Automatic driving test system and method for special vehicle

Abstract

The invention provides an automatic driving test system and method for a special vehicle, and the system comprises an environment simulation module which is used for constructing different simulation scenes required by the test of the special vehicle; the sensor simulation module is used for simulating sensor data collected by a sensor in the special vehicle based on the simulation scene; the controller is used for controlling the automatic driving system to perform automatic driving test on the special vehicle model in the same simulation scene according to the sensor data in the simulation scene; the monitoring module is used for monitoring operation data of the automatic driving system in the test in the simulation scene; and the data processing module is used for receiving test data generated by different simulation scenes in the test, performing performance analysis on the automatic driving system according to the test data and generating an optimization report of the automatic driving system based on an analysis result, and the test data comprises simulation scene data, sensor data and operation data. Therefore, the development efficiency and the test precision of the automatic driving technology of the special vehicle are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a dedicated vehicle autonomous driving testing system and method. Background Art

[0002] With the rapid development of autonomous driving technology, its application in various fields is becoming more and more extensive, especially for special vehicles such as industrial vehicles, explosion-proof vehicles, special vehicles, etc. The introduction of autonomous driving technology can not only significantly improve work efficiency, but also greatly reduce the safety risks brought by human operation. However, compared with autonomous driving vehicles for public use, these special vehicles often need to operate in extremely complex and changeable working environments, such as blasting areas, industrial plants, dangerous environments, etc. These environments place extremely high demands on the perception ability, decision-making speed, stability and safety of the autonomous driving system. In related technologies, the conventional testing methods of special vehicle autonomous driving technology mainly rely on field testing, that is, vehicle operation and performance testing on real roads or environments.

[0003] However, for special-purpose vehicles, field testing has many limitations that are difficult to overcome. On the one hand, field testing is costly, time-consuming, and severely affected by external environmental factors such as weather and traffic, resulting in unstable test results and difficulty in fully evaluating the performance of the autonomous driving system. On the other hand, field testing is difficult to cover all possible complex working scenarios, resulting in low test accuracy. Summary of the invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] In view of the above-mentioned shortcomings of the prior art, the present application discloses a dedicated vehicle autonomous driving test system and method to solve at least one of the above-mentioned technical problems.

[0006] In the first aspect, the present application provides a special-purpose vehicle automatic driving test system, comprising: an automatic driving system is configured in the special-purpose vehicle, including: an environmental simulation module, used to construct different simulation scenarios required for the special-purpose vehicle test, the simulation scenario is used to simulate the working scenario of the automatic driving of the special-purpose vehicle; a sensor simulation module, used to simulate the sensor data collected by the sensors in the special-purpose vehicle based on the simulation scenario; a controller, used to control the automatic driving system to perform automatic driving test on a special-purpose vehicle model in the same simulation scenario according to the sensor data in the simulation scenario, the special-purpose vehicle model is obtained by simulating the special-purpose vehicle; a monitoring module, used to monitor the operating data of the automatic driving system in the test under the simulation scenario; a data processing module, used to receive test data generated in the test of different simulation scenarios, perform performance analysis on the automatic driving system according to the test data, and generate an optimization report on the automatic driving system based on the analysis results, the test data at least includes the data of the simulation scenario, the sensor data and the operating data.

[0007] In one embodiment of the present application, the simulation scene includes basic elements and dynamic interactive elements. The basic elements include simulated road types, traffic flow and environmental information, and the dynamic interactive elements include simulated behaviors of pedestrians, vehicles and traffic lights.

[0008] In one embodiment of the present application, the sensor simulation module is also used to adjust the performance of the simulated sensor according to the environmental information if it is determined that the environmental information in the simulation scene meets the preset environmental conditions, wherein the environmental information and the preset mapping relationship are matched to determine the target performance of the sensor, and the preset mapping relationship represents the mapping relationship between the environmental information and the performance of the sensor, the environmental information includes at least weather conditions, lighting conditions and road conditions, and the sensing performance includes at least perception range and accuracy.

[0009] In one embodiment of the present application, the sensor simulation module is further used to perform fault simulation on at least one of the sensors in the special vehicle to generate sensor data collected by the faulty sensor.

