Functional safety verification method and readable storage medium for autonomous driving domain controller

By using shadow mode to set functional safety targets and triggers in the autonomous driving domain controller, recording and labeling related data packets, the problem of lack of real-life scenario support for functional safety verification in the prior art is solved, and more efficient and realistic functions are achieved Security verification improves the persuasiveness and test coverage of verification results.

CN115167346BActive Publication Date: 2024-11-26CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210741049.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-28
Publication Date
2024-11-26
Estimated Expiration
2042-06-28

AI Technical Summary

Technical Problem

The existing functional safety verification methods of autonomous driving domain controllers lack real scenario support and cannot effectively trigger and label functional safety events, resulting in unconvincing verification results and low coverage.

Method used

Design a functional safety verification method based on shadow mode, and realize functional safety verification by setting functional safety shadow mode in the target vehicle, determining functional safety goals and mechanisms, triggering scene triggers that violate the target, recording and labeling related data packets.

Benefits of technology

It improves the authenticity and effectiveness of the functional safety verification of the autonomous driving domain controller, enhances the persuasiveness of the verification results, and improves the coverage rate of the test scenario and the utilization rate of the chip computing power.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115167346B_ABST
    Figure CN115167346B_ABST
Patent Text Reader

Abstract

The present invention specifically relates to a functional safety verification method and a readable storage medium for an autonomous driving domain controller. The method includes: setting a functional safety shadow mode; then determining the functional safety target and its functional safety mechanism, and formulating a scenario trigger that violates the functional safety target; during the driving process of the target vehicle, starting the functional safety shadow mode; when a safety event that violates the functional safety target occurs in the target vehicle, the corresponding scenario trigger is triggered, thereby triggering the corresponding functional safety mechanism; recording vehicle-related data within a preset period before and after the safety event occurs, generating a safety event data packet and marking it; and implementing functional safety verification of the autonomous driving domain controller based on the marked safety event data packet. The present invention also discloses a readable storage medium. The present invention can trigger and mark safety events that violate functional safety targets in real scenarios in shadow mode and use them to implement functional safety verification.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving vehicle technology, and in particular to a functional safety verification method and a readable storage medium for an autonomous driving domain controller. Background Art

[0002] At present, autonomous driving technology is developing rapidly. Both traditional car companies and new car companies are rushing to enter the autonomous driving track. They have also launched L2, L3 and even higher-level autonomous driving functions. However, many manufacturers over-promote their limited advanced driver assistance functions as autonomous driving functions, which misleads consumers and gradually forms dependence and relaxes their vigilance in the process of using driving assistance, which eventually leads to accidents. Regardless of the level of autonomous driving, the safety of consumers' lives should be put first. Therefore, the functional safety development of autonomous driving domain controllers is crucial.

[0003] There is a relatively complete development process for the functional safety of autonomous driving domain controllers, and the verification of functional safety is currently generally done by fault injection. Although this method is efficient and targeted, it lacks support from actual scenarios and cannot provide effective confirmation indicators during the safety confirmation process, which is also the difficulty of functional safety verification of autonomous driving domain controllers.

[0004] As the concept of software-defined cars is gradually gaining wide recognition, major OEMs are developing a new generation of EE architecture based on SOA. At the same time, as the level of autonomous driving becomes higher and higher, algorithms and models require a large amount of data for training, and more manufacturers will reserve shadow mode in product development. Shadow mode means that when the driver is in the driving state, the autonomous driving system including sensors is still running but does not participate in vehicle control. It only verifies the decision algorithm. That is, the system algorithm makes continuous simulated decisions in "shadow mode" and compares the decision with the driver's behavior. Once the two are inconsistent, the scene is judged as a "special condition", which triggers data feedback.

