A safety assessment method, system, storage medium and device for an autonomous driving vehicle

Abstract

The present invention provides a safety assessment method, system, storage medium and device for an autonomous driving vehicle, the method comprising obtaining a standard file for assessing an autonomous driving vehicle; when the autonomous driving vehicle is driving, obtaining real data of the autonomous driving vehicle in multiple driving environments, the real data at least including vehicle driving data and traffic environment data when the vehicle is driving; performing virtual simulation based on each vehicle driving data and traffic environment data to obtain a virtual test scene corresponding to each driving environment; evaluating a target vehicle in combination with the standard file and each virtual test scene to obtain multiple virtual assessment reports for a comprehensive assessment of the current target vehicle. Through this setting, when performing a safety assessment on a vehicle, a comprehensive safety assessment of the vehicle can be performed by simulating multiple virtual test scenes and combining the standard file at the same time.

Description

Technical Field

[0001] The present invention relates to the field of vehicle system assessment technology, and in particular to a safety assessment method, system, storage medium and device for an autonomous driving vehicle. Background Art

[0002] Self-driving cars rely on artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to work together, allowing computers to automatically and safely operate motor vehicles without any active human operation.

[0003] To evaluate the safety of autonomous vehicles (AVs), evaluation standards in this field are usually used, including ISO26262, ISO21448, ISO26262 and ISO21448. The above evaluation standards, such as ISO26262, only evaluate the safety of a given design and do not include autonomous vehicles with safe designs; ISO21448 evaluation is related to environmental perception, but environmental sensors usually have inherent limitations that may cause unsafe AV behavior; ISO26262 and ISO 21448 do not provide an evaluation method for behavioral safety in combination with traffic road conditions;

[0004] Therefore, the existing evaluation methods can only evaluate part of the safety performance of AV and cannot conduct a systematic evaluation, resulting in inaccurate and unreliable evaluation results. Summary of the invention

[0005] Based on this, the purpose of the present invention is to provide a safety assessment method, system, storage medium and device for an autonomous driving vehicle, so as to solve the technical problem that the existing assessment methods in the background technology can only evaluate part of the safety performance of the AV and cannot perform a systematic assessment, resulting in the inaccuracy and reliability of the assessment results.

[0006] A first aspect of the present invention is to provide a safety assessment method for an autonomous driving vehicle, the assessment method comprising:

[0007] Obtain standard profiles for evaluating autonomous vehicles;

[0008] When the autonomous driving vehicle is driving, obtaining real data of the autonomous driving vehicle in multiple driving environments, the real data at least including vehicle driving data and traffic environment data when the vehicle is driving;

[0009] Performing virtual simulation according to each of the vehicle driving data and the traffic environment data to obtain a virtual test scene corresponding to each of the driving environments;

[0010] The target vehicle is evaluated in combination with the standard file and each virtual test scenario to obtain multiple virtual evaluation reports for a comprehensive evaluation of the current target vehicle.

[0011] Further, after the step of obtaining a plurality of virtual assessment reports for comprehensive assessment of the current target vehicle, the method further includes:

[0012] The results corresponding to the multiple virtual assessment reports are combined to obtain a virtual overall assessment report that comprehensively assesses the current target vehicle.

[0013] Furthermore, in the step of evaluating the target vehicle in combination with the standard file and each virtual test scenario, the following is further included:

[0014] Classify each of the virtual test scenarios according to its type;

[0015] At least one virtual test scenario of each type is selected to evaluate the target vehicle to obtain multiple virtual evaluation reports evaluated by each type of virtual test scenario, and the results corresponding to the multiple virtual evaluation reports are combined to obtain a virtual total evaluation report that comprehensively evaluates the current target vehicle.

