Automatic driving system testing method of vehicle and electronic equipment

Abstract

The invention discloses a method for testing an automatic driving system of a vehicle and electronic equipment. The method relates to the field of vehicles, and comprises the following steps: in response to a detected starting instruction of an automatic driving system corresponding to a vehicle, obtaining driving scene data of the vehicle and input data and output data of the automatic driving system, and inputting the driving scene data and the input data into a safety test model, and testing the output data by using the security test model to obtain a first test result. According to the invention, the technical problem of low safety of the automatic driving system caused by low accuracy of testing the automatic driving system in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of vehicles, and in particular to a method and electronic equipment for testing an automatic driving system of a vehicle. Background Art

[0002] With the improvement of scientific and technological levels and economic levels, facilitating users' lives based on the achievements of scientific and technological development has become one of the main purposes of improving scientific and technological levels. In recent years, the automotive industry, computer industry, and artificial intelligence industry have developed rapidly. In order to facilitate users' daily lives, vehicle autonomous driving has become one of the important research directions of some vehicle companies. Ensuring the safety of autonomous driving technology is also a prerequisite for studying autonomous driving technology. Therefore, it is necessary to test the vehicle's autonomous driving system to determine the safety of autonomous driving technology. However, the accuracy of the test of the autonomous driving system in related technologies is low, resulting in low safety of the autonomous driving system.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] An embodiment of the present invention provides a method and electronic device for testing an autonomous driving system of a vehicle, so as to at least solve the technical problem of low safety of the autonomous driving system caused by low accuracy of testing the autonomous driving system in related technologies.

[0005] According to one aspect of an embodiment of the present invention, there is provided a method for testing an autonomous driving system of a vehicle, comprising: in response to detecting a start-up instruction of an autonomous driving system corresponding to the vehicle, obtaining driving scene data of the vehicle and input data and output data of the autonomous driving system, wherein the driving scene data is used to indicate that the autonomous driving system is used to implement at least one autonomous driving function corresponding to the vehicle, the input data is used to indicate data input to the autonomous driving system, and the output data is used to indicate data output by the autonomous driving system to implement at least one autonomous driving function; inputting the driving scene data and the input data into a safety test model, testing the output data using the safety test model, and obtaining a first test result, wherein the first test result is used to indicate whether the output data meets a preset safety condition corresponding to the driving scene data.

[0006] Furthermore, the driving scenario data and the input data are input into the safety test model, and the output data is tested using the safety test model to obtain a first test result, including: inputting the driving scenario data and the input data into the safety test model, and using the safety test model to output test data that meets preset safety conditions; and testing the output data based on the test data to obtain a first test result.

[0007] Further, the output data is tested based on the test data to obtain a first test result, including: in response to the similarity between the test data and the output data being greater than a first preset similarity, determining that the first test result is that the output data meets the preset security conditions; in response to the similarity between the test data and the output data being less than or equal to the first preset similarity, determining that the first test result is that the output data does not meet the preset security conditions.

[0008] Furthermore, in response to the first test result that the output data does not meet the preset safety conditions, the method also includes: generating risk warning information based on the safety level of the driving scene data, and outputting the risk warning information on the vehicle's interactive interface; in response to receiving a shutdown instruction of the autonomous driving system, or, in response to not receiving a feedback instruction of the risk warning information after the risk warning information is displayed for a preset period of time, shutting down the autonomous driving system.

[0009] Furthermore, the method also includes: obtaining preset input data corresponding to the driving scene data; testing the input data based on the preset input data to obtain a second test result, wherein the second test result is used to indicate whether there is an abnormality in the input data.

[0010] Further, the input data is tested based on the preset input data to obtain a second test result, including: in response to the similarity between the preset input data and the input data being greater than the second preset similarity, determining that the second test result is that there is no abnormality in the input data; in response to the similarity between the preset input data and the input data being less than or equal to the second preset similarity, determining that the second test result is that there is an abnormality in the input data.

[0011] Furthermore, in response to the second test structure indicating that there is an abnormality in the input data, the method also includes: generating abnormal prompt information based on the input data, and outputting the abnormal prompt information on an interactive interface of the vehicle; in response to a feedback instruction received from the abnormal prompt information, collecting new input data based on the feedback instruction, and inputting the new input data into the autonomous driving system, so that the autonomous driving system can realize at least one autonomous driving function.