[0005] The applicant found that based on the shadow mode, it is possible to obtain cases related to functional safety in real scenarios, and then complete functional safety verification based on these cases. However, how to design a functional safety verification method for autonomous driving domain controllers based on the shadow mode is a technical problem that needs to be solved urgently. Summary of the invention

[0006] In view of the above-mentioned deficiencies in the prior art, the technical problem to be solved by the present invention is: how to provide a functional safety verification method for an autonomous driving domain controller, so as to trigger and mark safety events that violate functional safety goals in real scenarios in shadow mode and use them to achieve functional safety verification, thereby improving the authenticity and effectiveness of the functional safety verification of the autonomous driving domain controller.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0008] The functional safety verification method of the autonomous driving domain controller includes the following steps:

[0009] S1: Set the functional safety shadow mode based on the shadow mode of the target vehicle; then determine the functional safety goals and functional safety mechanisms of the autonomous driving domain controller, and formulate scenario triggers that violate the functional safety goals;

[0010] S2: When the target vehicle is driving, the functional safety shadow mode is activated;

[0011] S3: When a safety event that violates the functional safety goal occurs in the target vehicle, the corresponding scenario trigger is triggered, thereby triggering the corresponding functional safety mechanism;

[0012] S4: Record vehicle-related data within a preset period before and after the safety incident occurs, generate a safety incident data packet and mark it;

[0013] S5: Implement functional safety verification of autonomous driving domain controller based on annotated safety event data packets.

[0014] Preferably, in step S1, the functional safety shadow mode means that the functional safety mechanism in the shadow mode of the target vehicle can be triggered normally when the target vehicle is in driving state but will not be output to the corresponding actuator.

[0015] Preferably, in step S1, a functional safety analysis is performed on the autonomous driving domain controller of the target vehicle to confirm the functional safety goals and the corresponding functional safety mechanisms.

[0016] Preferably, the functional safety mechanism includes reminding the driver to immediately take over the vehicle, implement emergency braking and emergency pull-over.

[0017] Preferably, in step S1, the scene trigger includes:

[0018] Trigger 1: A violation of the functional safety goal occurs, and the target vehicle's autonomous driving domain controller issues a warning: The driver is requested to take over lateral control immediately;

[0019] Trigger 2: A violation of the functional safety goal occurs, and the target vehicle's autonomous driving domain controller issues a warning: The driver is requested to take longitudinal control immediately;

[0020] Trigger 3: The target vehicle’s automatic emergency braking function activates;

[0021] Trigger 4: The target vehicle's emergency pull-over function is activated.

[0022] Preferably, in step S4, the vehicle-related data includes vehicle speed, function activation data, driver takeover request, shadow mode-related data and video image data.

[0023] Preferably, in step S4, the security event data packet is marked according to the security event and the security target status of the horizontal and vertical functions.

[0024] Preferably, in step S5, the annotated security event data packet is uploaded to the cloud for download.

[0025] Preferably, in step S5, the triggering scenario of the corresponding functional safety mechanism is restored through the annotated security event data packet, and then the fault tolerance time of the shadow mode functional safety mechanism under the security event is analyzed, so as to verify whether the functional safety meets the design expectations.

[0026] The present invention also discloses a readable storage medium on which a computer management program is stored. When the computer management program is executed by a processor, the steps of the functional safety verification method of the autonomous driving domain controller of the present invention are implemented.

[0027] The functional safety verification method of the autonomous driving domain controller in the present invention has the following beneficial effects:

[0028] The present invention determines the functional safety goals and functional safety mechanisms of the autonomous driving domain controller, and formulates scenario triggers that violate the functional safety goals, so that when a safety incident that violates the functional safety goals occurs in the vehicle, the corresponding scenario triggers and functional safety mechanisms can be triggered, and then the corresponding functional safety mechanisms and vehicle-related data are recorded and marked for the functional safety verification of the autonomous driving domain controller, that is, the safety incidents that violate the functional safety goals in real scenarios can be triggered and marked in shadow mode and used to achieve functional safety verification, thereby improving the effectiveness of the functional safety verification of the autonomous driving domain controller.