[0010] In one embodiment of the present application, the controller is also used to receive different test tasks, control the autonomous driving system to perform path planning according to the sensor data and preset traffic rules, and control the autonomous driving system to generate control instructions based on the planned path and the test tasks to control the dedicated vehicle model to perform autonomous driving testing in the simulation scenario.

[0011] In one embodiment of the present application, the monitoring module is used to feed back the operating data of the autonomous driving system to the controller, so that the controller adjusts the control of the autonomous driving system according to the operating data, the operating data includes performance data and status data, the performance data includes at least path tracking accuracy, obstacle recognition rate and reaction time, and the status data includes at least processor load, memory occupancy and network status.

[0012] In one embodiment of the present application, the monitoring module is also used to monitor the data of the simulation environment and the sensor data during the test process. The data of the simulation environment, the sensor data and the operation data identify abnormal conditions in the operation of the autonomous driving system and generate abnormal alarms. The abnormal conditions include at least simulated failure of the sensor, data loss and operation errors of the autonomous driving system.

[0013] In one embodiment of the present application, the monitoring module includes a visualization unit for visually displaying the autonomous driving test of the dedicated vehicle model in the simulation scenario, wherein the visualization includes at least the simulation scenario, the sensor data, and the driving data of the dedicated vehicle model during the test, wherein the driving data includes at least the throttle status, steering angle, speed, acceleration, and braking status.

[0014] In one embodiment of the present application, the data processing module is used to preprocess the test data under the same simulation scenario, perform performance analysis on the autonomous driving system based on the preprocessed test data under different simulation scenarios to generate the optimization report, and adjust the preset autonomous driving algorithm configured in the autonomous driving system based on the optimization report.

[0015] In the second aspect, the present application provides a special-purpose vehicle automatic driving test method, which is applied to the special-purpose vehicle automatic driving test device described in the above embodiment, and the method includes: constructing different simulation scenarios required for special-purpose vehicle testing, and the simulation scenarios are used to simulate the working scenarios of the automatic driving of the special-purpose vehicle; simulating sensor data collected by sensors in the special-purpose vehicle based on the simulation scenarios; according to the sensor data in the simulation scenarios, controlling the automatic driving system to perform automatic driving test on the special-purpose vehicle model in the same simulation scenario, wherein the special-purpose vehicle model is obtained by simulating the special-purpose vehicle, and the automatic driving system is configured on the special-purpose vehicle; monitoring the operating data of the automatic driving system in the test in the simulation scenarios; performing performance analysis on the automatic driving system according to the test data in different simulation scenarios, and generating an optimization report on the automatic driving system based on the analysis results, and the test data at least includes the data of the simulation scenarios, the sensor data and the operating data.

[0016] Beneficial effects of the present application: The present application proposes a special vehicle automatic driving test system and method. Among them, the system includes an environmental simulation module, which constructs different simulation scenarios required for special vehicle testing, and the simulation scenarios are used to simulate the working scenarios of the automatic driving of special vehicles; a sensor simulation module, which is used to simulate the sensor data collected by the sensors in the special vehicle based on the simulation scenarios; a controller, which is used to control the automatic driving system to test the automatic driving of the special vehicle model in the same simulation scenario according to the sensor data in the simulation scenario, and the special vehicle model is obtained by simulating the special vehicle; a monitoring module, which is used to monitor the operating data of the automatic driving system in the test under the simulation scenario; a data processing module, which is used to receive the test data generated by different simulation scenarios in the test, perform performance analysis on the automatic driving system according to the test data, and generate an optimization report on the automatic driving system based on the analysis results, and the test data at least includes the data of the simulation scenario, sensor data and operation data. In this way, first, by combining the environment simulation module and the sensor simulation module, various working scenarios that professional vehicles may encounter in actual autonomous driving can be restored in a diversified manner, improving the test efficiency and test accuracy of the autonomous driving system in professional vehicles; second, the monitoring module can be used to monitor the performance of the autonomous driving system in different simulation scenarios in real time, so as to adjust the test strategy in time, ensure the continuity and stability of the test, and further improve the test efficiency and reliability; third, the data processing module can be used to promote the further optimization of the autonomous driving system. In addition, the use of simulation testing reduces the test cost and test cycle.