[0016] Furthermore, after the step of performing virtual simulation according to each of the vehicle driving data and the traffic environment data to obtain a virtual test scene corresponding to each of the driving environments, the method further includes:

[0017] Analyzing the vehicle driving data and traffic environment data corresponding to each of the virtual test scenarios, and clustering the vehicle driving data or traffic environment data corresponding to any one of the virtual test scenarios with the vehicle driving data or traffic environment data corresponding to another of the virtual test scenarios;

[0018] To obtain at least one other virtual test scene in which the vehicle driving data and the traffic environment data in the determined plurality of virtual test scenes are clustered with each other.

[0019] Further, after the step of obtaining at least one other virtual test scene in which the vehicle driving data and the traffic environment data in the determined plurality of virtual test scenes are clustered with each other, the method further includes:

[0020] The target vehicle is evaluated according to the virtual test scenarios in the other virtual test scenarios to obtain other evaluation reports corresponding to the other virtual test scenarios, and the other evaluation reports are integrated into the virtual overall evaluation report.

[0021] Further, after the step of obtaining a plurality of virtual assessment reports for comprehensive assessment of the current target vehicle, the method further includes:

[0022] The target vehicle is evaluated in multiple real test scenarios, where each real test scenario corresponds to each virtual test scenario;

[0023] A real safety assessment is performed on the target vehicle in combination with each of the real test scenarios and the standard files corresponding to the real test scenarios, and multiple real safety assessments are combined to obtain a real safety assessment report that comprehensively evaluates the current target vehicle.

[0024] Furthermore, after the step of obtaining a true safety assessment report that comprehensively assesses the current target vehicle, the method further includes:

[0025] The real safety assessment report and the virtual overall assessment report are compared to determine the similarity between the real safety assessment report and the virtual overall assessment report, and the authenticity of the virtual overall assessment report is comprehensively judged based on the similarity.

[0026] A second aspect of the present invention is to provide a safety assessment system for an autonomous driving vehicle, the system comprising:

[0027] An acquisition module for acquiring standard archives for evaluating autonomous vehicles;

[0028] Also used for obtaining real data of the autonomous driving vehicle in multiple driving environments when the autonomous driving vehicle is driving, the real data at least including vehicle driving data and traffic environment data when the vehicle is driving;

[0029] A simulation module, used for performing virtual simulation according to each of the vehicle driving data and the traffic environment data, so as to obtain a virtual test scene corresponding to each of the driving environments;

[0030] The evaluation module is used to evaluate the target vehicle in combination with the standard file and each virtual test scenario to obtain multiple virtual evaluation reports for comprehensive evaluation of the current target vehicle.

[0031] A third aspect of the present invention is to provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned safety assessment method for an autonomous driving vehicle.

[0032] The fourth aspect of the present invention is to provide a safety assessment device for an autonomous driving vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned safety assessment method for the autonomous driving vehicle when executing the program.

[0033] Compared with the prior art, the safety assessment method, system, storage medium and device of an autonomous driving vehicle shown in the present invention have the following beneficial effects:

[0034] In a safety assessment method for an autonomous driving vehicle provided by the present invention, a standard file for evaluating the autonomous driving vehicle is first obtained; when the autonomous driving vehicle is driving, real data of the autonomous driving vehicle in multiple driving environments is obtained, and the real data at least includes vehicle driving data when the vehicle is driving and traffic environment data when the vehicle is driving; virtual simulation is performed according to each vehicle driving data and traffic environment data to obtain a virtual test scene corresponding to each driving environment; the target vehicle is evaluated in combination with the standard file and each virtual test scene to obtain multiple virtual assessment reports for comprehensive assessment of the current target vehicle. Through this setting, when performing a safety assessment on the vehicle, a comprehensive safety assessment of the vehicle can be performed through the simulated multiple virtual test scenes and combined with the standard file, which solves the problem that the prior art can only evaluate part of the safety performance of AV and cannot perform a systematic assessment, resulting in the inaccuracy and reliability of the assessment results. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a flow chart of a safety assessment method for an autonomous driving vehicle in a first embodiment of the present invention;

[0036] Figure 2 A schematic diagram of a safety assessment system for an autonomous driving vehicle in a second embodiment of the present invention;

[0037] Figure 3 Schematic diagram of a safety assessment device for an autonomous driving vehicle in the third embodiment of the present invention.

