Testing method, device, electronic device and non-volatile storage medium

Abstract

The present invention discloses a testing method, device, electronic device and non-volatile storage medium. The method includes: determining target area data, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area; determining the device movement trajectory of the target device in the target area based on the set of functions to be tested and the target area data, wherein the function to be tested is used to generate the device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information; determining the movement state of the target device when it moves in the target area according to the device movement trajectory, and determining the test result of the set of functions to be tested based on the movement state. The present invention solves the technical problem of low reliability of simulation results caused by the lack of complex conditions in the real traffic environment in the virtual scenes in the related technologies.

Description

Technical Field

[0001] The present invention relates to the field of simulation, and in particular to a testing method, device, electronic equipment and non-volatile storage medium. Background Art

[0002] Autonomous driving simulation systems can provide richer and more diverse static environments, continuous and dynamic random traffic flows, and, combined with parameter generalization techniques for edge cases and dangerous situations, effectively increase the frequency and density of high-value training scenarios within a limited virtual test mileage. This allows for repeated testing and validation, making it easier to identify and locate problems. Virtual scene construction specifically refers to virtual static scenes for autonomous vehicle testing, typically including roads (centerlines, lane markings, pavement materials, etc.), traffic elements (traffic lights and traffic signs), traffic participants (motor vehicles, non-motor vehicles, and pedestrians), and roadside elements (including streetlights, bus stops, trash cans, green belts, and buildings). Based on this approach, most domestic autonomous driving manufacturers often run simulation programs by editing virtual scenes. While virtual scenes in related technologies can be simple and efficient for testing autonomous vehicles, they lack the complexities of real traffic environments, resulting in lower reliability of simulation results and, in turn, reduced validation of planning and control algorithms.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] Embodiments of the present invention provide a testing method, apparatus, electronic device, and non-volatile storage medium to at least solve the technical problem of low reliability of simulation results caused by the lack of complex conditions in real traffic environments in virtual scenes in related technologies.

[0005] According to one aspect of an embodiment of the present invention, a testing method is provided, comprising: determining target area data, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area; determining a movement trajectory of a target device in the target area based on a set of functions to be tested and the target area data, wherein the function to be tested is used to generate a device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information; determining a movement state of the target device when it moves in the target area according to the device movement trajectory, and determining a test result of the set of functions to be tested based on the movement state.

[0006] Optionally, determining the movement trajectory of the target device in the target area based on the set of functions to be tested and the target area data includes: generating a target road in the target area based on the environmental information in the target area data; determining a first obstacle distribution on the target road based on the obstacle information in the target area data, wherein the first obstacle distribution includes the first position information of the obstacle on the target road and the first obstacle movement trajectory of the obstacle; determining the device movement trajectory based on the set of functions to be tested, the target road and the obstacle distribution.

[0007] Optionally, the function set to be tested includes a first planning function, a second planning function and a prediction function, wherein, based on the function set to be tested, the target road and the obstacle distribution, determining the device movement trajectory includes: determining the path information of the target device based on the first planning function and the target road information of the target road, wherein the path information is the path information of the moving path of the target device on the target road; determining the second obstacle distribution based on the prediction function and the first obstacle distribution, wherein the second obstacle distribution includes the second position information of the obstacle on the target road, and the second obstacle movement trajectory of the obstacle; determining the device movement trajectory based on the second planning function, the path information and the second obstacle distribution.

[0008] Optionally, processing the first obstacle distribution situation based on the prediction function to determine the second obstacle distribution situation includes: generating a detection signal corresponding to the first obstacle distribution situation based on the first obstacle distribution situation during the process of simulating the target device moving along the moving path, wherein the detection signal is a signal generated when the simulated target device detects an obstacle; and determining the second obstacle distribution situation based on the prediction function and the detection signal.

[0009] Optionally, determining the test results of the set of functions to be tested based on the moving state includes: when the moving state is that the target device collides with an obstacle, determining that the test result of the second planned function is failed the test; and when the moving state is that the target device does not collide with the obstacle, determining that the test result of the second planned function is passed the test.