[0012] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0014] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0015] According to another aspect of the embodiments of the present invention, a computer program is provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0016] In an embodiment of the present invention, in response to detecting a start-up instruction of the vehicle corresponding to the automatic driving system, the driving scene data of the vehicle and the input data and output data of the automatic driving system are obtained, the driving scene data and the input data are input into the safety test model, and the output data is tested using the safety test model to obtain a first test result. The present application detects the start-up instruction of the automatic driving system to collect the driving scene data of the vehicle and the input and output data of the automatic driving system, and accurately tests the output data based on the driving scene data and the input data through the established safety test model to obtain an accurate first test result, thereby achieving the purpose of effectively improving the accuracy of the automatic driving system test, thereby achieving the technical effect of effectively improving the safety of the automatic driving system, and further solving the technical problem of low safety of the automatic driving system caused by low accuracy of the automatic driving system test 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 an optional method for testing an automatic driving system of a vehicle according to an embodiment of the present invention;

[0019] Figure 2 is a flowchart of another optional method for testing an automatic driving system of a vehicle according to an embodiment of the present invention;

[0020] Figure 3 It is a schematic structural diagram of another optional automatic driving system for a vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification 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 data 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to an embodiment of the present invention, an embodiment of a method for testing an automatic driving system of a vehicle 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 may be executed in an order different from that shown here.

[0024] Figure 1 is a flow chart of an optional method for testing an automatic driving system of a vehicle according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0025] Step S102, in response to detecting a start-up instruction of the autonomous driving system corresponding to the vehicle, obtaining the vehicle's driving scene data and the input data and output data of the autonomous driving system, wherein the driving scene data is used to indicate that the autonomous driving system is used to implement at least one autonomous driving function corresponding to the vehicle, the input data is used to indicate data input to the autonomous driving system, and the output data is used to indicate data output by the autonomous driving system to implement at least one autonomous driving function.

[0026] The above-mentioned vehicles refer to vehicles with automatic driving systems, which can realize automatic driving on the road through the automatic driving systems. The above-mentioned vehicles include but are not limited to: gasoline-powered cars, gasoline-powered trucks, gasoline-powered trucks, gasoline-powered buses, electric cars, electric trucks, electric trucks, electric buses, hybrid cars, hybrid trucks, hybrid trucks or hybrid buses with automatic driving functions.

[0027] The above-mentioned autonomous driving system refers to a system that integrates sensors, computer algorithms and control strategies to enable the vehicle to drive safely without direct intervention from a human driver. In this application, the above-mentioned autonomous driving system needs to be tested to determine whether the above-mentioned vehicle can drive safely when driving autonomously.

[0028] The above-mentioned start instruction refers to an instruction for the user to control the above-mentioned vehicle to start the above-mentioned automatic driving system. The user can control the operation of the above-mentioned vehicle's automatic driving system through voice commands, action commands or touch commands, and then control the above-mentioned vehicle to perform the automatic driving function.

[0029] The above-mentioned driving scene data refers to the scene data of the roads around the vehicle when the start-up command of the above-mentioned automatic driving system is detected, wherein the above-mentioned driving scene data includes but is not limited to: the route of the roads around the vehicle, the surrounding environment data of the vehicle or the road obstacle data around the vehicle, etc.

[0030] The above-mentioned input data refers to the input data of the above-mentioned automatic driving system, wherein the above-mentioned automatic driving system adjusts the state such as the posture or speed of the above-mentioned vehicle through the above-mentioned input data to control the above-mentioned vehicle to drive automatically safely and stably. The above-mentioned input data includes but is not limited to: the distance of objects around the vehicle, the speed of objects around the vehicle, the angle of objects around the vehicle, the position of the vehicle, the speed of the vehicle, the acceleration of the vehicle, the steering angle of the vehicle and other data related to the driving of the vehicle.

[0031] The above output data refers to the output data of the above automatic driving system, wherein the above automatic driving system controls the driving state of the vehicle through the above output data. The above output data includes but is not limited to: acceleration data, deceleration data, steering angle and vehicle driving direction data and other data used by the user to control the driving of the vehicle.