[0017] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0019] Figure 1 is a schematic diagram of a dedicated vehicle automatic driving test system shown in an exemplary embodiment of the present application;

[0020] Figure 2 is a schematic diagram of an overall system architecture shown in an exemplary embodiment of the present application;

[0021] Figure 3is a schematic diagram of an automatic driving test process shown in an exemplary embodiment of the present application;

[0022] Figure 4 is a schematic diagram of a visualization interface shown in an exemplary embodiment of the present application;

[0023] Figure 5 It is a flowchart of a dedicated vehicle autonomous driving testing method shown as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.

[0025] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0026] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0027] It should be noted that the testing of the autonomous driving system of professional vehicles usually adopts field testing, which has the following disadvantages: First, the cost is high. In order to simulate different road conditions, such as gravel, pebbles, high-speed runways, etc., as well as slopes reflecting various slopes, it is necessary to build a special test site, which requires a large amount of capital investment and needs to be equipped with high-precision testing equipment and instruments, such as acceleration sensors, brake pedal contact switches, etc. The purchase and maintenance costs of these equipment are also relatively high. Second, the time period is long. Before each field test, a lot of preparation work needs to be done, including site layout, equipment debugging, etc., which will consume a lot of time. In addition, due to the complexity and uncertainty of the test environment during the test, the test process may need to be repeated to ensure the accuracy and reliability of the test results, which further prolongs the test cycle. Third, due to environmental factors, field testing is greatly affected by weather conditions. For example, dry land tests cannot be carried out on rainy days, and it is difficult to simulate wetland skidding tests on sunny days. In addition, in order to conduct tests under extreme conditions (such as high temperature and low temperature tests), testers need to go to specific locations in specific seasons for testing, which also increases the complexity and difficulty of the test. Fourth, the vehicle may face various emergencies during the test, such as collision and rollover, which will cause damage to the vehicle itself, and the tester needs to carry out inspections on the vehicle and monitor the vehicle performance in real time, which also increases the safety risks faced by the tester. Fifth, real-time monitoring is difficult, and the equipment structure is required to be high, making it difficult to collect and transmit test data in real time and accurately.

[0028] Based on this, the present application proposes a dedicated vehicle autonomous driving test system and method.

[0029] See also Figure 1 , is a schematic diagram of a dedicated vehicle automatic driving test system shown in an exemplary embodiment of the present application. Figure 1 As shown, in an exemplary embodiment, the dedicated vehicle automatic driving test system includes at least an environment simulation module 110, a sensor simulation module 120, a controller 130, a monitoring module 140 and a data processing module 150, and the dedicated vehicle is equipped with an automatic driving system, which is described in detail as follows:

[0030] The environment simulation module 110 is used to construct different simulation scenarios required for special vehicle testing, and the simulation scenarios are used to simulate the working scenarios of automatic driving of special vehicles;

[0031] A sensor simulation module 120, for simulating sensor data collected by sensors in a special vehicle based on a simulation scenario;

[0032] The controller 130 is used to control the automatic driving system to perform automatic driving test on the special vehicle model in the same simulation scenario according to the sensor data in the simulation scenario, where the special vehicle model is obtained by simulating the special vehicle;

[0033] A monitoring module 140 is used to monitor the operating data of the autonomous driving system during the test in the simulation scenario;

[0034] The data processing module 150 is used to receive the test data generated by different simulation scenarios during the test, perform performance analysis on the autonomous driving system according to the test data, and generate an optimization report on the autonomous driving system based on the analysis results. The test data includes at least simulation scenario data, sensor data and operation data.

[0035] See also Figure 2 , is a schematic diagram of an overall system architecture shown in an exemplary embodiment of the present application. Figure 2 As shown in the figure, the special vehicle automatic driving test system mainly includes a sensor simulation module, an environment simulation module, a controller, a monitoring module and a data processing module. These five models form a closed-loop test system. Among them, the environment simulation module is used to create simulation scenes of various professional vehicles in actual operation. The simulation scene includes at least virtual terrain, obstacles and interference elements. The sensor simulation module is used to simulate the sensor data around the special vehicle in the simulation scene, such as radar, camera and GPS (global positioning system) data. At the same time, the simulation scene data, sensor data and the vehicle parameters of the special vehicle are input into the controller, and then the controller outputs control instructions for automatic driving test, such as Figure 2 The throttle / brake commands, steering commands, working commands, etc. in the vehicle are generated according to the vehicle parameters. The monitoring module is used to monitor the performance of the autonomous driving system tested in the simulation scenario in combination with the sensor data to obtain performance data. The data processing module is used to evaluate the performance and emergency response capabilities of the autonomous driving system in different simulation scenarios based on the test, as well as to verify the safety and stability of the autonomous driving system in different simulation scenarios, and generate an optimization report.