[0010] Optionally, after determining the moving trajectory of the target device in the target area, the testing method further includes: displaying the target road, the distribution of the first obstacle, and the movement process of the target device along the moving trajectory in the interactive interface.

[0011] Optionally, after determining the moving trajectory of the target device in the target area, the testing method further includes: determining the device information of the target device; generating a control signal for the target device based on the device moving trajectory and the device information, wherein the control signal includes at least one of the following: a throttle signal, a brake signal, and a steering wheel signal; determining a control method corresponding to the target device; and controlling the target device to move along the moving trajectory based on the control method and the control signal.

[0012] According to another aspect of an embodiment of the present invention, a testing device is also provided, including: a reading module for determining target area data, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area; a first processing module for determining a moving trajectory of a target device in the target area based on a function set to be tested and the target area data, wherein the function set to be tested is used to generate a device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information; a second processing module for determining a moving state of the target device when it moves in the target area according to the device movement trajectory, and determining a test result of the function set to be tested based on the moving state.

[0013] According to another aspect of an embodiment of the present invention, an electronic device is provided, which includes a processor, a memory, and a display module, wherein the memory is used to store target area data and a test system, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area, and the test system includes: a data loading module for loading the target area data; a simulation module for running a set of functions to be tested, and determining a moving trajectory of the target device in the target area based on the set of functions to be tested and the target area data, wherein the set of functions to be tested is used to generate a device movement trajectory of the target device in the target area based on the target area data; a judgment module for determining a moving state of the target device when it moves in the target area according to the device movement trajectory, and determining a test result of the set of functions to be tested based on the moving state; a processor for running the test system; and a display module for displaying the movement process of the target device when it moves along the movement trajectory through an interactive interface.

[0014] According to another aspect of an embodiment of the present invention, a nonvolatile storage medium is provided. The nonvolatile storage medium includes a stored program, wherein when the program is executed, a device where the nonvolatile storage medium is located is controlled to execute a testing method.

[0015] According to another aspect of an embodiment of the present invention, an electronic device is provided. The electronic device includes a processor, wherein the processor is configured to execute a testing method.

[0016] In an embodiment of the present invention, target area data is determined, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area; based on the set of functions to be tested and the target area data, a moving trajectory of the target device in the target area is determined, wherein the function to be tested is used to generate a device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information; a moving state of the target device when moving in the target area according to the device movement trajectory is determined, and a test result of the set of functions to be tested is determined based on the moving state. By determining the moving trajectory of the target device based on the obstacle information actually collected, the purpose of adding real obstacle information to the virtual scene is achieved, thereby achieving the technical effect of increasing the complexity of the virtual scene, and further solving the technical problem of low reliability of simulation results caused by the lack of complex conditions in the real traffic environment in the virtual scenes in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 is a flow chart of a testing method according to an embodiment of the present invention;

[0019] Figure 2 is a flow chart of a test process according to an embodiment of the present invention;

[0020] Figure 3 is a schematic structural diagram of a testing device according to an embodiment of the present invention;

[0021] Figure 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;

[0022] Figure 5 It is a structural diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention 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 invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] Example 1

[0026] According to an embodiment of the present invention, a method embodiment of a testing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] Figure 1 is a test method according to an embodiment of the present invention, such as Figure 1 As shown, the method includes the following steps:

[0028] Step S102: determining target area data, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environment information in the target area;

[0029] In some embodiments of the present disclosure, the target area can be an area selected by the user based on their own needs. Specifically, different area types can be defined based on information such as the degree of road congestion, traffic volume, and time period, and different area types will match different user needs. For example, when a user wants to determine the test effect of the function set to be tested in the morning rush hour scenario, the user can select an area with a morning time period, dense traffic volume, and congested road congestion as the target area, and collect data for the target area, including environmental data and obstacle data in the target area, such as road data, traffic element data, road surrounding element data, and traffic participant data. Among them, the road data includes the road surface material, road width, centerline information, and lane line information of the road; the traffic element data includes traffic light data and traffic sign data on the road; the road surrounding element data includes street light data on both sides of the road, station data, trash can data, green belt data, building data, etc.; the traffic participant data includes motor vehicle data, non-motor vehicle data, and pedestrian data on the road.