[0032] The above-mentioned automatic driving function refers to the vehicle function executed by the above-mentioned automatic driving system controlling the vehicle, and the above-mentioned automatic driving function refers to the function executed by the vehicle without direct intervention of the human driver. Among them, the above-mentioned automatic driving function includes but is not limited to: automatic parking, automatic driving or automatic overtaking, etc. In this application, the above-mentioned automatic driving function is realized by controlling the above-mentioned vehicle through the above-mentioned output data.

[0033] In an optional embodiment, the user can control the startup of the autonomous driving system of the above-mentioned vehicle by sending a startup command of the autonomous driving system to the vehicle. When the vehicle detects the startup command of the autonomous driving system, the scene data of the above-mentioned vehicle's driving can be obtained through sensors, and the input data of the autonomous driving system can be obtained through vehicle sensors, and the output data of the above-mentioned autonomous driving system can be obtained through vehicle sensors. In the present application, the driving scene of the vehicle corresponds to at least one autonomous driving function, and the output data of the above-mentioned autonomous driving system is used to control the above-mentioned vehicle to execute at least one autonomous driving function corresponding to the driving scene of the vehicle. Among them, the driving scene data of the vehicle can be obtained through point cloud laser radar, millimeter wave radar or ultrasonic radar, and the input data of the vehicle's autonomous driving system can be obtained through acceleration sensors; the input data of the vehicle's autonomous driving system can be obtained through acceleration sensors.

[0034] In the case where the start command is an action command, the user makes a specific action, and the camera installed inside the vehicle obtains the user's real-time image data, and transmits the user's real-time image data to the vehicle controller. The vehicle controller recognizes the above real-time image data, and after recognizing the user's specific action, generates a start command for the vehicle's automatic driving system to control the start of the automatic driving system of the above vehicle. After the start command for the vehicle's automatic driving system is generated, the vehicle's driving scene data and the input and output data of the automatic driving system are obtained.

[0035] In the case where the start command is a voice command, the user speaks a specific voice command, and the vehicle's central control screen receives the user's voice. When the vehicle's central control screen recognizes the voice command from the user's voice, it generates a start command for the vehicle's automatic driving system to control the start of the automatic driving system of the above vehicle. After the start command for the vehicle's automatic driving system is generated, the vehicle's driving scene data and the input and output data of the automatic driving system are obtained.

[0036] When the start command is a touch command, there is a pre-set virtual start button in the vehicle's central control screen for starting the vehicle's automatic driving. The user controls the start of the automatic driving system of the vehicle by touching the above virtual start button. When the vehicle's central control screen detects the user's touch command, it obtains the vehicle's driving scene data and the input and output data of the automatic driving system.

[0037] For example, Figure 2 is a flowchart of another optional method for testing an automatic driving system of a vehicle according to an embodiment of the present invention. Figure 2As shown in FIG. 1 , the vehicle's driving scene data can be obtained through multiple sensors such as the front-view sensor, rear-view sensor, perimeter sensor, millimeter wave sensor, ultrasonic sensor, and lidar sensor, and the vehicle's input data can be obtained through auxiliary modules such as the combined inertial navigation positioning module, high-precision map module, vehicle power information module, fault diagnosis module, and expected function safety monitoring module. The input data and the vehicle's driving scene data are input into the autonomous driving system, and the above output data is output to the control interface such as the human-computer interaction module and the vehicle actuator to control the vehicle to perform the autonomous driving function.

[0038] In the present application, by acquiring the vehicle's scene data and the input data of the autonomous driving system to accurately acquire the output data of the autonomous driving system, the accuracy of testing the vehicle's autonomous driving system is effectively improved, thereby improving the user experience.

[0039] Step S104, input the driving scenario data and the input data into the safety test model, use the safety test model to test the output data, and obtain a first test result, wherein the first test result is used to indicate whether the output data meets the preset safety conditions corresponding to the driving scenario data.