[0038] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0039] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0040] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0042] First embodiment

[0043] See also Figure 1 , which shows a safety assessment method for an autonomous driving vehicle in a first embodiment of the present invention, and the assessment method includes:

[0044] S01, obtain standard files for evaluating autonomous vehicles.

[0045] It should be noted that, in this embodiment, the standard file may have an AV developer safety standard to create a safety file. It should be noted that AV is an autonomous driving vehicle technology, which is collectively referred to as AV in the following statements.

[0046] Specifically, the standard dossier is a wide range of information provided by developers about the safety measures of AV automation systems. The information contained in the safety dossier can make a qualitative assessment of the functional safety of the autonomous vehicle and make a decision on whether to continue the safety assessment process; it can provide an in-depth understanding of the test scenarios that may be particularly challenging for autonomous vehicles or automation system components, and the threats that these components pose when failures occur, such as "single point failures", and define and select simulation test scenarios for scenario verification components in the assessment process.

[0047] S02, when the autonomous driving vehicle is driving, obtaining real data of the autonomous driving vehicle in multiple driving environments, the real data at least including vehicle driving data when the vehicle is driving and traffic environment data when the vehicle is driving.

[0048] Specifically, the autonomous driving vehicle is a determined and qualified vehicle, and the vehicle travels according to the determined autonomous driving vehicle and obtains real data.

[0049] To facilitate understanding of this case, in the presence of an autonomous vehicle, autonomous vehicle driving data is obtained. The real data includes vehicle driving data and traffic environment data.

[0050] It should be noted that vehicle driving data may include vehicle positioning, driving speed, acceleration, steering angle, etc.; traffic environment data may include traffic signs, moving vehicles, pedestrians, obstacles, road markings, etc. The above vehicle driving data and traffic environment data are not limited to real data, and can also be other real data, such as weather, road type, road conditions, etc. Weather classification may include sunny days, rainy days, snowy days, etc.; road conditions may be the surrounding target conditions of the current autonomous driving vehicle, including no target, approaching target, distant target, etc.; road conditions may include expressways, urban roads, factory and mine roads, forest roads, rural roads, etc.

[0051] S03, performing virtual simulation according to each vehicle driving data and traffic environment data to obtain a virtual test scene corresponding to each driving environment.

[0052] Specifically, a virtual test scene can be constructed based on real data, and the virtual test scene can be a virtual test scene established by a test scene for testing an autonomous driving vehicle.

[0053] S04, evaluating the target vehicle in combination with the standard file and each virtual test scenario to obtain a plurality of virtual evaluation reports for comprehensive evaluation of the current target vehicle.

[0054] Specifically, when conducting a safety assessment of a vehicle, a comprehensive safety assessment of the vehicle can be performed by simulating multiple virtual test scenarios and combining them with standard files. This solves the problem that the existing technology can only evaluate part of the safety performance of the AV and cannot conduct a systematic assessment, resulting in inaccurate and unreliable assessment results.

[0055] In addition, in some preferred embodiments, after the step of obtaining multiple virtual assessment reports for comprehensive assessment of the current target vehicle, the method further includes:

[0056] The results corresponding to the multiple virtual assessment reports are combined to obtain a virtual total assessment report that comprehensively evaluates the current target vehicle.

[0057] Specifically, the virtual overall assessment report is a comprehensive report of all safety assessment reports of the target vehicle, which is convenient for staff to analyze the results in some practical situations.

[0058] It should be noted that in some special driving environments, higher requirements are placed on testing conditions. For example, testing vehicle safety in some extreme driving environments requires obtaining real data of autonomous driving vehicles in multiple driving environments in order to establish a virtual test scenario. However, multiple extreme driving environments will result in higher costs for obtaining real data.

