Method, device and equipment for detecting associated operating components of an autonomous driving system

Abstract

The application provides a detection method, device and equipment for associated running components of an automatic driving system. When a target object within a set distance range is perceived by an automatic driving system of a target vehicle, the target vehicle is controlled in a vehicle state based on the target object within the set distance range. Control instruction parameters output by associated running components of the automatic driving system of the target vehicle are obtained. State result actual data determined by the automatic driving system based on the target object is obtained. Whether the associated running components of the automatic driving system of the target vehicle are abnormal is determined based on the control instruction parameters and the state result actual data. If the associated running components of the automatic driving system of the target vehicle are abnormal, abnormal prompt information that the associated running components of the automatic driving system of the target vehicle are abnormal is output. The application realizes closed-loop and comprehensive abnormal detection of the associated running components of the automatic driving system, and improves the safety and reliability of system operation.

Description

Technical Field

[0001] This application relates to the field of autonomous driving control technology, specifically to a method, apparatus, and equipment for detecting associated operating components of an autonomous driving system. Background Technology

[0002] In the field of autonomous driving technology, monitoring the health status of associated operating components of an autonomous driving system is crucial to ensure its continued compliance with safe operation requirements. Relevant standards explicitly require vehicles to possess the capability to monitor the performance of associated operating components of the autonomous driving system, thereby enabling appropriate measures to be taken to ensure driving safety when performance deteriorates or malfunctions.

[0003] In related technologies, to monitor the status of associated operating components in an autonomous driving system, fault diagnosis typically relies on the diagnostic functions of each component or preset performance thresholds. For example, the proper functioning of a specific component is determined by feedback signals from associated operating components (actuators, etc.), internal status codes of the controller, or direct measurements from independent sensors. However, these methods are essentially "open-loop" detection based on a single technical path or local signals. This approach is therefore ill-suited for effectively detecting comprehensive faults caused by coordinated performance deviations of multiple components, latent sensor biases, or system-wide performance degradation.

[0004] Therefore, during the long-term use of vehicles, how to effectively identify those hidden comprehensive faults that are not directly detected by the self-inspection mechanisms of each component but cause the actual movement of the vehicle to deviate from the expected behavior has become a technical problem that urgently needs to be solved to improve the operational safety and reliability of autonomous driving systems. Summary of the Invention

[0005] In view of this, this application aims to provide a method, apparatus and equipment for detecting associated operating components of an autonomous driving system, so as to solve the technical problem that related technologies are difficult to identify hidden comprehensive faults and improve the operational safety and reliability of autonomous driving systems.

[0006] The first aspect of this application provides a method for detecting associated operating components of an autonomous driving system, comprising: when the autonomous driving system of a target vehicle perceives a target object within a set distance range, performing vehicle state control on the target vehicle based on the target object within the set distance range; during the vehicle state control of the target vehicle, acquiring control command parameters output by the associated operating components of the autonomous driving system of the target vehicle, wherein the control command parameters are obtained by collecting data from the associated operating components during vehicle control; acquiring actual data of the state result determined by the autonomous driving system based on the target object, wherein the actual data of the state result is calculated and output by the autonomous driving system before and after identifying the target object; determining whether there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual data of the state result; and if there is an anomaly, outputting an anomaly prompt message indicating that there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle.

[0007] In one possible implementation, determining whether there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual state result data includes: if the deviation between the control command parameters and the actual state result data exceeds a first preset deviation threshold, then it is determined that there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle; if the deviation between the control command parameters and the actual state result data does not exceed the first preset deviation threshold, then it is determined that there is no anomaly in the associated operating components of the autonomous driving system of the target vehicle.

[0008] In one possible implementation, determining whether there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual data of the state results includes: determining the maximum locking capability parameter of the corresponding control command parameters based on the control command parameters; if the deviation between the maximum locking capability parameter and the actual data of the state results exceeds a second preset deviation threshold, then determining that there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle; if the deviation between the maximum locking capability parameter and the actual data of the state results does not exceed the second preset deviation threshold, then determining that there is no anomaly in the associated operating components of the autonomous driving system of the target vehicle.

[0009] In one possible implementation, determining the maximum locking capability parameter of the corresponding control command parameter based on the control command parameter includes: obtaining the corresponding vehicle capability boundary value, functional safety constraint value, and regulatory constraint value based on the control command parameter; and determining the maximum locking capability parameter of the control command parameter according to the vehicle capability boundary value, the functional safety constraint value, and the regulatory constraint value.

