, planning path and other data. The control algorithm is run through the computing module, and the control instructions are sent through the communication module. The underlying simulation module receives the sent control instructions, retrieves the specified test case data from the test case library, and feeds back the actual operation data through the chassis simulation module. The feedback data is transmitted to the computing module through the communication module for the next step of control instruction calculation, so as to verify the effectiveness and reliability of the control algorithm. The test case library can also be updated by manually pulling down from the cloud or sending it down regularly to meet the task requirements of autonomous driving tests such as different conditions and adapting to site changes. The construction and update of the test case library is to continuously send the actual test data and the first sampling data back to the cloud module through the vehicle terminal. The cloud module sorts and selects according to different scenarios, different vehicle speeds, different road types and other conditions to form test cases under different conditions, and then sends them to the underlying simulation module by manually pulling down or regularly updating them to meet the control algorithms and joint debugging test requirements between modules under different scenarios and conditions.

[0100] The semi-physical simulation test platform for autonomous driving of the embodiments of the present application can execute the method provided by the embodiments of the present application, and the implementation principles are similar. The actions performed by each module in the platform of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the platform, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0101] The semi-physical simulation test platform of the embodiment of the present application provides a new testing method by combining the advantages of virtual simulation and real vehicle testing, which can simulate the mining scene more realistically and provide a highly realistic and cost-effective testing environment. The cloud module can dynamically update the test case library according to the actual vehicle operation data to adapt to the ever-changing mining environment and ensure the diversity and foresight of the test scenarios. The computing module can dynamically adjust the control algorithm according to the real-time test data provided by the underlying simulation module to improve the accuracy and effectiveness of the test.

[0102] In an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory. The processor executes the above-mentioned computer program to implement the steps of a semi-physical simulation test method for autonomous driving. Compared with the related art, it can be realized by receiving test instructions for a target test scenario, so that the tester does not need to perform complex configurations, but only needs to input the target test scenario to start the test, thereby reducing the difficulty of getting started with the test. A target test case matching the target test scenario is determined from a preset case library, and the case library includes multiple test cases. The test case is generated according to the first sampling data of the vehicle when driving in the corresponding real environment. Since the test case is generated based on real operating data, the test scenario can be simulated more realistically, and at least the vehicle only needs to actually drive once in the real scenario. A test scene corresponding to the real scene can be generated, and some parameters of the test scene can be updated in a random manner to obtain a new test scene, thereby providing a highly realistic and cost-effective test environment. The autonomous driving algorithm iteratively executes the first operation based on the target test case until the test end condition is met, and determines the test result of the autonomous driving algorithm according to the first difference of each time step. The first operation includes: obtaining the second sampling data and the first difference of the vehicle at the current time step in the virtual environment, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step. The first difference is the difference between the first sampling data and the second sampling data of the corresponding time step, which can effectively realize the control and testing of the vehicle in the virtual environment.

[0103] In an alternative embodiment, an electronic device is provided, such as Figure 8 As shown, Figure 8The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0104] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0105] The bus 4002 may include a path for transmitting information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus 4002 is represented by only one thick line in the figure, but it does not mean that there is only one bus or one type of bus.

[0106] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation herein.

[0107] The memory 4003 is used to store the computer program for executing the embodiment of the present application, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0108] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0109] The embodiment of the present application also provides a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor.

[0110] The terms "first", "second", "third", "fourth", "1", "2", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that shown or described in the drawings.

[0111] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same time, and each sub-step or stage in these sub-steps or stages may also be executed at different times respectively. In different scenarios of execution time, the execution order of these sub-steps or stages may be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0112] The above is only an optional implementation method for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A semi-physical simulation test method for autonomous driving, characterized in that: include: receiving test instructions for a target test scenario; Determine a target test case matching the target test scenario from a preset test case library, wherein the test case library includes a plurality of test cases, and the test case is generated according to first sampling data when the vehicle is driving in a corresponding real environment; Iteratively executing a first operation based on the target test case by the autonomous driving algorithm until a test end condition is met, and determining a test result of the autonomous driving algorithm according to a first difference at each time step; The first operation includes: obtaining the second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step; The first difference is the difference between the first sampling data and the second sampling data at the corresponding time step.