[0059] In some other preferred embodiments, after performing virtual simulation according to each vehicle driving data and traffic environment data to obtain a virtual test scene corresponding to each driving environment, the method further includes:

[0060] Analyze the vehicle driving data and traffic environment data corresponding to each virtual test scene, and cluster the vehicle driving data or traffic environment data corresponding to any virtual test scene with the vehicle driving data or traffic environment data corresponding to another virtual test scene;

[0061] To obtain at least one other virtual test scenario in which the vehicle driving data and the traffic environment data in the determined plurality of virtual test scenarios are clustered with each other;

[0062] The target vehicle is evaluated according to the virtual test scenarios in other virtual test scenarios to obtain other evaluation reports corresponding to the other virtual test scenarios, and the other evaluation reports are integrated into the virtual overall evaluation report.

[0063] Specifically, to facilitate understanding of this case, vehicle driving data can be divided into multiple events. For example, the vehicle ahead on the road slows down and stepping on the brake pedal may cause a mode switch, which can be regarded as an event; or traffic environment data can be divided into multiple events, such as weather conditions, road conditions and surrounding environment conditions, various types of autonomous driving states trigger various events.

[0064] The above time is clustered into complete scenarios, i.e. other virtual test scenarios. For example, the deceleration of vehicles ahead on the road can be clustered with weather conditions, the deceleration of vehicles ahead on the road can be clustered with weather conditions and road conditions, or the normal driving of vehicles can be clustered with weather conditions and surrounding environment, etc., so that other test scenarios can be constructed through the determined virtual test scenarios, thereby greatly saving the virtual steps of the virtual test scenarios and the data acquisition before obtaining the virtual test scenarios. At the same time, in some extreme test environments, other extreme test environments can be generated correspondingly through one real data acquisition.

[0065] In addition, in some preferred embodiments, the step of evaluating the target vehicle in combination with the standard file and each virtual test scenario also includes: classifying according to the type of each virtual test scenario;

[0066] At least one virtual test scenario of each type is selected to evaluate the target vehicle to obtain multiple virtual evaluation reports evaluated by each type of virtual test scenario, and the results corresponding to the multiple virtual evaluation reports are combined to obtain a virtual total evaluation report that comprehensively evaluates the current target vehicle.

[0067] Through probability distribution, typical and extreme scenarios are extracted and used as test scenarios to ensure that the test scenarios cover all possibilities, greatly reducing the number of evaluations.

[0068] In addition, to ensure the authenticity of the virtual total assessment report, after the step of obtaining multiple virtual assessment reports for a comprehensive assessment of the current target vehicle, it also includes:

[0069] The target vehicle is evaluated in multiple real test scenarios, where each real test scenario corresponds to each virtual test scenario;

[0070] Combine each real test scenario with the standard file corresponding to the real test scenario to conduct a real safety assessment on the target vehicle, and combine multiple real safety assessments to obtain a real safety assessment report that comprehensively evaluates the current target vehicle;

[0071] The real safety assessment report and the virtual overall assessment report are compared to determine the similarity between the real safety assessment report and the virtual overall assessment report, and the authenticity of the virtual overall assessment report is comprehensively judged based on the similarity.

[0072] That is, if the similarity is high, the virtual overall assessment report of the current vehicle is judged to be the final safety report.

[0073] In summary, the safety assessment method for an autonomous driving vehicle shown in this embodiment has at least the following beneficial effects compared with the safety assessment method for an autonomous driving vehicle in the prior art:

[0074] In a safety assessment method for an autonomous driving vehicle provided by the present invention, a standard file for evaluating the autonomous driving vehicle is first obtained; when the autonomous driving vehicle is driving, real data of the autonomous driving vehicle in multiple driving environments is obtained, and the real data at least includes vehicle driving data when the vehicle is driving and traffic environment data when the vehicle is driving; virtual simulation is performed according to each vehicle driving data and traffic environment data to obtain a virtual test scene corresponding to each driving environment; the target vehicle is evaluated in combination with the standard file and each virtual test scene to obtain multiple virtual assessment reports for comprehensive assessment of the current target vehicle. Through this setting, when performing a safety assessment on the vehicle, a comprehensive safety assessment of the vehicle can be performed through the simulated multiple virtual test scenes and combined with the standard file, which solves the problem that the prior art can only evaluate part of the safety performance of AV and cannot perform a systematic assessment, resulting in the inaccuracy and reliability of the assessment results.