[0010] In one possible implementation, after determining whether there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual data of the state results, the method further includes: determining an abnormal deviation value between the control command parameters and the actual data of the state results; if the abnormal deviation value is greater than or equal to a first-level risk threshold and less than a second-level risk threshold, then triggering the autonomous driving system to perform a callback control operation on the vehicle; wherein the second-level risk threshold is greater than the first-level risk threshold.

[0011] In one possible implementation, after triggering the autonomous driving system to perform a callback control operation on the vehicle if the abnormal deviation value is greater than or equal to the first risk threshold, the method further includes: if it is determined that the vehicle does not respond after performing the callback control operation, then triggering the autonomous driving system to perform a minimum risk control operation on the vehicle.

[0012] In one possible implementation, it further includes: if the abnormal deviation value is greater than or equal to the second-level risk threshold, then triggering the autonomous driving system to perform minimum risk control operations on the vehicle.

[0013] A second aspect of this application also provides a detection device for associated operating components of an autonomous driving system, comprising: a control module, configured to control the vehicle state of a target vehicle based on the target object within a set distance range when the autonomous driving system of a target vehicle perceives the target object within a set distance range; an acquisition module, configured to acquire control command parameters output by the associated operating components of the autonomous driving system of the target vehicle during the vehicle state control process, wherein the control command parameters are obtained by collecting data from the associated operating components during the vehicle control process; and to acquire actual data of the state result determined by the autonomous driving system based on the target object, wherein the actual data of the state result is calculated and output by the autonomous driving system before and after identifying the target object; a detection module, configured to determine whether there is an abnormality in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual data of the state result; and an output module, configured to output an abnormality prompt message indicating that there is an abnormality in the associated operating components of the autonomous driving system of the target vehicle if an abnormality exists.

[0014] A third aspect of this application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform a detection method for associated operating components of an autonomous driving system as described in the first aspect and possible implementations thereof.

[0015] The fourth aspect of this application provides a computer storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement a method for detecting associated operating components of an autonomous driving system as described in the first aspect and possible implementations of the first aspect.

[0016] The fifth aspect of this application provides a computer program product, comprising: a computer program that, when executed by a processor, implements a method for detecting associated operating components of an autonomous driving system as described in the first aspect and possible implementations of the first aspect.

[0017] The present application provides a method, apparatus, and device for detecting associated operating components of an autonomous driving system. In this method, control command parameters during vehicle control and actual data of state results determined based on environmental perception objects are acquired and compared to determine whether there are any abnormalities in the associated operating components. By using data from two independent technical paths—control command expectation (control command parameters) and environmental perception feedback (actual data of state results)—end-to-end cross-validation is performed. When inconsistencies occur between the data verifications, systematic deviations or faults that cannot be detected by a single system self-test can be effectively identified. This achieves closed-loop, comprehensive fault detection of associated operating components of the autonomous driving system, improving the safety and reliability of system operation. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of this application, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram illustrating an application scenario for detecting associated operating components of an autonomous driving system provided in an embodiment of this application.

[0020] Figure 2 This is a flowchart illustrating the detection method for associated operating components of an autonomous driving system provided in an embodiment of this application.

[0021] Figure 3 This is a schematic diagram illustrating the control of a target vehicle by a target vehicle based on the autonomous driving system provided in this application embodiment.

[0022] Figure 4 This is a schematic diagram of the structure of the detection device for the associated operating components of the autonomous driving system provided in the embodiments of this application.

[0023] Figure 5This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] In the field of performance testing of associated operating components in a vehicle's autonomous driving system, a common approach is to utilize the self-testing mechanism of these components. This involves reading sensor feedback signals (e.g., brake master cylinder pressure, steering motor current, position) from each associated operating component (such as the braking system and steering system) and comparing them in real time with the control command values ​​issued by the controller. The basic principle is that after a control command is issued, it verifies whether the actuators of the associated operating components have reached the required state or output the expected physical quantity within the expected timeframe. This method is widely used primarily because it can directly diagnose clear hardware faults such as communication interruptions, sensor failures, or driver damage in associated operating components.

[0026] However, this solution performs poorly when applied to detect comprehensive anomalies caused by aging of associated operating components, gradual performance degradation, or coordination deviations between multiple systems. For example, in scenarios where the braking system experiences a slight decrease in hydraulic pressure due to aging seals, or where the sensing system exhibits systematic deviations in ranging due to lens contamination, the sensor feedback of the actuators in the associated operating components may still be within the normal range, and the command-feedback closed loop between the controller and the actuators may appear normal. However, the actual motion of the vehicle relative to the external environment (such as deceleration and lateral displacement) has deviated significantly from the control expectations. This deviation cannot be captured by traditional self-testing mechanisms.