2. The method according to claim 1, characterized in that second sampling data of a first time step of the vehicle in the virtual environment, rendered according to the test case; The second sampling data of the vehicle in the virtual environment at a non-first time step is rendered according to the test case and the control instruction and the second sampling data of the vehicle at a previous time step of the non-first time step.

3. The method according to claim 1, characterized in that Also includes: Receiving first sampling data when the vehicle is traveling in a real environment sent by a vehicle-mounted terminal deployed on the vehicle; Determine a corresponding test scenario according to the first sampling data; If it is determined that a test case matching the test scenario has been stored in the test case library, updating the test case matching the test scenario according to the first sampling data; If it is determined that the first test case of the test scenario is not stored in the use case library, a test case matching the test scenario is generated according to the first sampling data.

4. The method according to claim 1, characterized in that Also includes: A visualization interface is displayed, where the visualization interface is used to display at least one of the test instruction, the use case library, the second sampling data of at least one time step, and the test result.

5. The method according to claim 1, characterized in that The sampled data includes environmental information and vehicle status information of the vehicle in the corresponding environment, wherein the environmental information includes at least position information and heading information, and the vehicle status information includes at least speed information; The first difference includes at least one of a position difference, a heading difference, and a speed difference.

6. The method according to claim 1, characterized in that The test scenario is related to at least one of site information, vehicle speed level information, and road type; The site information of each test scenario is a mine.

7. A semi-physical simulation test platform for autonomous driving, characterized in that: include: A cloud module, configured to receive a test instruction for a target test scenario, and determine a target test case matching the target test scenario from a preset test case library, wherein the test case library includes a plurality of test cases, and the test case is generated according to first sampling data when a vehicle is driving in a corresponding real environment; a computing module, configured to iteratively perform a first operation based on the test case through the autonomous driving algorithm until a test end condition is met, and determine a test result of the autonomous driving algorithm according to a first difference at each time step; The first operation includes: obtaining the second sampling data of the vehicle at the current time step in the virtual environment and the first difference, generating a control instruction to be executed at the current time step according to the second sampling data, and executing the control instruction to enter the next time step; The first difference is the difference between the first sampling data and the second sampling data at the corresponding time step.

8. The platform according to claim 7, characterized in that It also includes low-level simulation modules; Wherein, the second sampling data of the first time step of the vehicle in the virtual environment is rendered by the underlying simulation module according to the test case; The second sampling data of the vehicle in the virtual environment at a non-first time step is rendered by the underlying simulation module according to the test case and the control instructions and second sampling data of the vehicle at a previous time step of the non-first time step.

9. The method according to claim 7, characterized in that: The cloud module is also used for: Receiving first sampling data when the vehicle is traveling in a real environment sent by a vehicle-mounted terminal deployed on the vehicle; Determine a corresponding test scenario according to the first sampling data; If it is determined that a test case matching the test scenario has been stored in the test case library, updating the test case matching the test scenario according to the first sampling data; If it is determined that the first test case of the test scenario is not stored in the use case library, a test case matching the test scenario is generated according to the first sampling data.

10. The platform according to claim 8, characterized in that Also includes: A visualization interface module is used to display a visualization interface, wherein the visualization interface is used to display at least one of the test instructions, the use case library, the second sampling data of at least one time step, and the test results.

11. The platform according to claim 10, characterized in that Also includes: A communication module, used for data transmission between the computing module, the visualization interface module, the cloud module and the underlying simulation module; The management module is used to collect data from the computing module, the cloud module and the underlying simulation module and transmit the data to the visualization interface module so that the visualization interface module displays a visualization interface.

12. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 6.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images