[0036] Specifically, the simulation scenario includes basic elements and dynamic interactive elements. The basic elements include simulated road types, traffic flow and environmental information, and the dynamic interactive elements include simulated pedestrians, vehicles and traffic lights. In this way, the authenticity and comprehensiveness of the simulation test of the autonomous driving system are improved.

[0037] In one embodiment of the application, the environment simulation module can use Unity 3D (a game development engine) to create realistic scene elements, including basic elements and dynamic interactive elements, to highly restore various work scenarios that special vehicles may encounter.

[0038] In one embodiment of the present application, the environmental simulation module may use a physical engine (such as ODE, Bullet, etc.) to simulate the physical characteristics of the working scene of the special vehicle, such as the terrain and obstacles in the scene, so as to further improve the authenticity and credibility of the simulation scene, which is beneficial for the subsequent testing of the performance of the autonomous driving system in a complex environment and improves the reliability and accuracy of the test.

[0039] In one embodiment of the present application, the sensor data includes at least data such as obstacle distance, obstacle identification, road markings, and traffic signs.

[0040] Specifically, the sensor simulation module is also used to adjust the performance of the simulated sensor according to the environmental information if it is determined that the environmental information in the simulation scene meets the preset environmental conditions, wherein the environmental information and the preset mapping relationship are matched to determine the target performance of the sensor, and the preset mapping relationship represents the mapping relationship between the environmental information and the performance of the sensor, and the environmental information at least includes weather conditions, lighting conditions and road conditions, and the sensing performance at least includes the perception range and accuracy. In this way, the authenticity and comprehensiveness of the test are further improved.

[0041] In one embodiment of the present application, the performance of the simulated sensor is adjusted through environmental information, and the sensor module can accurately simulate the performance difference of the sensor in the vehicle under different simulation environments, and then the sensor data output by the dynamic sensor can more accurately verify the performance and robustness of the autonomous driving system in various complex simulation scenarios. In addition, the simulated sensor data can effectively reduce the safety risks and testing costs in actual testing, and the simulated sensor data and simulation scenarios are highly flexible and repeatable when adjusted, which can iterate and adjust the test conditions of the autonomous driving system more quickly, improving the test efficiency and reliability of the test.

[0042] Specifically, the sensor simulation module is also used to simulate the fault of at least one sensor in the special vehicle and generate sensor data collected by the faulty sensor.

[0043] In one embodiment of the present application, in order to test the robustness of the autonomous driving system, the sensor simulation module can simulate sensor failures, such as sensor failure, data noise during sensor acquisition, and other failures to improve the emergency response capability of the autonomous driving system.

[0044] In one embodiment of the present application, the simulation scene constructed by the environment simulation module and the sensor data simulated by the sensor simulation module can be customized and adjusted in real time according to actual needs. For example, extreme working scenes of professional vehicles are simulated, and combined with the sensor data simulated in the simulation scene, the autonomous driving system is controlled to perform a large number of repeated tests in the simulation environment. In this way, the performance of the autonomous driving system in extreme working scenes can be tested, and support can be provided for the optimization of autonomous driving. The test reliability is high, and the simulation scene during the test is controllable, repeatable, and safe, which can not only reduce the cost and time of testing, but also discover and solve potential problems in the early design stage of the autonomous driving system, and improve the development efficiency and overall performance of the system.

[0045] Specifically, the controller is also used to receive different test tasks, control the autonomous driving system to perform path planning according to sensor data and preset traffic rules, and control the autonomous driving system to generate control instructions based on the planned path and test tasks to control the dedicated vehicle model to perform autonomous driving tests in a simulation scenario.