[0027] In related technologies, for the associated operating components of autonomous driving systems, the lack of a mechanism to cross-verify the expected physical effects of control commands with the actual motion results of the vehicle in the real environment makes it difficult to effectively detect comprehensive faults caused by the coordinated performance deviation of multiple components, latent sensor biases, or system-level performance degradation. Such faults result in a hidden inconsistency between the actual motion state of the vehicle and the expected state of the control system, which is difficult to detect by existing independent detection modules. To overcome this contradiction, this invention proposes a different technical approach. The inventive concept is to introduce end-to-end verification based on environmental perception results, cross-verifying the expected vehicle motion changes corresponding to control commands with the actual motion changes of the vehicle relative to environmental references calculated by the perception system. This effectively identifies hidden comprehensive performance anomalies that traditional self-testing mechanisms cannot cover without weakening the ability to detect explicit hardware faults. In other words, it provides a method to indirectly detect anomalies in associated operating components by comparing the expected effect of commands with the actual perceived effect, solving the problem of missed detection of comprehensive faults caused by the lack of closed-loop result verification in related technologies, and achieving a more comprehensive and reliable detection effect on the performance of associated operating components of autonomous driving systems.

[0028] Figure 1 This is a schematic diagram illustrating an application scenario for detecting associated operating components of an autonomous driving system provided in an embodiment of this application. (Reference) Figure 1 This scenario includes a control terminal 101 and a target vehicle 102. The control terminal 101 and the target vehicle 102 can transmit data via a vehicle bus. It should be noted that the control terminal 101 can be any type of controller on the vehicle, such as a vehicle controller. The control terminal 101 is used to collect various operational data related to the target vehicle 102, such as control command parameters output by associated operating components of the autonomous driving system and various calculated data identified by the autonomous driving system.

[0029] Exemplary methods Figure 2 This is a flowchart illustrating the detection method for associated operating components of an autonomous driving system provided in an embodiment of this application. The executing entity in this embodiment can be... Figure 1 The control terminal in the illustrated embodiment. For example... Figure 2 As shown, the method includes: S201: When the autonomous driving system of the target vehicle perceives a target object within a set distance range, the vehicle state control is performed on the target vehicle based on the target object within the set distance range.

[0030] In this embodiment of the application, the target object can be a person or an object. For example, the target object is one or more pedestrians located on a sidewalk.

[0031] For example, refer to Figure 3 When the target object is one or more pedestrians on the sidewalk, the autonomous driving system of the target vehicle senses one or more pedestrians within a set distance range (such as within 50 meters) and performs vehicle state control on the target vehicle, including deceleration control or braking control.

[0032] S202: During the process of controlling the vehicle state of the target vehicle, the control command parameters output by the associated operating components of the autonomous driving system of the target vehicle are obtained, wherein the control command parameters are obtained by collecting data from the associated operating components during the vehicle control process; and the actual data of the state result determined by the autonomous driving system based on the target object are obtained, wherein the actual data of the state result is calculated and output by the autonomous driving system before and after recognizing the target object.

[0033] In one embodiment of this application, the associated operating component may be a braking system; correspondingly, the collected control command parameters may be various real-time factor characteristic parameters. These various real-time factor characteristic parameters specifically include, but are not limited to: the average deceleration control value, hydraulic pressure control value, lateral acceleration control value, and lateral steering angle control value of the braking system.

[0034] In one embodiment of this application, the actual state result data can be determined in real time by the autonomous driving system during vehicle state control of the target vehicle. Optionally, within any control time interval, actual data obtained based on the target object at the start of control of the control time interval and actual data obtained based on the target object at the end of control of the control time interval are collected, and the actual state result data is obtained based on the actual data at the start and the actual data at the end.

[0035] S203: Based on control command parameters and actual data of status results, determine whether there are any abnormalities in the associated operating components of the target vehicle's autonomous driving system.

[0036] In one embodiment of the application, S203 may specifically include: if the deviation between the control command parameters and the actual data of the state result exceeds a first preset deviation threshold, then it is determined that there is an anomaly in the associated operating component of the autonomous driving system of the target vehicle; if the deviation between the control command parameters and the actual data of the state result does not exceed the first preset deviation threshold, then it is determined that there is no anomaly in the associated operating component of the autonomous driving system of the target vehicle.