[0075] Second embodiment

[0076] Another aspect of the present invention is to provide a safety assessment system for an autonomous driving vehicle. Figure 2, which shows a safety assessment system for an autonomous driving vehicle in a second embodiment of the present invention. The safety assessment system for an autonomous driving vehicle includes:

[0077] An acquisition module 11 is used to acquire a standard file for evaluating an autonomous driving vehicle;

[0078] It is also used to obtain real data of the autonomous driving vehicle in multiple driving environments when the autonomous driving vehicle is driving, and the real data at least includes vehicle driving data when the vehicle is driving and traffic environment data when the vehicle is driving;

[0079] A simulation module 12, for performing virtual simulation according to each vehicle driving data and traffic environment data to obtain a virtual test scene corresponding to each driving environment;

[0080] The evaluation module 13 is used to evaluate the target vehicle in combination with the standard file and each virtual test scenario to obtain a plurality of virtual evaluation reports for comprehensive evaluation of the current target vehicle.

[0081] Third embodiment

[0082] Another aspect of the present invention is to provide a safety assessment device for an autonomous driving vehicle, see Figure 3 , shown is a safety assessment device for an autonomous driving vehicle in the third embodiment of the present invention, including a memory 200, a processor 100, and a computer program 300 stored in the memory and executable on the processor. When the processor 100 executes the computer program 300, the safety assessment method for the autonomous driving vehicle as described above is implemented.

[0083] Among them, the safety assessment device of the autonomous driving vehicle can specifically be a computer, a safety assessment device of the autonomous driving vehicle, etc., and the processor 100 in some embodiments can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, which is used to run the program code stored in the memory 200 or process data, such as executing access restriction programs, etc.

[0084] The memory 200 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 200 may be an internal storage unit of the safety assessment device of the autonomous driving vehicle, such as a hard disk of the safety assessment device of the autonomous driving vehicle. In other embodiments, the memory 200 may also be an external storage device of the safety assessment device of the autonomous driving vehicle, such as a plug-in hard disk equipped on the safety assessment device of the autonomous driving vehicle, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDiɡital, SD) card, a flash card (FlashCard), etc. Further, the memory 200 may also include both an internal storage unit and an external storage device of the safety assessment device of the autonomous driving vehicle. The memory 200 can be used not only to store application software and various types of data installed in the safety assessment device of the autonomous driving vehicle, but also to temporarily store data that has been output or is to be output.

[0085] It should be pointed out that Figure 3 The structure shown does not constitute a limitation on the safety assessment device for an autonomous vehicle. In other embodiments, the safety assessment device for an autonomous vehicle may include fewer or more components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0086] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the safety assessment method for an autonomous driving vehicle as described above.

[0087] Those skilled in the art will appreciate that the logic or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable storage medium for use by an instruction execution system, device or apparatus (e.g., based on a computer system, including a processor system or other system that can fetch instructions from an instruction execution system, device or apparatus and execute an instruction system), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0088] More specific examples (a non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in another suitable manner as necessary, and then stored in a computer memory.

[0089] It should be understood that the various parts of the present invention can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PɡA), a field programmable gate array (FPɡA), etc.