[0046] See also Figure 3 , is a schematic diagram of an automatic driving test process shown in an exemplary embodiment of the present application. Figure 3 As shown, the input of the controller includes a simulated environment (i.e., a simulation scene), a simulated car (i.e., a special vehicle model) and sensor data. After receiving the target position to which the special vehicle model needs to drive, the controller determines the current position of the special vehicle model in the simulation scene based on the sensor data and predicts the objects around the special vehicle model, and obtains the vehicle state (i.e., the driving data of the special vehicle), and then receives or formulates different test tasks, and controls the automatic driving system to perform path planning (i.e., motion planning) in combination with the sensor data and preset traffic rules. Finally, the control instructions are generated in combination with the test tasks and the planned path and output to the special vehicle model, so that the special vehicle model automatically drives to the target position according to the planned path.

[0047] In one embodiment of the present application, the controller is responsible for allocating resources of the autonomous driving system and scheduling the execution of different test tasks, including starting and stopping tests, arranging the frequency and time of data collection, and deploying computing resources to process test data.

[0048] In one embodiment of the present application, the execution of the test task can be realized by the controller using a dynamic resource scheduling algorithm, such as a dynamic resource scheduling algorithm that can use a load balancing or task priority algorithm, as well as other algorithms. When the test task is executed based on load balancing or task priority, the controller dynamically allocates new test tasks or requests to relatively idle computing resources according to the load of computing resources (such as CPU usage, memory occupancy, network bandwidth, etc.) in the current autonomous driving system to complete the execution of the test task based on load balancing, or assigns a priority to each test task, and selects the test task with the highest priority for execution each time. The priority can be dynamically adjusted according to the status data of the autonomous driving system and the execution of the test task. For example, if a test task is not completed for a long time, its corresponding priority is increased. For test tasks with time limits, the priority can be set according to the deadline of the test task, and the test task that is about to reach the deadline has a higher priority.

[0049] In one embodiment of the present application, the controller may also include a scheduler (such as Apache Mesos, Apache Spark), which coordinates and manages multiple test tasks to ensure that the test tasks are executed according to priority or load balancing.

[0050] In one embodiment of the present application, the data received and generated by the controller can be processed and stored by a computer, and the software logic of the controller can be implemented using MATLAB (Matrix Laboratory).

[0051] Specifically, the monitoring module is used to feed back the operating data of the autonomous driving system to the controller, so that the controller adjusts the control strategy of the autonomous driving system according to the operating data, that is, generates control instructions. The operating data includes performance data and status data. The performance data includes at least path tracking accuracy, obstacle recognition rate and reaction time. The status data includes at least processor load, memory occupancy and network status.

[0052] In one embodiment of the present application, the performance data and status data of the autonomous driving system are continuously and in real time monitored by a monitoring module, and the operating data under different test scenarios are classified and stored according to the test time for subsequent analysis and backtracking.

[0053] Specifically, the monitoring module is also used to monitor the data of the simulation environment and sensor data during the test process. The data of the simulation environment, sensor data and operation data identify abnormal conditions in the operation of the autonomous driving system and generate abnormal alarms. The abnormal conditions include at least simulated sensor failures, data loss and operational errors of the autonomous driving system.

[0054] In one embodiment of the present application, by identifying abnormal conditions in the operation of the autonomous driving system through the monitoring module, potential problems and abnormalities in the operation of the autonomous driving system can be quickly discovered and diagnosed, and adjustments and improvements can be made in a timely manner, thereby effectively improving the stability and safety of the system.

[0055] Specifically, the monitoring module includes a visualization unit for visually displaying the autonomous driving test of the special vehicle model in a simulation scenario. The visualization display includes at least the simulation scenario, sensor data, and driving data of the special vehicle model during the test. The driving data includes at least throttle status, steering angle, speed, acceleration and braking status.

[0056] See also Figure 4 , which is a schematic diagram of a visualization interface shown as an exemplary embodiment of the present application. Figure 4 This is an example of visual display, showing the driving data of the vehicle in the simulation scenario, namely Figure 4 The throttle and brake status, as well as the instrument display, show the sensor data in the simulation scene, namely the radar and the obstacle vehicle. In this way, the visualization unit enables testers to intuitively and efficiently understand the entire process of the autonomous driving test, improve the transparency of the test, and testers can quickly locate the problem and repeat the test by adjusting the simulation scene or sensor parameters, thereby speeding up the test progress and improving the test efficiency.