[0030] Specifically, it can be seen that in the solution provided in this application, the collected target area data not only includes the road surrounding element data that is stationary relative to the road, but also includes the traffic participant data that is moving relative to the road. Therefore, during the simulation process, the actual operation scenario of the target device can be better reflected.

[0031] In addition, to make the simulation more targeted, typical scenarios can be selected as target areas. For example, if the user wants to determine the performance of the function set under test in terms of safe driving, they can select sections with high accident rates as target areas; if the user wants to determine the performance of the function set under test in terms of path planning, they can select sections with dense road distribution as target areas.

[0032] After the target area is determined, data collection for the target area can be performed using a vehicle or drone equipped with data acquisition equipment. To ensure accuracy, multiple data types can be collected simultaneously. For example, point cloud data for traffic element data, road perimeter data, and traffic participant data can be collected and modeled. Image data for road centerline and lane marking information can be collected, where the image data can be either color or grayscale.

[0033] Step S104: determining a movement trajectory of the target device in the target area based on the set of functions to be tested and the target area data, wherein the function to be tested is used to generate a movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information;

[0034] In some embodiments of the present application, when determining the movement trajectory of a target device based on the set of functions to be tested and the target area data, a target road and the distribution of obstacles on the target road can be first generated based on the target area data. Then, the movement trajectory of the target device can be determined based on the target road and the distribution of obstacles using the set of functions to be tested.

[0035] Before determining the target device's trajectory, a model must be constructed based on real device information to obtain the target device. This real device information can be customized based on user needs. For example, if the user wishes to test a set of functions applicable to a truck, the real device information would be the device information for a specific truck model.

[0036] In addition, it should be noted that the number of to-be-tested functions in the to-be-tested function set may be one or more.

[0037] Step S106 : determining a movement state of the target device when it moves in the target area according to the device movement trajectory, and determining a test result of the function set to be tested according to the movement state.

[0038] By adopting a method of determining target area data, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area; determining the movement trajectory of the target device in the target area based on the set of functions to be tested and the target area data, wherein the function to be tested is used to generate the device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information; determining the movement state of the target device when it moves in the target area according to the device movement trajectory, and determining the test result of the set of functions to be tested based on the movement state, the movement trajectory of the target device is determined based on the obstacle information actually collected, and the purpose of adding real obstacle information to the virtual scene is achieved, thereby achieving the technical effect of increasing the complexity of the virtual scene, and further solving the technical problem of low reliability of simulation results caused by the lack of complex conditions in the real traffic environment in the virtual scenes in related technologies.

[0039] As an optional implementation, in step S104 of the above-mentioned testing method, when determining the movement trajectory of the target device in the target area based on the set of functions to be tested and the target area data, the movement trajectory of the target device in the target area can be determined by the following method:

[0040] The first step is to generate a target road in the target area based on the environmental information in the target area data;

[0041] Specifically, when generating a target road based on environmental information, not only a target road corresponding to the actual road in the target area will be generated, but also lane line information in the target road will be generated, as well as street lights, stations, trash cans, green belts and buildings on both sides of the road, traffic on the road and traffic signs will also be generated.

[0042] The second step is to determine a first obstacle distribution on the target road based on the obstacle information in the target area data, wherein the first obstacle distribution includes first position information of the obstacle on the target road and a first obstacle movement trajectory of the obstacle;

[0043] Specifically, the first obstacle distribution refers to the actual distribution of obstacles collected on the road. Optionally, when determining the movement trajectory of the target device, in order to reduce computing power consumption during the simulation test, only obstacles whose distance from the target device is no greater than a preset distance can be loaded.

[0044] The third step is to determine the movement trajectory of the device based on the set of functions to be tested, the target road and the distribution of obstacles.