[0029] At the same time, the present invention realizes the triggering of scene triggers and functional safety mechanisms based on the shadow mode and then realizes functional safety verification. On the one hand, the present invention can obtain cases related to functional safety in real scenes based on the shadow mode, making the results of functional safety verification more convincing, thereby improving the authenticity of the functional safety verification of the autonomous driving domain controller. On the other hand, the shadow mode can be installed on a large scale and carried out road tests across the country with the fleet, which can improve the coverage of functional safety test scenarios, and the running data can be used for functional safety algorithm training, thereby further improving the effectiveness and authenticity of the functional safety verification of the autonomous driving domain controller.

[0030] It should be noted that, as major manufacturers are increasingly pursuing hardware configuration in the process of autonomous driving development, in order to meet the iterative upgrades of subsequent algorithms, most of them will reserve excessively surplus autonomous driving chip computing power. These expensive hardware become decorations when autonomous driving is not in use. Therefore, the method of implementing the functional safety verification of the autonomous driving domain controller based on the shadow mode of the present invention can greatly improve the utilization rate of chip computing power, mine the value of data, and open up a new idea for the development of autonomous driving functional safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to make the purpose, technical solution and advantages of the invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings, in which:

[0032] Figure 1 The logical block diagram of the functional safety verification method for the autonomous driving domain controller;

[0033] Figure 2 A system block diagram of a vehicle with integrated functional safety shadow mode;

[0034] Figure 3 The operating logic diagram of a vehicle with integrated functional safety shadow mode. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, 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 part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but only represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0036] It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In the description of the present invention, it should be noted that the orientation or position relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the invention product is usually placed when used, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance. In addition, the terms "horizontal", "vertical", etc. do not mean that the components are absolutely horizontal or suspended, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted. In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0037] The following is a further detailed description through specific implementation methods:

[0038] Embodiment 1:

[0039] This embodiment discloses a functional safety verification method for an autonomous driving domain controller.

[0040] like Figure 1 As shown in the figure, the functional safety verification method of the autonomous driving domain controller includes the following steps:

[0041] S1: Set the functional safety shadow mode based on the shadow mode of the target vehicle; then determine the functional safety goals and functional safety mechanisms of the autonomous driving domain controller, and formulate scenario triggers that violate the functional safety goals;

[0042] S2: During the driving process of the target vehicle (or ODD, the operating conditions set by the autonomous driving system function), the functional safety shadow mode is activated;

[0043] S3: When a safety event that violates the functional safety goal occurs in the target vehicle, the corresponding scenario trigger is triggered, thereby triggering the corresponding functional safety mechanism;

[0044] S4: Record the triggered functional safety mechanism and the vehicle-related data within a preset period (calibrable, preferably set to 30S) before and after the safety event occurs, generate a safety event data packet and mark it;

[0045] S5: Implement functional safety verification of autonomous driving domain controllers based on annotated safety event data packets. Restore the triggering scenario of the corresponding functional safety mechanism through annotated safety event data packets, and then analyze the fault tolerance time of the shadow mode functional safety mechanism under the safety event, and then verify whether the functional safety meets the design expectations.

[0046] In this embodiment, the annotated security event data packet is uploaded to the cloud via the 5G network for download by functional safety engineers. After the security event data packet is uploaded, the local data is deleted to release local storage space.

[0047] It should be noted that the functional safety verification method of the autonomous driving domain controller in the present invention can generate corresponding software codes or software services through program programming, which can then be run and implemented on servers and computers.

[0048] The present invention determines the functional safety goals and functional safety mechanisms of the autonomous driving domain controller, and formulates scenario triggers that violate the functional safety goals, so that when a safety incident that violates the functional safety goals occurs in the vehicle, the corresponding scenario triggers and functional safety mechanisms can be triggered, and then the corresponding functional safety mechanisms and vehicle-related data are recorded and marked for the functional safety verification of the autonomous driving domain controller, that is, the safety incidents that violate the functional safety goals in real scenarios can be triggered and marked in shadow mode and used to achieve functional safety verification, thereby improving the effectiveness of the functional safety verification of the autonomous driving domain controller.