[0040] The above-mentioned safety test model refers to a model for pre-established test data that takes the above-mentioned driving scene data and the above-mentioned input data as input and meets safety requirements and user requirements. In this application, the above-mentioned driving scene data and the above-mentioned input data are used as input to obtain test data, and the above-mentioned output data is tested according to the above-mentioned test data to obtain a first test result.

[0041] The above-mentioned first test result refers to the result of testing whether the above-mentioned output data meets the above-mentioned preset safety conditions, wherein the above-mentioned first test result is that the output data meets the preset safety conditions, or the output data does not meet the preset safety conditions.

[0042] The above-mentioned preset safety conditions refer to pre-set conditions for determining whether the above-mentioned automatic driving system can ensure the safety of automatic driving. When the above-mentioned first test result is that the output data meets the preset safety conditions, it is determined that the user can control the vehicle for automatic driving through the above-mentioned automatic driving system. When the above-mentioned first test result is that the output data does not meet the preset safety conditions, it is determined that the user is prohibited from controlling the vehicle for automatic driving through the above-mentioned automatic driving system. Among them, the above-mentioned preset safety conditions can be set according to the state of the automatic driving system, the above-mentioned preset safety conditions can also be set manually according to experience and needs, and the above-mentioned preset safety conditions can also be set according to actual application scenarios. The above-mentioned preset safety conditions can be preset safety conditions for the vehicle state, and the above-mentioned preset safety conditions can also be preset safety conditions for vehicle driving.

[0043] In an optional embodiment, after obtaining the scenario data, input data and output data, the scenario data and input data are input into a pre-established security test model, the output of the security test model is obtained, and the above output data is tested according to the output of the security test model to obtain a first test result that the output data meets the preset security conditions, or the output data does not meet the preset security conditions.

[0044] In another optional embodiment, a test result acquisition model is pre-established, and after obtaining scenario data, input data and output data, the scenario data and input data are input into a pre-established security test model to obtain the output result of the security test model, and the output and output result of the security test model are used as input to the test result acquisition model and input into the above-mentioned test result acquisition model, and the output data output meets the preset security conditions, or the output data does not meet the first test result of the preset security conditions.

[0045] In another optional embodiment, after obtaining the scenario data, input data and output data, the scenario data and input data are input into a pre-established safety test model, the output of the safety test model is obtained, the safe vehicle state and the safe vehicle driving state are determined, and the vehicle state corresponding to the output data is compared with the safe vehicle state to obtain a first comparison result; the vehicle driving state of the output data is compared with the safe vehicle driving state to obtain a second comparison result, and based on the first comparison result and the second comparison result, it is determined that the output data meets the preset safety conditions, or the output data does not meet the first test result of the preset safety conditions.

[0046] In the present application, a pre-established safety test model is used to accurately test the output data to obtain a relatively accurate first test result, thereby effectively improving the accuracy of the test of the vehicle's autonomous driving system and enhancing the user experience.

[0047] Through the above steps, in response to detecting the start-up instruction of the vehicle corresponding to the automatic driving system, the driving scene data of the vehicle and the input data and output data of the automatic driving system are obtained, the driving scene data and the input data are input into the safety test model, and the output data is tested using the safety test model to obtain a first test result. The present application detects the start-up instruction of the automatic driving system to collect the driving scene data of the vehicle and the input and output data of the automatic driving system, and accurately tests the output data based on the driving scene data and the input data through the established safety test model to obtain an accurate first test result, thereby achieving the purpose of effectively improving the accuracy of the automatic driving system test, thereby achieving the technical effect of effectively improving the safety of the automatic driving system, and further solving the technical problem of low safety of the automatic driving system caused by the low accuracy of the automatic driving system test in the related technology.

[0048] Optionally, the driving scenario data and the input data are input into a safety test model, and the output data is tested using the safety test model to obtain a first test result, including: inputting the driving scenario data and the input data into a safety test model, and using the safety test model to output test data that meets preset safety conditions; and testing the output data based on the test data to obtain a first test result.

[0049] The above test data refers to the output data of the safety test model. In this application, the driving scene data and the input data are used as the input of the safety test model, and are input into the safety test model to output the test data. The above test data is the reference data used to determine whether the above output data meets the preset safety conditions. The above test data can be a numerical value or an interval.