[0045] Specifically, in some embodiments of the present application, the above-mentioned set of functions to be tested may include a first planning function, a second planning function and a prediction function, wherein the above-mentioned third step determines the movement trajectory of the device based on the set of functions to be tested, the target road and the obstacle distribution, including: determining the path information of the target device based on the first planning function and the target road information of the target road, wherein the path information is the path information of the movement path of the target device on the target road; determining the second obstacle distribution based on the prediction function and the first obstacle distribution, wherein the second obstacle distribution includes the second position information of the obstacle on the target road and the second obstacle movement trajectory of the obstacle; determining the movement trajectory of the device based on the second planning function, the path information and the second obstacle distribution.

[0046] In some embodiments of the present application, when the path information of the target device is determined through the first planning function, it is necessary to first set the planning goal when planning the moving path, such as the shortest total distance, the shortest total time, or the least number of traffic lights passed, etc.

[0047] Optionally, when determining the second obstacle distribution situation based on the prediction function and the first obstacle distribution situation, in the process of simulating the movement of the target device along the moving path, a detection signal corresponding to the first obstacle distribution situation can be first generated based on the first obstacle distribution situation, wherein the detection signal is a signal generated when simulating the target device detecting the obstacle, and then the second obstacle distribution situation is determined based on the prediction function and the detection signal.

[0048] Specifically, the detection signal may be determined by simulating an actual working state of a sensor on an actual device corresponding to the target device.

[0049] As an optional implementation, in step S106 of the above-mentioned testing method, taking the second planning function as an example, when determining the test results of the set of functions to be tested based on the moving state, when the moving state is that the target device collides with the obstacle, the test result of the second planning function can be determined as failing the test; and, when the moving state is that the target device does not collide with the obstacle, the test result of the second planning function can be determined as passing the test.

[0050] Alternatively, if the user only wishes to test the second test function, they can directly set the second obstacle distribution to be the same as the first obstacle distribution. This means that the obstacle distribution predicted by the prediction function is identical to the actual obstacle distribution, eliminating any interference from the prediction function on the test results.

[0051] Likewise, when the user wishes to test the prediction function, the second test function may be a test function that has passed the test, thereby eliminating interference of the second test function on the test result of the prediction function.

[0052] As an optional implementation, after determining the device movement trajectory, the above-mentioned test method can also determine the device information of the target device in order to better simulate the operating status of the target device; generate a control signal for the target device based on the device movement trajectory and the device information, wherein the control signal includes at least one of the following: throttle signal, brake signal, steering wheel signal; determine the control method corresponding to the target device; and control the target device to move along the device movement trajectory based on the control method and the control signal.

[0053] In some embodiments of the present application, in order to more intuitively display the entire simulation process, after determining the moving trajectory, the above-mentioned testing method can also display the target road, the distribution of the first obstacle, and the movement process of the target device when moving along the moving trajectory in the interactive interface.

[0054] Specifically, in order to display the above content on the interactive interface, it is necessary to load visualization tools and data playback simulation engines during the simulation process. Among them, the data playback simulation engine includes a data playback tool (i.e., a broadcasting tool) and a simulation engine. The data playback tool can load the vehicle-side collected data packets and play them in the time sequence within the packets to achieve the purpose of reproducing the scene. The simulation engine can read the data sent by the data playback tool, cooperate with relevant functional modules such as planning and control, re-control the operation of the simulated vehicle, and realize the testing of the algorithm code of relevant functional modules such as planning and control.

[0055] As an optional implementation, the data playback simulation engine tool is developed in C++ language, uses the Bazel project building tool that supports incremental compilation and is fast, and uses the protobuf data protocol that is fast in resolution, highly efficient, and supports multiple languages.

[0056] In some embodiments of the present application, since the simulation process involves the collaborative work between multiple functional modules, for example, the collaborative work between the prediction functional module and the second planning module, it is necessary to be able to achieve fast communication between the functional modules. To achieve this goal, the embodiments of the present application choose to use the underlying Cyber_RT framework to achieve communication between different functional modules and between functional modules and the data playback simulation engine.