[0037] In one embodiment, the associated operating component is a braking system; the control command parameter is the distance (S1) between the target vehicle and the target object at the first moment (T0) output by the braking system. n ), and the distance between the target vehicle and the target object at the second time (T1) (S1) n+1), and thus obtain the first braking distance (S1) between the first time (T0) and the second time (T1) related to the target vehicle and the target object. n+1 -S1 n The control command parameters are used as the actual data of the state result, which is the distance between the target vehicle and the target object at the first moment (T0) obtained by the autonomous driving system after identifying the target object (S0). n ), and the distance between the target vehicle and the target object at the second time (T1) (S0) n+1 ), and thus obtain the second braking distance (S0) between the target vehicle and the target object between the first time (T0) and the second time (T1). n+1 -S0 n ) as the actual data of the state result; if the first braking distance (S1) n+1 -S1 n ) and the second braking distance (S0) n+1 -S0 n If the deviation exceeds the first preset deviation threshold (braking distance deviation threshold), it is determined that there is an abnormality in the associated operating component (braking system) of the target vehicle's autonomous driving system; otherwise, it is determined that there is no abnormality in the associated operating component (braking system).

[0038] In another embodiment, the associated operating component is the braking system; the control command parameter is the average deceleration control value output by the braking system (denoted as the first average deceleration); the actual state result data is the average deceleration result data determined by the autonomous driving system based on the target object (denoted as the second average deceleration); if the deviation between the first average deceleration and the second average deceleration exceeds the first preset deviation threshold (deceleration deviation threshold), it is determined that the associated operating component (braking system) of the autonomous driving system of the target vehicle is abnormal; otherwise, it is determined that the associated operating component (braking system) is not abnormal.

[0039] For example, the control command parameter is the average deceleration control value output by the braking system, specifically 5 m / s². 2 The actual data for the state result is the average deceleration result determined by the autonomous driving system based on the target object, specifically 3 m / s². 2 The first preset deviation threshold is set to 1 m / s. 2 Average deceleration control value (5m / s²) 2 ) and average deceleration results (3m / s 2 The deviation is 2m / s 2 It is greater than the first preset deviation threshold (deceleration deviation threshold, 1 m / s²). 2 This indicates that there is an anomaly in the associated operating components (i.e., the braking system) of the target vehicle's autonomous driving system.

[0040] In this embodiment, the control command parameters and actual data of the status results may include the following combinations: the average deceleration control value of the braking system and the actual braking distance, the hydraulic pressure control value and the actual braking distance, the lateral acceleration control value and the actual lateral displacement, and the lateral steering angle control value and the actual lateral displacement.

[0041] S204: If an anomaly exists, output an anomaly message indicating that there is an anomaly in the associated operating components of the target vehicle's autonomous driving system.

[0042] In the embodiments of this application, an abnormality prompt message is displayed when the associated operating components of the autonomous driving system of the target vehicle are abnormal. This abnormality prompt message can be displayed on the vehicle's central control screen, on the instrument panel, or played through a speaker.

[0043] As described in this embodiment, by acquiring control command parameters during vehicle control and actual data of state results determined based on environmental perception objects, and comparing the two, it is possible to determine whether there are any abnormalities in the associated operating components. By using data from two independent technical paths—control command expectation (control command parameters) and environmental perception feedback (actual data of state results)—end-to-end cross-verification can be performed. When inconsistencies occur in the verification between the data, it is possible to effectively identify abnormalities caused by systematic deviations or faults that cannot be detected by a single system self-test. This achieves closed-loop and comprehensive anomaly detection of associated operating components of the autonomous driving system, thereby improving the safety and reliability of system operation.

[0044] In another embodiment of this application, step S203 specifically includes: S231: Based on the control command parameters, determine the maximum locking capability parameter of the corresponding control command parameters.

[0045] In the embodiments of this application, the associated operating component can be a braking system; correspondingly, the maximum locking capability parameter can be various locking factor characteristic parameters. These various locking factor characteristic parameters specifically include, but are not limited to, the maximum locking braking capability value and the maximum locking driving speed capability value of the braking system.

[0046] In one example, the control command parameter is the average deceleration control value, and its corresponding maximum locking capacity parameter can be the maximum locking braking capacity value.

[0047] S232: If the deviation between the maximum capability parameter and the actual data of the state result exceeds the second preset deviation threshold, it is determined that there is an anomaly in the associated operating component of the target vehicle's autonomous driving system.