[0050] In an optional embodiment, the driving scene data and the input data are used as inputs of the safety test model, input into the safety test model, and the test data is output. After the test data is obtained, the output data is tested with the test data as a reference to obtain a first test result.

[0051] In the case where the test data is numerical, the driving scene data and the input data are used as inputs of the safety test model, input into the safety test model, and the test data is output. After the test data is obtained, the test data is compared with the output data to obtain a comparison result. When the comparison result is less than a preset deviation, it is determined that the first test result is that the output data meets the preset safety condition. When the comparison result is greater than or equal to the preset deviation, it is determined that the first test result is that the output data does not meet the preset safety condition.

[0052] In the case where the test data is an interval, the driving scene data and the input data are used as inputs of the safety test model, input into the safety test model, and the test data is output. After the test data is obtained, it is determined whether the output data falls into the interval of the test data. When the output data falls into the interval of the test data, it is determined that the first test result is that the output data meets the preset safety condition. When the output data does not fall into the interval of the test data, it is determined that the first test result is that the output data does not meet the preset safety condition.

[0053] In the present application, test data is obtained to test the above output data. Since the test data load safety preset conditions, the credibility of the test of the vehicle's automatic driving system is effectively improved, and the user experience is improved.

[0054] Optionally, the output data is tested based on the test data to obtain a first test result, including: in response to the similarity between the test data and the output data being greater than a first preset similarity, determining that the first test result is that the output data meets preset security conditions; in response to the similarity between the test data and the output data being less than or equal to the first preset similarity, determining that the first test result is that the output data does not meet preset security conditions.

[0055] The first preset similarity refers to the similarity between the preset test data and the output data. In the present application, the first preset similarity is used to determine whether the output data meets the preset safety condition. The first preset similarity can be set according to the state of the automatic driving system, the first preset similarity can also be set manually according to experience and needs, and the first preset similarity can also be set according to the actual application scenario.

[0056] In an optional embodiment, after obtaining the test data and the output data, the Jaccard similarity coefficient between the test data and the output data can be determined to determine the similarity between the test data and the output data, and the similarity is compared with a first preset similarity. When the similarity between the test data and the output data is greater than the first preset similarity, the first test result is determined to be that the output data meets the preset safety condition; when the similarity between the test data and the output data is less than or equal to the first preset similarity, the first test result is determined to be that the output data does not meet the preset safety condition. The similarity between the test data and the output data can also be determined by the Manhattan distance, the Pearson correlation coefficient, or the Spearman rank correlation coefficient.

[0057] In another optional embodiment, a similarity determination model may be pre-established, and after obtaining the test data and the output data, the test data and the output data are used as inputs of the similarity determination model, input into the similarity determination model, output the similarity between the test data and the output data, and compare the similarity with a first preset similarity. When the similarity between the test data and the output data is greater than the first preset similarity, the first test result is determined to be that the output data meets the preset security conditions; when the similarity between the test data and the output data is less than or equal to the first preset similarity, the first test result is determined to be that the output data does not meet the preset security conditions.

[0058] In the present application, the similarity between the test data and the output data is used to determine whether the output data meets the preset safety conditions, thereby effectively improving the rate of determining whether the output data meets the preset safety conditions, thereby effectively improving the rate of testing the vehicle's autonomous driving system and improving the user experience.

[0059] Optionally, in response to the first test result that the output data does not meet preset safety conditions, the method also includes: generating risk warning information based on the safety level of the driving scene data, and outputting the risk warning information on the vehicle's interactive interface; in response to receiving a shutdown instruction of the autonomous driving system, or, in response to not receiving a feedback instruction of the risk warning information after the risk warning information is displayed for a preset period of time, shutting down the autonomous driving system.

[0060] The above safety level refers to the level of the pre-set driving scene. The higher the safety level, the safer the driving, and the lower the safety level, the more dangerous the driving. The above safety level is used to remind the user of the driving scene around, to remind the user that the automatic driving is not possible and the user should pay attention to safety when driving by himself. Among them, the above safety level can be set according to the vehicle status, the above safety level can also be set manually according to experience and needs, and the above safety level can also be set according to the actual application scenario.