[0057] As an optional implementation, the functions in the set of functions to be tested in the above-mentioned testing method can be implemented by different functional modules during the simulation process. For example, different functions can be implemented by a planning module, a control module, a perception module, a prediction module, and a navigation module. The planning module plans a drivable trajectory for the vehicle based on the prediction results of the perception module and the prediction module, current vehicle information, and road conditions. This trajectory is then passed to the control module, which uses the accelerator, brake, and steering to control the vehicle along the planned trajectory. The control module calculates the accelerator, brake, and steering signals based on the trajectory generated by the planning module, controlling the vehicle to follow the specified trajectory. This method is to model the vehicle based on knowledge of vehicle dynamics and kinematics to achieve vehicle control. Two control methods can be used for vehicle control: PID control and model control. The prediction module receives obstacle information from the perception module and predicts the obstacle trajectory. The predicted trajectory and obstacle information are sent to the planning module for use. The navigation module determines the optimal path based on a preset target.

[0058] On this basis, the data collected by the vehicle can be replayed to reproduce the real road scene and complete the simulation task.

[0059] Furthermore, it can be seen that in the test method provided in this application, each function to be tested in the set of functions to be tested is executed by an independent functional module. This can achieve strong independence and low coupling between the functional modules, thereby improving the versatility and stability of the test method.

[0060] In order to facilitate understanding of the test method provided in this embodiment, Figure 2 The test process shown in further explains the above test method. It should be noted that Figure 2 The test process in this section is only an example test process and does not mean that the above test methods must be strictly followed. Figure 2 Specifically, the test process includes the following steps:

[0061] Step S202: Compile and install the Cyber_RT framework. Apollo Cyber_RT is an open-source, high-performance runtime framework designed specifically for autonomous driving scenarios. Based on a centralized computing model, it is significantly optimized for the high concurrency, low latency, and high throughput of autonomous driving. Furthermore, the Cyber_RT framework is an open-source tool that is easy to use, free of charge, and professionally maintained. The Cyber_RT framework provides features that accelerate development, including a well-defined task interface with data fusion capabilities and a large number of sensor drivers. It also provides features that simplify deployment, including efficient and adaptive message communication, a resource-aware, configurable user-level scheduler, portability, and fewer dependencies.

[0062] Step S204: Load the map and visualization tool. The map uses the protobuf data protocol and includes basic information such as roads (centerlines, lane markings, road surface materials, etc.), traffic elements (traffic lights and traffic signs), and road surrounding elements (including streetlights, bus stops, trash cans, green belts, and buildings). The visualization tool displays the simulation progress and status in real time, facilitating the timely identification of problems that arise during the simulation. The Cyber_RT framework already includes the visualization tool Dreamview.

[0063] Step S206: Prepare the vehicle-side collected data packets. The vehicle-side collected data packets are data packets recorded when the autonomous driving vehicle is tested on a real road. The packets contain all the information specified in the Cyber_RT framework during recording and are used to play back and reproduce the real road scene.

[0064] Step S208: Activate planning and control related modules. Modules such as the planning module, control module, prediction module, and navigation module are activated. These modules re-issue trajectory information, control commands, obstacle prediction information, and route information, replacing the original information in the package. The planning module plans a drivable trajectory for the vehicle based on the prediction results from the perception and prediction modules, current vehicle information, and road conditions. This trajectory is then passed to the control module, which uses the accelerator, brake, and steering to control the vehicle along the planned trajectory. The control module calculates the accelerator, brake, and steering signals based on the trajectory generated by the planning module, controlling the vehicle to follow the specified trajectory. This method utilizes vehicle modeling based on knowledge of vehicle dynamics and kinematics to achieve vehicle control. Two control methods can be used for vehicle control: PID control and model control. The prediction module receives obstacle information from the perception module and predicts the obstacle trajectory. The predicted trajectory and obstacle information are then sent to the planning module. The navigation module determines the optimal path based on a preset target.

[0065] Step S210: Run the data playback simulation engine. First, configure the correct data packet path and use the data playback tool to broadcast the information. Then, run the simulation engine. Working with external planning and control modules, the simulation engine receives and processes new trajectory information, control commands, obstacle prediction information, route information, and other module information, re-controls the main vehicle, and outputs information such as position and speed for display in the visualization tool.

[0066] Step S212: Jointly test and view the process in a visualization tool. Jointly run planning and control and other related modules, and the data playback simulation engine, and view the simulation process and results in a front-end visualization tool.