[0057] Specifically, the data processing module is used to preprocess the test data under the same simulation scenario, perform performance analysis on the autonomous driving system based on the preprocessed test data under different simulation scenarios, generate an optimization report, and adjust the preset autonomous driving algorithm configured in the autonomous driving system based on the optimization report. In this way, through data preprocessing, noise and outliers in the test data are removed, which improves the accuracy of subsequent analysis results.

[0058] In one embodiment of the present application, statistical analysis and machine learning algorithms can be used to perform performance analysis on the autonomous driving system running in various simulation scenarios, and the performance of the autonomous driving system in different simulation scenarios can be evaluated based on the analysis results. Based on the analysis results, an optimization report is generated. The optimization report may involve optimization suggestions or strategies such as adjusting the parameters of the autonomous driving algorithm, improving the simulation configuration of the sensor, or enhancing the robustness of the autonomous driving system, so as to further improve the performance of the autonomous driving system.

[0059] In one embodiment of the present application, the data processing module can also analyze the long-term trend of the performance of the autonomous driving system based on historical test data under the same simulation scenario to detect the changing pattern of the performance of the autonomous driving system.

[0060] The special vehicle automatic driving test method provided in this application has the following advantages: first, by combining the environment simulation module and the sensor simulation module, it can restore various working scenarios that professional vehicles may encounter in actual automatic driving in a diversified manner, thereby improving the test efficiency and test accuracy of the automatic driving system in professional vehicles; second, by using the monitoring module, the performance of the automatic driving system in different simulation scenarios can be monitored in real time, so as to adjust the test strategy in time, ensure the continuity and stability of the test, and further improve the test efficiency and reliability; third, by using the data processing module, it can promote the further optimization of the automatic driving system; fourth, it avoids many challenges existing in field testing, such as high cost, long time, being affected by external factors such as weather and traffic, and causing adverse effects on the surrounding environment and other road users, which has important significance and practical application value.

[0061] See also Figure 5 , is a flow chart of a dedicated vehicle automatic driving test method shown in an exemplary embodiment of the present application. Figure 5 As shown, in an exemplary embodiment, the dedicated vehicle automatic driving test method includes at least steps S510 to S550, which are described in detail as follows:

[0062] Step S510, constructing different simulation scenarios required for special vehicle testing, where the simulation scenarios are used to simulate working scenarios of automatic driving of special vehicles;

[0063] Step S520, simulating sensor data collected by sensors in the special vehicle based on the simulation scenario;

[0064] Step S530, according to the sensor data in the simulation scenario, controlling the automatic driving system to perform an automatic driving test on the dedicated vehicle model in the same simulation scenario, where the dedicated vehicle model is obtained by simulating the dedicated vehicle, and the automatic driving system is configured on the dedicated vehicle;

[0065] Step S540, monitoring the operating data of the autonomous driving system in the test under the simulation scenario;

[0066] Step S550, performing performance analysis on the autonomous driving system according to the test data under different simulation scenarios, and generating an optimization report on the autonomous driving system based on the analysis results, wherein the test data includes at least simulation scenario data, sensor data, and operation data.

[0067] It should be noted that the special vehicle automatic driving test device provided in the above embodiment and the special vehicle automatic driving test method provided in the above embodiment belong to the same concept, and the contents of the operations performed by each module have been described in detail in the method embodiment and will not be repeated here.

[0068] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0069] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0070] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A dedicated vehicle automatic driving test system, characterized in that: The dedicated vehicle is equipped with an automatic driving system, including: An environmental simulation module, used to construct different simulation scenarios required for the special vehicle test, wherein the simulation scenarios are used to simulate the working scenarios of the automatic driving of the special vehicle; A sensor simulation module, used to simulate sensor data collected by sensors in the special vehicle based on the simulation scenario; A controller, configured to control the autonomous driving system to perform an autonomous driving test on a dedicated vehicle model in the same simulation scenario according to the sensor data in the simulation scenario, wherein the dedicated vehicle model is obtained by simulating the dedicated vehicle; A monitoring module, used to monitor the operating data of the autonomous driving system in the test under the simulation scenario; A data processing module is used to receive test data generated by different simulation scenarios during testing, perform performance analysis on the autonomous driving system according to the test data, and generate an optimization report on the autonomous driving system based on the analysis results, wherein the test data includes at least data of the simulation scenarios, the sensor data and the operation data.