[0048] S233: If the deviation between the locked maximum capability parameter and the actual data of the state result does not exceed the second preset deviation threshold, then it is determined that there is no abnormality in the associated operating components of the target vehicle's autonomous driving system.

[0049] In this embodiment, another comparison benchmark is introduced: the "locked maximum capability parameter." In certain specific control scenarios, some faults manifest as an abnormal "enhancement" of the capabilities of associated operating components, exceeding their theoretically or safety-permissible maximum boundaries. For example, due to software errors or hardware failures, a vehicle may generate acceleration far exceeding functional safety constraints (e.g., 0.25g) when starting at an intersection. In this case, the control command parameter (the requested acceleration) may not be large, so the deviation from the actual data of the state result (the perceived large acceleration) may not exceed a first preset deviation threshold, leading to a missed detection. The locked maximum capability parameter represents the maximum capability value that the vehicle or system is allowed or theoretically capable of achieving in this scenario. By comparing the actual results observed by perception with this locked maximum capability parameter (capacity upper limit), anomalies in such capability-over-limit scenarios can be effectively detected.

[0050] Specifically, the maximum capability parameter can be determined based on the type of control command parameter. For example, for deceleration commands, the maximum capability parameter might be the maximum physical deceleration determined by the current road surface adhesion coefficient, or the maximum permissible deceleration required for functional safety. The second preset deviation threshold is an independent threshold used for this comparison, and its setting can be more stringent than the first preset deviation threshold because the margin of error for comparison with the maximum capability value is usually smaller. In practical applications, the two comparison methods mentioned above can be combined to form a "dual-track verification": first, the control command parameter is compared with the actual result (verifying command execution consistency), and then the maximum capability parameter is compared with the actual result (verifying capability boundary compliance). Any deviation in either comparison result can be considered an anomaly. This combined strategy greatly broadens the coverage of fault detection, enabling the simultaneous capture of both "unreasonable execution" and "capability exceeding limits" problems.

[0051] In this embodiment, the control command parameters and actual data of the status results may include the following combinations: the maximum braking capacity value of the braking system and the actual braking distance, and the maximum driving speed capacity value and the actual running distance of the road segment.

[0052] As can be seen from the description of this embodiment, by determining the maximum locked capability parameter that represents the maximum theoretical or constraint capability of the component, and comparing the maximum locked capability parameter with the actual result data a second time, a dual verification mechanism is constructed, which can further reduce misjudgments and thus improve the accuracy of detecting abnormal performance of related operating components.

[0053] In one embodiment of this application, the specific process of determining the maximum locking capability parameter of the corresponding control command parameter based on the control command parameter in step S231 may be as follows: based on the control command parameter, obtain the corresponding vehicle capability boundary value, functional safety constraint value and regulatory constraint value; and determine the maximum locking capability parameter of the control command parameter according to the vehicle capability boundary value, the functional safety constraint value and the regulatory constraint value.

[0054] Among them, the most conservative value (the maximum or minimum value will be determined according to the actual situation) among the vehicle capability boundary value, functional safety constraint value and regulatory constraint value will be determined as the locked maximum capability parameter of the control command parameters.

[0055] In this embodiment, the vehicle capability boundary value can refer to the theoretical limit determined by the vehicle's physical properties, such as the maximum deceleration determined by the current road surface adhesion coefficient being approximately 0.8g (in units of gravitational acceleration g), or the absolute maximum acceleration determined by the peak torque of the engine / motor.

[0056] In this embodiment, the functional safety constraint value may refer to the performance upper limit set in the software algorithm based on the vehicle's functional safety objectives. For example, to prevent unexpected acceleration, the starting acceleration is limited to 0.25g.

[0057] In this embodiment, the regulatory constraint value can refer to the restrictions imposed on vehicle behavior in certain scenarios by traffic regulations or road design specifications, such as the speed limit or recommended turning speed specified for highway ramps.

[0058] In this embodiment, by combining the above three dimensions (vehicle capability boundary value, functional safety constraint value, and regulatory constraint value) and taking conservative values ​​(maximum or minimum value), the final locked maximum capability parameter is a strict capability boundary that simultaneously meets safety, physical, and regulatory requirements. If any perceived actual motion state continuously exceeds this boundary, even if there are no fault codes in the component self-test, it indicates that there is an abnormality in the associated operating component.

[0059] As described in this embodiment, by comprehensively considering functional safety constraints, vehicle physical capability boundary values, and regulatory constraints, and selecting a conservative value among them to determine the maximum capability parameter, this ensures that the parameter always represents a safe, reliable, and achievable true capability upper limit. This method guarantees the safety of the fault detection benchmark from the source and transforms the abstract capability boundary into a definite value that can be derived from specific engineering and regulatory constraints, enhancing the feasibility and standardization of the solution.