[0061] The above-mentioned risk warning information refers to the warning information used to remind the user that the automatic driving is not possible and the user should pay attention to safety when driving by himself, wherein the above-mentioned risk warning information may be: voice information, vibration information or image information, etc. Different risk warning information is generated according to different safety levels.

[0062] The above-mentioned shutdown instruction refers to an instruction used to shut down the automatic driving system, wherein the above-mentioned shutdown instruction can be: a voice command, an action command or a touch command.

[0063] In an optional embodiment, when the first test result is that the output data does not meet the preset safety conditions, the vehicle is prohibited from automatically driving, and risk warning information corresponding to the safety level is generated based on the safety level of the driving scene data, and the risk warning information is output on the vehicle's interactive interface. After receiving the risk warning information, the user can turn off the automatic driving system through a shutdown command. If the user's shutdown command is not received during the preset time of the risk warning information display, the automatic driving system will be automatically shut down. Among them, the user can apply a shutdown command to the vehicle through a voice command, a motion command, or a touch command.

[0064] In this application, by shutting down the command, when the driving scene data is risky, the user's safety level can be promptly reminded, which effectively improves the reliability of the vehicle's automatic driving system, improves the safety of vehicle driving, and improves the user experience.

[0065] Optionally, the method further includes: obtaining preset input data corresponding to the driving scene data; testing the input data based on the preset input data to obtain a second test result, wherein the second test result is used to indicate whether there is an abnormality in the input data.

[0066] The above-mentioned preset input data refers to pre-set input data. Since the vehicle state may be abnormal during driving, and in order to ensure safety when the vehicle state is abnormal, the use of the automatic driving function is also prohibited. It is necessary to determine whether the input data is abnormal. In this application, the input data is tested by the above-mentioned preset input data. Among them, the above-mentioned preset input data can be set according to the driving scene, the above-mentioned preset input data can also be set manually according to experience and needs, and the above-mentioned preset input data can also be set according to the actual application scenario.

[0067] The second test result is a test result for testing whether the input data is abnormal, wherein the second test result is: the input data is abnormal, or the input data is not abnormal.

[0068] In an optional embodiment, preset input data corresponding to the current driving scene can be obtained through driving scene data, and the input data can be tested according to the preset input data to obtain a second test result indicating that the input data is abnormal or that the input data does not have an abnormality.

[0069] In another optional embodiment, a preset input data determination model may be pre-established, and the driving scene data is used as the input of the preset input data determination model, input into the preset input data determination model, and the preset input data is output. After the preset input data is obtained, the input data is tested according to the preset input data to obtain a second test result indicating that the input data is abnormal or that the input data is not abnormal.

[0070] In this application, the input data is tested by pre-setting input data to prevent abnormal input data from causing danger during automatic driving of the vehicle, thereby effectively improving the reliability of the vehicle's automatic driving system, improving the safety of vehicle driving, and improving the user experience.

[0071] Optionally, the input data is tested based on preset input data to obtain a second test result, including: in response to the similarity between the preset input data and the input data being greater than a second preset similarity, determining that the second test result is that there is no abnormality in the input data; in response to the similarity between the preset input data and the input data being less than or equal to the second preset similarity, determining that the second test result is that there is an abnormality in the input data.

[0072] In an optional embodiment, after obtaining the preset input data and the input data, the Jaccard similarity coefficient between the preset input data and the input data can be determined to determine the similarity between the preset input data and the input data, and the similarity is compared with the second preset similarity. When the similarity between the preset input data and the input data is greater than the second preset similarity, the second test result is determined to be that the input data does not have an abnormality; when the similarity between the preset input data and the input data is less than or equal to the second preset similarity, the second test result is determined to be that the input data has an abnormality. The similarity between the test data and the output data can also be determined by the Manhattan distance, the Pearson correlation coefficient, or the Spearman rank correlation coefficient.

[0073] In another optional embodiment, a similarity determination model may be pre-established, and after obtaining the preset input data and the input data, the preset input data and the input data are used as inputs of the above-mentioned similarity determination model, input into the above-mentioned similarity determination model, output the similarity between the preset input data and the input data, and compare the similarity with a second preset similarity. When the similarity between the preset input data and the input data is greater than the second preset similarity, it is determined that the second test result is that there is no abnormality in the input data; when the similarity between the preset input data and the input data is less than or equal to the second preset similarity, it is determined that the second test result is that there is an abnormality in the input data.