2. The dedicated vehicle automatic driving test system according to claim 1, characterized in that: The simulation scenario includes basic elements and dynamic interactive elements. The basic elements include simulated road types, traffic flow and environmental information, and the dynamic interactive elements include simulated behaviors of pedestrians, vehicles and traffic lights.

3. The dedicated vehicle automatic driving test system according to claim 2, characterized in that: The sensor simulation module is also used to adjust the performance of the simulated sensor according to the environmental information if it is determined that the environmental information in the simulation scene meets the preset environmental conditions, wherein the environmental information and the preset mapping relationship are matched to determine the target performance of the sensor, and the preset mapping relationship represents the mapping relationship between the environmental information and the performance of the sensor, the environmental information includes at least weather conditions, lighting conditions and road conditions, and the sensing performance includes at least perception range and accuracy.

4. The dedicated vehicle automatic driving test system according to claim 1, characterized in that: The sensor simulation module is also used to simulate a fault of at least one of the sensors in the special vehicle, and generate sensor data collected by the faulty sensor.

5. The dedicated vehicle automatic driving test system according to claim 1, characterized in that: The controller is also used to receive different test tasks, control the autonomous driving system to perform path planning according to the sensor data and preset traffic rules, and control the autonomous driving system to generate control instructions based on the planned path and the test tasks to control the dedicated vehicle model to perform autonomous driving testing in the simulation scenario.

6. The dedicated vehicle automatic driving test system according to claim 1, characterized in that: The monitoring module is used to feed back the operating data of the autonomous driving system to the controller, so that the controller adjusts the control of the autonomous driving system according to the operating data, the operating data includes performance data and status data, the performance data includes at least path tracking accuracy, obstacle recognition rate and reaction time, and the status data includes at least processor load, memory occupancy and network status.

7. The dedicated vehicle automatic driving test system according to claim 1, characterized in that: The monitoring module is also used to monitor the data of the simulation environment and the sensor data during the test process. The data of the simulation environment, the sensor data and the operating data identify abnormal conditions in the operation of the autonomous driving system and generate abnormal alarms. The abnormal conditions at least include simulated failure of the sensor, data loss and operating errors of the autonomous driving system.

8. The dedicated vehicle automatic driving test system according to claim 1, characterized in that: The monitoring module includes a visualization unit for visually displaying the autonomous driving test of the dedicated vehicle model in the simulation scenario, wherein the visualization at least includes the simulation scenario, the sensor data, and the driving data of the dedicated vehicle model during the test, wherein the driving data at least includes the throttle status, steering angle, speed, acceleration, and braking status.

9. The dedicated vehicle automatic driving test system according to claim 1, characterized in that: The data processing module is used to preprocess the test data under the same simulation scenario, perform performance analysis on the autonomous driving system according to the preprocessed test data under different simulation scenarios to generate the optimization report, and adjust the preset autonomous driving algorithm configured in the autonomous driving system based on the optimization report.

10. A method for testing automatic driving of a special vehicle, characterized in that: Applied to the dedicated vehicle automatic driving test system as claimed in any one of claims 1 to 9, the method comprises: Constructing different simulation scenarios required for special vehicle testing, wherein the simulation scenarios are used to simulate the working scenarios of the automatic driving of the special vehicle; Simulating sensor data collected by sensors in the special vehicle based on the simulation scenario; According to the sensor data in the simulation scenario, control the automatic driving system to perform an automatic driving test on a dedicated vehicle model in the same simulation scenario, wherein the dedicated vehicle model is obtained by simulating the dedicated vehicle and the automatic driving system is configured on the dedicated vehicle; Monitoring the operating data of the autonomous driving system in the test under the simulation scenario; The performance of the autonomous driving system is analyzed according to the test data under the different simulation scenarios, and an optimization report on the autonomous driving system is generated based on the analysis results, wherein the test data at least includes the data of the simulation scenarios, the sensor data and the operation data.

Images