[0060] In one embodiment of this application, after detecting an anomaly in an associated operating component, in order to implement differentiated and progressive safety responses based on the severity of the anomaly to balance driving safety and functional availability, this application also provides a preferred scheme for a graded response strategy. Specifically, after step S203, the following may also be included: S205: Determine the abnormal deviation values ​​between the control command parameters and the actual data of the status results.

[0061] S206: If the abnormal deviation value is greater than or equal to the first-level risk threshold and less than the second-level risk threshold, the autonomous driving system is triggered to perform a callback control operation on the vehicle; wherein the second-level risk threshold is greater than the first-level risk threshold.

[0062] In this embodiment, the first and second risk thresholds are used to classify the severity of the anomaly. The first risk threshold can correspond to the aforementioned first preset deviation threshold, or it can be a value slightly higher than the first preset deviation threshold, representing a mild anomaly. When the abnormal deviation value falls within the first range, it indicates that an inconsistency has occurred in the system, but the degree is not yet severe, and there is a possibility of compensation and recovery through adjusting the control strategy. At this time, a callback control operation is triggered. The callback control operation refers to the autonomous driving system actively adjusting the control command parameters it issues based on the detected inconsistency, attempting to bring the subsequent actual vehicle movement back to the expected range.

[0063] In one example, during a braking scenario, if the detected actual deceleration (actual data of the state result) is less than the requested value (control command parameter), indicating that the braking is too soft, the autonomous driving system can appropriately increase the braking request value; if the detected actual deceleration is greater than the requested value, indicating that the braking is too abrupt, the system can appropriately decrease the requested value. This "closed-loop control supplement" is essentially an experimental repair, aiming to maintain the basic controllability of the vehicle through active adaptation at the control end before the fault leads to serious consequences, and to observe whether the system still has responsiveness.

[0064] As can be seen from the description of this embodiment, by setting a first-level risk threshold and a second-level risk threshold to classify the degree of anomaly, and triggering callback control operations and minimum risk control operations in sequence accordingly, the safety response is refined and progressive. It can first attempt to compensate and recover when a minor anomaly is detected, and only execute the highest level of safety policy (minimum risk control operation) when a serious anomaly is detected, thereby maintaining the availability of the autonomous driving system as much as possible while ensuring driving safety.

[0065] In one embodiment of this application, after step S206 described above, the method further includes: S207: If it is determined that the vehicle does not respond after a callback control operation is performed, the autonomous driving system is triggered to perform a minimum risk control operation on the vehicle.

[0066] In the embodiments of this application, if, within a certain period of time (e.g., 500ms) after the callback operation is executed, continuous comparison reveals that the abnormal deviation has not been reduced or corrected, or even continues to increase, it indicates that the autonomous driving system can no longer correct the deviation through simple instruction adjustments, and the fault may be quite serious or rapidly deteriorating. In this case, the "repair" attempt should be abandoned immediately, and instead, a minimum risk control operation should be executed. A minimum risk control operation refers to a control strategy aimed at achieving the lowest possible risk state for the vehicle, such as smoothly decelerating to a stop, pulling over to the side of the road under safe conditions, or performing emergency braking to avoid a collision.

[0067] In summary, the design of this embodiment ensures that in the event of partial system failure, the system can quickly and decisively switch from attempting to restore functionality to the minimum objective of ensuring safety.

[0068] In one embodiment of this application, after step S205 described above, the method further includes: If the abnormal deviation value is greater than or equal to the second-level risk threshold, the autonomous driving system will be triggered to perform minimum risk control operations on the vehicle.

[0069] In the embodiments of this application, the second risk threshold represents a severe anomaly and is typically set to a high value. When the anomaly deviation value reaches or exceeds this threshold from the outset, it indicates a very serious inconsistency that may directly jeopardize safety, leaving no time to attempt a callback operation. In this case, the system should bypass the callback phase and directly trigger the minimum risk control operation to bring the vehicle to a safe state as quickly as possible.

[0070] In summary, this differentiated response logic based on the threshold range of the deviation value enables refined handling of faults of different degrees: minor anomalies attempt to compensate and recover, while severe anomalies or recovery failures immediately execute the minimum risk strategy, thereby extending the system's availability as much as possible while ensuring a safety baseline.