[0074] In the present application, by obtaining the similarity between the output preset input data and the input data, and combining it with the second preset similarity, the second test result can be quickly determined, which effectively improves the rate of determining the second test result, improves the rate of testing the vehicle's automatic driving system, and improves the user experience.

[0075] Optionally, in response to the second test result indicating that there is an abnormality in the input data, the method further includes: generating abnormal prompt information based on the input data, and outputting the abnormal prompt information on an interactive interface of the vehicle; in response to a feedback instruction received from the abnormal prompt information, collecting new input data based on the feedback instruction, and inputting the new input data into the autonomous driving system, so that the autonomous driving system can realize at least one autonomous driving function.

[0076] The above-mentioned abnormal prompt information refers to prompt information used to prompt the user that there is an abnormality in the input data, wherein the above-mentioned abnormal prompt information can be sound information, vibration information or image information, etc.

[0077] In an optional embodiment, when the second test result is that the input data is abnormal, abnormal prompt information is generated based on the input data, and the abnormal prompt information is output on the interactive interface of the vehicle to prompt the user that the input data is abnormal. After receiving the above abnormal prompt information, the user can input a feedback instruction to the vehicle to retry to start the vehicle's automatic driving. When the vehicle controller detects the feedback instruction of the abnormal prompt information, new input data is collected based on the feedback instruction, and the new input data is input into the automatic driving system, so that the automatic driving system realizes at least one automatic driving function.

[0078] In the present application, the vehicle's automatic driving function can be retried through feedback instructions to prevent abnormalities in vehicle input data due to reasons such as the camera device being covered. The vehicle's automatic driving function can be retried after timely troubleshooting, effectively improving the reliability of the test vehicle's automatic driving system, improving the applicability of the vehicle's automatic driving system, and improving the user experience.

[0079] According to another aspect of an embodiment of the present invention, there is also provided an automatic driving system for a vehicle, which can execute the automatic driving system testing method for a vehicle of the above embodiment, wherein: Figure 3 is a schematic diagram of the structure of another optional automatic driving system for a vehicle according to an embodiment of the present invention, such as Figure 3 As shown, the system includes: an acquisition module 30, which is used to obtain the vehicle's driving scene data and the input data and output data of the automatic driving system in response to detecting a start-up instruction of the vehicle corresponding to the automatic driving system, wherein the driving scene data is used to indicate that the automatic driving system is used to realize at least one automatic driving function corresponding to the vehicle, the input data is used to indicate the data input to the automatic driving system, and the output data is used to indicate the data output by the automatic driving system to realize at least one automatic driving function; a testing module, which is used to input the driving scene data and the input data into a safety test model, and use the safety test model to test the output data to obtain a first test result, wherein the first test result is used to indicate whether the output data meets the preset safety conditions corresponding to the driving scene data.

[0080] Optionally, the test module includes: an input unit, used to input driving scenario data and input data into a safety test model, and use the safety test model to output test data that meets preset safety conditions; a first test unit, used to test the output data based on the test data to obtain a first test result.

[0081] Optionally, the first test unit includes: a first comparison subunit, used to determine that the first test result is that the output data meets the preset security conditions in response to the similarity between the test data and the output data being greater than a first preset similarity; and a second comparison subunit, used to determine that the first test result is that the output data does not meet the preset security conditions in response to the similarity between the test data and the output data being less than or equal to the first preset similarity.

[0082] Optionally, in response to the first test result that the output data does not meet the preset safety conditions, the system also includes: an output module, used to generate risk warning information based on the safety level of the driving scene data, and output the risk warning information on the vehicle's interactive interface; a shutdown module, used to shut down the automatic driving system in response to receiving a shutdown instruction of the automatic driving system, or in response to not receiving a feedback instruction of the risk warning information after the risk warning information is displayed for a preset period of time.

[0083] Optionally, the system also includes: a preset input data module, used to obtain preset input data corresponding to the driving scene data; a test result module, used to test the input data based on the preset input data to obtain a second test result, wherein the second test result is used to indicate whether there is an abnormality in the input data.