[0067] Example 2

[0068] According to an embodiment of the present invention, an embodiment of a testing device is provided. Figure 3 Schematic diagram of a test device according to an embodiment of the present invention. Figure 4 As shown, the testing device includes: a reading module 30, used to determine the target area data, wherein the target area data is the data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area; a first processing module 32, used to determine the moving trajectory of the target device in the target area based on the function set to be tested and the target area data, wherein the function set to be tested is used to generate the device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information; a second processing module 34, used to determine the movement state of the target device when it moves in the target area according to the device movement trajectory, and determine the test result of the function set to be tested based on the movement state.

[0069] In some embodiments of the present application, the first processing module 32 determines the movement trajectory of the target device in the target area based on the set of functions to be tested and the target area data, including: generating a target road in the target area based on the environmental information in the target area data; determining the first obstacle distribution on the target road based on the obstacle information in the target area data, wherein the first obstacle distribution includes the first position information of the obstacle on the target road, and the first obstacle movement trajectory of the obstacle; determining the device movement trajectory based on the set of functions to be tested, the target road and the obstacle distribution.

[0070] In some embodiments of the present application, the set of functions to be tested includes a first planning function, a second planning function and a prediction function, wherein the first processing module 32 determines the device movement trajectory based on the set of functions to be tested, the target road and the obstacle distribution, including: determining the path information of the target device based on the first planning function and the target road information of the target road, wherein the path information is the path information of the moving path of the target device on the target road; determining the second obstacle distribution based on the prediction function and the first obstacle distribution, wherein the second obstacle distribution includes the second position information of the obstacle on the target road and the second obstacle movement trajectory of the obstacle; determining the device movement trajectory based on the second planning function, the path information and the second obstacle distribution.

[0071] In some embodiments of the present application, the first processing module 32 processes the first obstacle distribution situation based on the prediction function, and determines the second obstacle distribution situation, including: in the process of simulating the target device moving along the moving path, generating a detection signal corresponding to the first obstacle distribution situation based on the first obstacle distribution situation, wherein the detection signal is a signal generated when the simulated target device detects an obstacle; and determining the second obstacle distribution situation based on the prediction function and the detection signal.

[0072] In some embodiments of the present application, the second processing module 34 determines the test results of the set of functions to be tested based on the moving state, including: when the moving state is that the target device collides with an obstacle, determining that the test result of the second planning function is failed the test; and when the moving state is that the target device does not collide with the obstacle, determining that the test result of the second planning function is passed the test.

[0073] In some embodiments of the present application, after determining the movement trajectory of the target device in the target area, the second processing module 34 is further configured to execute: displaying the target road, the distribution of the first obstacle, and the movement process of the target device as it moves along the movement trajectory in the interactive interface.

[0074] In some embodiments of the present application, after determining the movement trajectory of the target device in the target area, the first processing module 32 is further configured to execute: determining the device information of the target device; generating a control signal for the target device based on the device movement trajectory and the device information, wherein the control signal includes at least one of the following: a throttle signal, a brake signal, and a steering wheel signal; determining a control method corresponding to the target device; and controlling the target device to move along the movement trajectory based on the control method and the control signal.

[0075] It should be noted that the testing device provided in this embodiment can be used to execute the testing method shown in Example 1. Therefore, the relevant explanations and descriptions of the testing method in Example 1 are also applicable to the embodiments of this application and will not be repeated here.

[0076] Example 3

[0077] According to an embodiment of the present invention, an embodiment of an electronic device is also provided. Figure 4 Schematic diagram of an electronic device according to an embodiment of the present invention. Figure 4 As shown, the electronic device includes: a processor 40, a memory 42, and a display module 44, wherein the memory 42 is used to store target area data and a test system, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area, and the test system includes: a data loading module for loading target area data; a simulation module for running a set of functions to be tested, and determining a moving trajectory of the target device in the target area based on the set of functions to be tested and the target area data, wherein the set of functions to be tested is used to generate a device movement trajectory of the target device in the target area based on the target area data; a judgment module for determining a moving state of the target device when it moves in the target area according to the device movement trajectory, and determining a test result of the set of functions to be tested based on the moving state; the processor 40 is used to run the test system; and the display module 44 is used to display the movement process of the target device when it moves along the movement trajectory through an interactive interface.