[0071] Exemplary device Figure 4 This is a schematic diagram of the structure of a detection device for associated operating components of an autonomous driving system provided in an embodiment of this application. Figure 4 As shown, the detection device for the associated operating components of the autonomous driving system is applied to the control end and includes: a control module 401, an acquisition module 402, a detection module 403, and an output module 404.

[0072] The control module 401 is used to control the vehicle state of the target vehicle based on the target object within the set distance range when the autonomous driving system of the target vehicle perceives the target object within the set distance range.

[0073] The acquisition module 402 is used to acquire, during the process of controlling the vehicle state of the target vehicle, control command parameters output by the associated operating components of the autonomous driving system of the target vehicle, wherein the control command parameters are obtained by collecting data from the associated operating components during the vehicle control process; and to acquire actual data of the state result determined by the autonomous driving system based on the target object, wherein the actual data of the state result is calculated and output by the autonomous driving system before and after recognizing the target object.

[0074] The detection module 403 is used to determine whether there is any abnormality in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual data of the state results.

[0075] The output module 404 is used to output an error message indicating that there is an error in the associated operating component of the autonomous driving system of the target vehicle if an error is found.

[0076] In one or more embodiments of this application, determining whether there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual state result data includes: if the deviation between the control command parameters and the actual state result data exceeds a first preset deviation threshold, then determining that there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle; if the deviation between the control command parameters and the actual state result data does not exceed the first preset deviation threshold, then determining that there is no anomaly in the associated operating components of the autonomous driving system of the target vehicle.

[0077] In one or more embodiments of this application, determining whether there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual data of the state results includes: determining the maximum locking capability parameter of the corresponding control command parameters based on the control command parameters; if the deviation between the maximum locking capability parameter and the actual data of the state results exceeds a second preset deviation threshold, then determining that there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle; if the deviation between the maximum locking capability parameter and the actual data of the state results does not exceed the second preset deviation threshold, then determining that there is no anomaly in the associated operating components of the autonomous driving system of the target vehicle.

[0078] In one or more embodiments of this application, determining the maximum locking capability parameter of the corresponding control command parameter based on the control command parameter includes: obtaining the corresponding vehicle capability boundary value, functional safety constraint value, and regulatory constraint value based on the control command parameter; and determining the maximum locking capability parameter of the control command parameter according to the vehicle capability boundary value, the functional safety constraint value, and the regulatory constraint value.

[0079] In one or more embodiments of this application, after determining whether there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual data of the state results, the method further includes: determining an abnormal deviation value between the control command parameters and the actual data of the state results; if the abnormal deviation value is greater than or equal to a first-level risk threshold and less than a second-level risk threshold, then triggering the autonomous driving system to perform a callback control operation on the vehicle; wherein the second-level risk threshold is greater than the first-level risk threshold.

[0080] In one or more embodiments of this application, after triggering the autonomous driving system to perform a callback control operation on the vehicle if the abnormal deviation value is greater than or equal to the first risk threshold, the method further includes: if it is determined that the vehicle does not respond after performing the callback control operation on the vehicle, then triggering the autonomous driving system to perform a minimum risk control operation on the vehicle.

[0081] In one or more embodiments of this application, the method further includes: if the abnormal deviation value is greater than or equal to the second risk threshold, then triggering the autonomous driving system to perform minimum risk control operation on the vehicle.

[0082] The apparatus provided in this application embodiment can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0083] Exemplary device Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device of this embodiment includes a processor 501 and a memory 502.

[0084] The memory 502 stores computer-executed instructions; the processor 501 executes the computer-executed instructions stored in the memory to implement the various steps performed by the electronic device in the above embodiments. For details, please refer to the relevant descriptions in the foregoing method embodiments.

[0085] Alternatively, the memory 502 can be either standalone or integrated with the processor 501.

[0086] When the memory 502 is set up independently, the electronic device also includes a bus 503 for connecting the memory 502 and the processor 501.

[0087] Exemplary media and products This application also provides a computer storage medium storing computer execution instructions. When the processor executes the computer execution instructions, it implements the above-described method for detecting associated operating components of the autonomous driving system.

[0088] This application also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-described method for detecting associated operating components of an autonomous driving system.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0090] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0091] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0092] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application.

[0093] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0094] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0095] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0096] The aforementioned storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0097] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. Both the processor and the storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic device or host device.