[0049] At the same time, the present invention realizes the triggering of scene triggers and functional safety mechanisms based on the shadow mode and then realizes functional safety verification. On the one hand, the present invention can obtain cases related to functional safety in real scenes based on the shadow mode, making the results of functional safety verification more convincing, thereby improving the authenticity of the functional safety verification of the autonomous driving domain controller. On the other hand, the shadow mode can be installed on a large scale and carried out road tests across the country with the fleet, which can improve the coverage of functional safety test scenarios, and the running data can be used for functional safety algorithm training, thereby further improving the effectiveness and authenticity of the functional safety verification of the autonomous driving domain controller.

[0050] It should be noted that, as major manufacturers are increasingly pursuing hardware configuration in the process of autonomous driving development, in order to meet the iterative upgrades of subsequent algorithms, most of them will reserve excessively surplus autonomous driving chip computing power. These expensive hardware become decorations when autonomous driving is not in use. Therefore, the method of implementing the functional safety verification of the autonomous driving domain controller based on the shadow mode of the present invention can greatly improve the utilization rate of chip computing power, mine the value of data, and open up a new idea for the development of autonomous driving functional safety.

[0051] In the specific implementation process, Figure 2 and Figure 3 As shown, the functional safety shadow mode means (adding an overwrite condition to the shadow mode of the vehicle so that) the functional safety mechanism in the shadow mode of the target vehicle can be triggered normally when it is in driving state but will not be output to the corresponding actuator.

[0052] During the specific implementation process, the functional safety goals and corresponding functional safety mechanisms are confirmed by conducting functional safety analysis on the target vehicle's autonomous driving domain controller.

[0053] Functional safety goals include:

[0054] SG01: Unintended lateral control of the vehicle should be avoided;

[0055] SG02: Loss of lateral control of the vehicle should be avoided;

[0056] SG03: Excessive lateral control of the vehicle should be avoided;

[0057] SG04: Avoid vehicles with too little lateral control;

[0058] SG05: Avoid unexpected acceleration of vehicles;

[0059] SG06: Avoid the vehicle losing its ability to accelerate;

[0060] SG07: Avoid excessive acceleration control of the vehicle;

[0061] SG08: Avoid excessive acceleration control of the vehicle;

[0062] SG09: Avoid unexpected vehicle deceleration;

[0063] SG10: Avoid excessive deceleration of the vehicle;

[0064] SG11: Avoid excessive deceleration of the vehicle;

[0065] Functional safety mechanisms include:

[0066] ST01: Remind the driver to take over the vehicle immediately;

[0067] ST02: Apply emergency braking;

[0068] ST03: Emergency pull-over;

[0069] Scene triggers include:

[0070] Trigger 1: A violation of the functional safety goal occurs, and the target vehicle's autonomous driving domain controller issues a warning: The driver is requested to take over lateral control immediately;

[0071] Tigger (Trigger): When a violation of the functional safety goal occurs, the target vehicle's autonomous driving domain controller issues a warning: Please ask the driver to take over longitudinally immediately;

[0072] Tigger: AEB_ActivatedReq = 1, the automatic emergency braking function of the target vehicle is activated;

[0073] Tigger: AES_ActivatedReq = 1, the emergency pull-over function of the target vehicle is activated.

[0074] Vehicle-related data includes:

[0075] Signal1: vehicle longitudinal speed;

[0076] Signal2: vehicle longitudinal acceleration;

[0077] Signal3: vehicle lateral speed;

[0078] Signal4: vehicle lateral acceleration;

[0079] Signal5: Automatic emergency braking function is activated;

[0080] Signal6: Driver's request for lateral takeover;

[0081] Signal7: Driver's longitudinal takeover request;

[0082] Signal8: Emergency parking function activated;

[0083] Signal9: Self-driving request deceleration in shadow mode;

[0084] Signal10: Self-driving request acceleration in shadow mode;

[0085] Signal11: Self-driving request for lateral steering wheel angle in shadow mode;

[0086] Signal12: lateral steering wheel angle change rate requested by self-driving in shadow mode;

[0087] Signal13: data about the self-driving car's perception of the surrounding environment in shadow mode;

[0088] Video data recorded by Signal14's full-vehicle cameras;

[0089] The safety event data packet is labeled according to the safety event and the safety target status of the lateral and longitudinal functions. For example, when Tigger1 is triggered and the actual steering wheel angle - the steering wheel requested by the intelligent driving in the shadow mode is greater than 5°, the safety event data packet is labeled as lateral takeover + lateral control is too large.