[0090] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0091] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A safety assessment method for autonomous driving vehicles, It is characterized in that The evaluation methods include: Obtain standard profiles for evaluating autonomous vehicles; When the autonomous driving vehicle is driving, obtaining real data of the autonomous driving vehicle in multiple driving environments, the real data at least including vehicle driving data and traffic environment data when the vehicle is driving; Performing virtual simulation according to each of the vehicle driving data and the traffic environment data to obtain a virtual test scene corresponding to each of the driving environments; Evaluate the target vehicle in combination with the standard file and each virtual test scenario to obtain multiple virtual evaluation reports for comprehensive evaluation of the current target vehicle; After the step of obtaining multiple virtual assessment reports for comprehensive assessment of the current target vehicle, the method further includes: Combining the results corresponding to the plurality of virtual assessment reports to obtain a virtual total assessment report that comprehensively assesses the current target vehicle; The step of evaluating the target vehicle in combination with the standard file and each virtual test scenario also includes: Classify each of the virtual test scenarios according to its type; Selecting at least one virtual test scenario of each type to evaluate the target vehicle to obtain a plurality of virtual evaluation reports evaluated by each type of virtual test scenario, and combining the results corresponding to the plurality of virtual evaluation reports to obtain a virtual overall evaluation report for a comprehensive evaluation of the current target vehicle; After the step of performing virtual simulation according to each of the vehicle driving data and the traffic environment data to obtain a virtual test scene corresponding to each of the driving environments, the method further includes: Analyzing the vehicle driving data and traffic environment data corresponding to each of the virtual test scenarios, and clustering the vehicle driving data or traffic environment data corresponding to any one of the virtual test scenarios with the vehicle driving data or traffic environment data corresponding to another of the virtual test scenarios; To obtain at least one other virtual test scene in which the vehicle driving data and the traffic environment data in the determined plurality of virtual test scenes are clustered with each other; After the step of obtaining at least one other virtual test scene in which the vehicle driving data and the traffic environment data in the determined plurality of virtual test scenes are clustered with each other, the method further includes: The target vehicle is evaluated according to the virtual test scenarios in the other virtual test scenarios to obtain other evaluation reports corresponding to the other virtual test scenarios, and the other evaluation reports are integrated into the virtual overall evaluation report.

2. The safety assessment method for an autonomous driving vehicle according to claim 1, It is characterized in that After the step of obtaining multiple virtual assessment reports for comprehensive assessment of the current target vehicle, the method further includes: The target vehicle is evaluated in multiple real test scenarios, where each real test scenario corresponds to each virtual test scenario; A real safety assessment is performed on the target vehicle in combination with each of the real test scenarios and the standard files corresponding to the real test scenarios, and multiple real safety assessments are combined to obtain a real safety assessment report that comprehensively evaluates the current target vehicle.

3. The safety assessment method for an autonomous driving vehicle according to claim 2, It is characterized in that After the step of obtaining a true safety assessment report that comprehensively assesses the current target vehicle, the method further includes: The real safety assessment report is compared with the virtual overall assessment report to determine the similarity between the real safety assessment report and the virtual overall assessment report, and the authenticity of the virtual overall assessment report is comprehensively judged based on the similarity.

4. A safety assessment system for autonomous vehicles, It is characterized in that The system is used to implement the safety assessment method for an autonomous driving vehicle according to any one of claims 1 to 3, and the system comprises: An acquisition module for acquiring standard archives for evaluating autonomous vehicles; Also used for obtaining real data of the autonomous driving vehicle in multiple driving environments when the autonomous driving vehicle is driving, the real data at least including vehicle driving data and traffic environment data when the vehicle is driving; A simulation module, used for performing virtual simulation according to each of the vehicle driving data and the traffic environment data, so as to obtain a virtual test scene corresponding to each of the driving environments; The evaluation module is used to evaluate the target vehicle in combination with the standard file and each virtual test scenario to obtain multiple virtual evaluation reports for comprehensive evaluation of the current target vehicle.

5. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, a safety assessment method for an autonomous driving vehicle as claimed in any one of claims 1 to 3 is implemented.

6. A safety assessment device for an autonomous vehicle, It is characterized in that The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a safety assessment method for an autonomous driving vehicle as claimed in any one of claims 1 to 3 is implemented.

Images