[0078] Example 4

[0079] According to an embodiment of the present invention, an embodiment of a non-volatile storage medium is provided. The non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to perform the following test method: determining target area data, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area; determining the movement trajectory of the target device in the target area based on the set of functions to be tested and the target area data, wherein the function to be tested is used to generate a device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information; determining the movement state of the target device when it moves in the target area according to the device movement trajectory, and determining the test result of the set of functions to be tested based on the movement state.

[0080] According to an embodiment of the present invention, an embodiment of an electronic device is provided. The electronic device includes a processor, wherein the processor is configured to execute the following test method: determining target area data, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area; determining a movement trajectory of a target device in the target area based on a set of functions to be tested and the target area data, wherein the function to be tested is configured to generate a device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information; determining a movement state of the target device when it moves in the target area according to the device movement trajectory, and determining a test result of the set of functions to be tested based on the movement state.

[0081] According to an embodiment of the present invention, an embodiment of a computer device is provided. Figure 5 It is a structural diagram of a computer device provided according to an embodiment of the present invention.

[0082] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 504 including instructions, and the above instructions can be executed by the processor 502 of the device 500 to complete the following test method: determining target area data, wherein the target area data is data actually collected in the target area, and the target area data includes obstacle information and environmental information in the target area; determining the movement trajectory of the target device in the target area based on the set of functions to be tested and the target area data, wherein the function to be tested is used to generate a device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information; determining the movement state of the target device when it moves in the target area according to the device movement trajectory, and determining the test result of the set of functions to be tested based on the movement state. Optionally, the storage medium can be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0083] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0084] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0086] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0087] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0088] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0089] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A testing method, characterized in that: include: Determining target area data, wherein the target area data is data actually collected in the target area, the target area data includes obstacle information and environmental information in the target area, and the types of the target area data include point cloud data and image data; Determining a device movement trajectory of a target device in the target area based on a set of functions to be tested and the target area data, wherein the function to be tested is used to generate a device movement trajectory of the target device in the target area based on the target area data, the target device is a virtual device modeled based on real device information, the set of functions to be tested includes a first planning function, a second planning function, and a prediction function, the first planning function and the second planning function are used to determine the device movement trajectory, and the prediction function is used to determine the distribution of obstacles; Determining, based on the set of functions to be tested and the target area data, a device movement trajectory of the target device in the target area includes: generating a target road in the target area based on environmental information in the target area data; determining, based on obstacle information in the target area data, a first obstacle distribution on the target road, wherein the first obstacle distribution includes first position information of the obstacle on the target road and a first obstacle movement trajectory of the obstacle, and a distance between the obstacle and the target device is no greater than a preset distance; determining, based on the set of functions to be tested, the target road, and the obstacle distribution, the device movement trajectory includes: when only the second planning function is tested, setting the second obstacle distribution predicted by the prediction function to be the same as the actual obstacle distribution; A movement state of the target device when it moves in the target area according to the device movement trajectory is determined, and a test result of the to-be-tested function set is determined according to the movement state.

2. The testing method according to claim 1, wherein: Determining the movement trajectory of the device according to the set of functions to be tested, the target road, and the obstacle distribution includes: determining path information of the target device according to the first planning function and target road information of the target road, wherein the path information is path information of a moving path of the target device on the target road; determining a second obstacle distribution situation based on the prediction function and the first obstacle distribution situation, wherein the second obstacle distribution situation includes second position information of the obstacle on the target road and a second obstacle movement trajectory of the obstacle; Determine the device movement trajectory based on the second planning function, the path information, and the second obstacle distribution.

3. The testing method according to claim 2, wherein: Processing the first obstacle distribution according to the prediction function to determine the second obstacle distribution includes: During the simulation of the target device moving along the movement path, generating a detection signal corresponding to the first obstacle distribution according to the first obstacle distribution, wherein the detection signal is a signal generated when the target device detects the obstacle; The second obstacle distribution is determined based on the prediction function and the detection signal.