[0090] Embodiment 2:

[0091] This embodiment discloses a readable storage medium.

[0092] A readable storage medium stores a computer management program, which, when executed by a processor, implements the steps of the functional safety verification method of the autonomous driving domain controller of the present invention. The readable storage medium can be a device with a readable storage function such as a USB flash drive or a computer.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit the technical solution. Those skilled in the art should understand that those modifications or equivalent substitutions of the technical solution of the present invention that do not depart from the purpose and scope of the technical solution should be included in the scope of the claims of the present invention.

Claims

1. A functional safety verification method for an autonomous driving domain controller, characterized in that: The following steps are involved: S1: Set the functional safety shadow mode based on the shadow mode of the target vehicle; then determine the functional safety goals and functional safety mechanisms of the autonomous driving domain controller, and formulate scenario triggers that violate the functional safety goals; In step S1, the functional safety shadow mode means that the functional safety mechanism in the shadow mode of the target vehicle can be triggered normally when the target vehicle is in driving state but will not be output to the corresponding actuator; S2: When the target vehicle is driving, the functional safety shadow mode is activated; S3: When a safety event that violates the functional safety goal occurs in the target vehicle, the corresponding scenario trigger is triggered, thereby triggering the corresponding functional safety mechanism; S4: Record vehicle-related data within a preset period before and after the safety incident occurs, generate a safety incident data packet and mark it; S5: Implement functional safety verification of autonomous driving domain controller based on annotated safety event data packets.

2. The functional safety verification method of the autonomous driving domain controller according to claim 1, characterized in that: In step S1, the functional safety objectives and corresponding functional safety mechanisms are confirmed by performing functional safety analysis on the autonomous driving domain controller of the target vehicle.

3. The functional safety verification method of the autonomous driving domain controller according to claim 2, characterized in that: Functional safety mechanisms include reminding the driver to take over the vehicle immediately, applying emergency braking and emergency pulling over.

4. The functional safety verification method of the autonomous driving domain controller according to claim 1, characterized in that: In step S1, the scene trigger includes: Trigger 1: A violation of the functional safety goal occurs, and the target vehicle's autonomous driving domain controller issues a warning: The driver is requested to take over lateral control immediately; Trigger 2: A violation of the functional safety goal occurs, and the target vehicle's autonomous driving domain controller issues a warning: The driver is requested to take longitudinal control immediately; Trigger 3: The target vehicle’s automatic emergency braking function activates; Trigger 4: The target vehicle's emergency pull-over function is activated.

5. The functional safety verification method of the autonomous driving domain controller according to claim 1, characterized in that: In step S4, the vehicle-related data includes vehicle speed, function activation data, driver takeover request, shadow mode-related data and video image data.

6. The functional safety verification method of the autonomous driving domain controller according to claim 1, characterized in that: In step S4, the security event data packet is marked according to the security event and the security target status of the horizontal and vertical functions.

7. The functional safety verification method of the autonomous driving domain controller according to claim 1, characterized in that: In step S5, the annotated security event data packet is uploaded to the cloud for download.

8. The functional safety verification method of the autonomous driving domain controller according to claim 1, characterized in that: In step S5, the triggering scenario of the corresponding functional safety mechanism is restored through the annotated security event data packet, and then the fault tolerance time of the shadow mode functional safety mechanism under the security event is analyzed to verify whether the functional safety meets the design expectations.

9. A readable storage medium, characterized in that: A computer management program is stored thereon, and when the computer management program is executed by the processor, the steps of the functional safety verification method of the autonomous driving domain controller as described in any one of claims 1 to 8 are implemented.