[0098] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for detecting associated operating components of an autonomous driving system, characterized in that, include: When the autonomous driving system of the target vehicle senses a target object within a set distance range, the vehicle state control is performed on the target vehicle based on the target object within the set distance range; During the vehicle state control process of the target vehicle, control command parameters output by the associated operating components of the autonomous driving system of the target vehicle are obtained, wherein the control command parameters are obtained by collecting data from the associated operating components during the vehicle control process; and actual data of the state result determined by the autonomous driving system based on the target object are obtained, wherein the actual data of the state result is calculated and output by the autonomous driving system before and after identifying the target object. Based on the control command parameters and the actual data of the status results, determine whether there are any abnormalities in the associated operating components of the target vehicle's autonomous driving system; If an anomaly is detected, an anomaly message will be output indicating that there is an anomaly in the associated operating components of the target vehicle's autonomous driving system.

2. The method according to claim 1, characterized in that, The step of determining whether there are any abnormalities in the associated operating components of the target vehicle's autonomous driving system based on the control command parameters and the actual data of the state results includes: If the deviation between the control command parameters and the actual data of the state result exceeds a first preset deviation threshold, it is determined that there is an abnormality in the associated operating components of the autonomous driving system of the target vehicle. If the deviation between the control command parameters and the actual data of the state result does not exceed the first preset deviation threshold, then it is determined that there is no abnormality in the associated operating components of the autonomous driving system of the target vehicle.

3. The method according to claim 1, characterized in that, The step of determining whether there are any abnormalities in the associated operating components of the target vehicle's autonomous driving system based on the control command parameters and the actual data of the state results includes: Based on the control command parameters, determine the maximum locking capability parameter of the corresponding control command parameters; If the deviation between the maximum locking capability parameter and the actual data of the state result exceeds the second preset deviation threshold, it is determined that there is an anomaly in the associated operating components of the autonomous driving system of the target vehicle. If the deviation between the maximum locked capability parameter and the actual data of the state result does not exceed the second preset deviation threshold, it is determined that there is no abnormality in the associated operating components of the autonomous driving system of the target vehicle.

4. The method according to claim 3, characterized in that, The step of determining the maximum locking capability parameter corresponding to the control command parameters based on the control command parameters includes: Based on the control command parameters, obtain the corresponding vehicle capability boundary values, functional safety constraint values, and regulatory constraint values; Based on the vehicle capability boundary value, the functional safety constraint value, and the regulatory constraint value, the maximum lock-in capability parameter of the control command parameters is determined.

5. The method according to any one of claims 1 to 4, characterized in that, After determining whether there are any abnormalities in the associated operating components of the target vehicle's autonomous driving system based on the control command parameters and the actual data of the state results, the method further includes: Determine the abnormal deviation values ​​between the control command parameters and the actual data of the state results; If the abnormal deviation value is greater than or equal to the first risk threshold and less than the second risk threshold, the autonomous driving system is triggered to perform a callback control operation on the vehicle; wherein the second risk threshold is greater than the first risk threshold.

6. The method according to claim 5, characterized in that, If the abnormal deviation value is greater than or equal to the first-level risk threshold, after triggering the autonomous driving system to perform a callback control operation on the vehicle, the method further includes: If the vehicle does not respond after a callback control operation is performed, the autonomous driving system is triggered to perform a minimum risk control operation on the vehicle.

7. The method according to claim 5, characterized in that, Also includes: If the abnormal deviation value is greater than or equal to the second-level risk threshold, the autonomous driving system is triggered to perform minimum risk control operations on the vehicle.

8. A detection device for associated operating components of an autonomous driving system, characterized in that, include: The control module is used to control the vehicle state of the target vehicle based on the target object within the set distance range when the autonomous driving system of the target vehicle perceives the target object within the set distance range. The acquisition module is used to acquire, during the process of controlling the vehicle state of the target vehicle, control command parameters output by the associated operating components of the autonomous driving system of the target vehicle, wherein the control command parameters are obtained by collecting data from the associated operating components during the vehicle control process; and to acquire actual data of the state result determined by the autonomous driving system based on the target object, wherein the actual data of the state result is calculated and output by the autonomous driving system before and after recognizing the target object. The detection module is used to determine whether there are any abnormalities in the associated operating components of the autonomous driving system of the target vehicle based on the control command parameters and the actual data of the state results. The output module is used to output an error message indicating that there is an abnormality in the associated operating components of the autonomous driving system of the target vehicle if an abnormality is found.

9. An electronic device, characterized in that, include: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the detection method of the associated operating component of the autonomous driving system according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the detection method for associated operating components of the autonomous driving system as described in any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the detection method for the associated operating components of the autonomous driving system as described in any one of claims 1 to 7.

Images