4. The testing method according to claim 2, wherein: Determining the test result of the set of functions to be tested according to the movement state includes: In a case where the moving state is that the target device collides with the obstacle, determining that the test result of the second planning function is a failure; and When the moving state is that the target device does not collide with the obstacle, it is determined that the test result of the second planning function is passed.

5. The testing method according to claim 2, wherein: After determining the movement trajectory of the target device in the target area, the testing method further includes: The target road, the distribution of the first obstacle, and the movement process of the target device along the device movement trajectory are displayed in the interactive interface.

6. The testing method according to claim 1, wherein: After determining the movement trajectory of the target device in the target area, the testing method further includes: Determining device information of the target device; generating a control signal for the target device according to the device movement trajectory and the device information, wherein the control signal includes at least one of the following: a throttle signal, a brake signal, and a steering wheel signal; determining a control method corresponding to the target device; According to the control method and the control signal, the target device is controlled to move along the device movement trajectory.

7. A testing device, characterized in that: include: a reading module, configured to determine target area data, wherein the target area data is data actually collected in the target area, the target area data includes obstacle information and environmental information in the target area, and the types of the target area data include point cloud data and image data; The first processing module is used to determine the movement trajectory of the target device in the target area based on the function set to be tested and the target area data, wherein the function set to be tested is used to generate the device movement trajectory of the target device in the target area based on the target area data, and the target device is a virtual device modeled based on real device information. The function set to be tested includes a first planning function, a second planning function and a prediction function, the first planning function and the second planning function are used to determine the device movement trajectory, and the prediction function is used to determine the distribution of obstacles; determining the device movement trajectory of the target device in the target area based on the function set to be tested and the target area data includes: The method further comprises: determining a first obstacle distribution on the target road based on the environmental information in the target area data; determining a first obstacle distribution on the target road based on the obstacle information in the target area data, wherein the first obstacle distribution includes first position information of the obstacle on the target road and a first obstacle movement trajectory of the obstacle, and the distance between the obstacle and the target device is not greater than a preset distance; determining the device movement trajectory based on the set of functions to be tested, the target road, and the obstacle distribution, including: when only the second planning function is tested, setting the second obstacle distribution predicted by the prediction function to be the same as the actual obstacle distribution; The second processing module is configured to determine a movement state of the target device when the target device moves in the target area according to the device movement trajectory, and determine a test result of the to-be-tested function set according to the movement state.

8. An electronic device, characterized in that: The electronic device includes a processor, a memory, and a display module, wherein: The memory is used to store target area data and a test system, wherein the target area data is data actually collected in the target area, the target area data includes obstacle information and environmental information in the target area, and the types of the target area data include point cloud data and image data. The test system includes: a data loading module for loading the target area data; a simulation module for running a set of functions to be tested and determining a movement trajectory of a target device in the target area based on the set of functions to be tested and the target area data, wherein the set of functions to be tested is used to generate a device movement trajectory of the target device in the target area based on the target area data, the set of functions to be tested includes a first planning function, a second planning function, and a prediction function, the first planning function and the second planning function are used to determine the device movement trajectory, and the prediction function is used to determine the distribution of obstacles; a judgment module, configured to determine a movement state of the target device when it moves in the target area according to the device movement trajectory, and determine a test result of the function set to be tested based on the movement state; determining the device movement trajectory of the target device in the target area based on the function set to be tested and the target area data, including: generating a target road in the target area based on environmental information in the target area data; determining a first obstacle distribution on the target road based on obstacle information in the target area data, wherein the first obstacle distribution includes first position information of the obstacle on the target road and a first obstacle movement trajectory of the obstacle, and the distance between the obstacle and the target device is not greater than a preset distance; determining the device movement trajectory based on the function set to be tested, the target road, and the obstacle distribution, including: when only the second planning function is tested, setting the second obstacle distribution predicted by the prediction function to be the same as the actual distribution of obstacles; The processor is configured to run the test system; The display module is used to display the movement process of the target device along the movement trajectory through an interactive interface.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the test method according to any one of claims 1 to 6.

Images