[0084] Optionally, the test result module includes: a first comparison unit, used to determine that the second test result is that there is no abnormality in the input data in response to the similarity between the preset input data and the input data being greater than a second preset similarity; a second comparison unit, used to determine that the second test result is that there is an abnormality in the input data in response to the similarity between the preset input data and the input data being less than or equal to the second preset similarity.

[0085] Optionally, in response to the second test result indicating that there is an abnormality in the input data, the system also includes: a generation module for generating abnormal prompt information based on the input data, and outputting the abnormal prompt information on the vehicle's interactive interface; a feedback module for responding to a feedback instruction received from the abnormal prompt information, collecting new input data based on the feedback instruction, and inputting the new input data into the autonomous driving system, so that the autonomous driving system can realize at least one autonomous driving function.

[0086] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention when running.

[0087] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0088] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0089] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0090] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0091] 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 schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, 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.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0093] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] 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, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a 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 and other media that can store program codes.

[0095] 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 principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for testing an automatic driving system of a vehicle, characterized in that: include: In response to detecting a start instruction of the autonomous driving system corresponding to the vehicle, obtaining driving scene data of the vehicle and input data and output data of the autonomous driving system, wherein the driving scene data is used to indicate that the autonomous driving system is used to implement at least one autonomous driving function corresponding to the vehicle, the input data is used to indicate data input to the autonomous driving system, and the output data is used to indicate data output by the autonomous driving system to implement the at least one autonomous driving function; The driving scenario data and the input data are input into a safety test model, and the output data is tested using the safety test model to obtain a first test result, wherein the first test result is used to indicate whether the output data meets a preset safety condition corresponding to the driving scenario data.

2. The method for testing the automatic driving system of a vehicle according to claim 1, characterized in that: Inputting the driving scenario data and the input data into a safety test model, and using the safety test model to test the output data to obtain a first test result, including: Inputting the driving scenario data and the input data into a safety test model, and using the safety test model to output test data that meets the preset safety conditions; The output data is tested based on the test data to obtain the first test result.

3. The method for testing the automatic driving system of a vehicle according to claim 2, characterized in that: Testing the output data based on the test data to obtain the first test result includes: In response to the similarity between the test data and the output data being greater than a first preset similarity, determining that the first test result is that the output data meets the preset safety condition; In response to the similarity between the test data and the output data being less than or equal to the first preset similarity, determining the first test result as the output data not meeting the preset safety condition.

4. The method for testing an automatic driving system of a vehicle according to any one of claims 1 to 3, characterized in that: In response to the first test result being that the output data does not meet the preset safety condition, the method further includes: generating risk warning information based on the safety level of the driving scenario data, and outputting the risk warning information on an interactive interface of the vehicle; In response to receiving a shutdown instruction of the autonomous driving system, or in response to not receiving a feedback instruction of the risk warning information after the risk warning information is displayed for a preset period of time, the autonomous driving system is shut down.

5. The method for testing the automatic driving system of a vehicle according to claim 1, characterized in that: The method further comprises: Acquire preset input data corresponding to the driving scene data; The input data is tested based on the preset input data to obtain a second test result, wherein the second test result is used to indicate whether the input data is abnormal.

6. The method for testing the automatic driving system of a vehicle according to claim 5, characterized in that: Testing the input data based on the preset input data to obtain a second test result includes: In response to the similarity between the preset input data and the input data being greater than a second preset similarity, determining that the second test result is that the input data does not have the anomaly; In response to the similarity between the preset input data and the input data being less than or equal to the second preset similarity, it is determined that the second test result is that the input data has the anomaly.

7. The method for testing the automatic driving system of a vehicle according to claim 5 or 6, characterized in that: In response to the second test result indicating that the input data has the anomaly, the method further includes: generating abnormal prompt information based on the input data, and outputting the abnormal prompt information on an interactive interface of the vehicle; In response to receiving a feedback instruction of the abnormal prompt information, new input data is collected based on the feedback instruction, and the new input data is input into the automatic driving system, so that the automatic driving system realizes at least one automatic driving function.

8. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 7 when running.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images