Vehicle failure control method and device

Abstract

The invention discloses a vehicle failure control method and device, and belongs to the technical field of automobiles. Acquiring vehicle data in the driving process; failure types and associated failure conditions are obtained, the failure types comprise at least one of sensing system failure, control system failure, execution system failure and front hatch cover system failure, the sensing system failure comprises visual sensing failure and radar sensing failure, and the control system failure comprises decision planning failure and control execution failure; the execution system failure comprises brake system failure, steering system failure and power system failure, and the front hatch cover system failure comprises front hatch cover locking failure; determining a target failure type according to a failure condition met by the vehicle data; and determining a control mode according to the target failure type. According to the method, the failure condition is preset for each failure type, matching and judgment are performed according to the vehicle data, the fault source is accurately positioned, the appropriate control mode is dynamically determined according to different target failure types, and differentiated intelligent decisions are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobiles, in particular to a failure control method and device of a vehicle. BACKGROUND

[0002] If some hardware or software in the vehicle fails during driving, we need to determine whether the failure will affect driving safety. If the failure will affect driving safety, the system needs to take over and perform relevant control operations. If the failure will not affect driving safety, it can be processed after the vehicle is safely parked.

[0003] In the related art, when the vehicle detects that the hardware or software fails, the user is prompted with the failure content. The user autonomously determines the failure type of the vehicle according to the failure, and takes appropriate measures according to the determination result.

[0004] However, the user's judgment may be one-sided, and the failure type of the vehicle cannot be accurately determined, so that the wrong measures are taken, resulting in traffic accidents. SUMMARY

[0005] The present application provides a failure control method and device of a vehicle, which is used to solve the problem that the user cannot accurately determine the failure type of the vehicle, and easily leads to traffic accidents. The technical solution is as follows: According to a first aspect of the present application, a failure control method of a vehicle is provided, the method comprising: acquiring vehicle data during driving, the vehicle data comprising at least one of perception system data, control system data, execution system data, and front hood system data; acquiring a preset failure type and at least one failure condition associated with each failure type, the failure type comprising at least one of a perception system failure, a control system failure, an execution system failure, and a front hood system failure, the perception system failure comprising a visual perception failure and a radar perception failure, the control system failure comprising a decision planning failure and a control execution failure, the execution system failure comprising a braking system failure, a steering system failure, and a power system failure, and the front hood system failure comprising a front hood locking failure; determining a target failure type of the vehicle according to the failure condition satisfied by the vehicle data; determining a control mode of the vehicle according to the target failure type, the control mode being used to control the vehicle to safely park.

[0006] In a possible implementation, the perception system data includes a camera signal continuous loss time, an image signal-to-noise ratio, an image contrast, a number of feature points in the image, and a tracking loss rate of an object, and the determining, according to the failure condition met by the vehicle data, of the target failure type of the vehicle includes: determining whether the camera signal continuous loss time is greater than a first time threshold, and if so, determining that there is a signal continuity loss phenomenon; determining whether the image signal-to-noise ratio is less than a signal-to-noise ratio threshold and whether the image contrast is less than a contrast threshold, and if so, determining that there is an image quality degradation phenomenon; determining whether the number of feature points is less than a number threshold or whether the tracking loss rate is greater than a loss rate threshold, and if so, determining that there is a visual perception algorithm abnormality phenomenon; if at least two of the signal continuity loss phenomenon, the image quality degradation phenomenon, and the visual perception algorithm abnormality phenomenon exist, determining that the target failure type of the vehicle is visual perception failure.

[0007] In a possible implementation, the perception system data includes a radar self-checking state, a point cloud density, and a detection accuracy rate, and the determining, according to the failure condition met by the vehicle data, of the target failure type of the vehicle includes: determining whether the radar self-checking state is abnormal, and if so, determining that there is a hardware state abnormality phenomenon; determining whether the point cloud density is less than a density threshold, and if so, determining that there is a point cloud data abnormality phenomenon; when the detection accuracy rate is a target miss detection rate, determining whether the target miss detection rate is greater than a miss detection rate threshold, or when the detection accuracy rate is a false alarm rate, determining whether the false alarm rate is greater than a false alarm rate threshold, and if so, determining that there is a detection performance abnormality phenomenon; if at least two of the hardware state abnormality phenomenon, the point cloud data abnormality phenomenon, and the detection performance abnormality phenomenon exist, determining that the target failure type of the vehicle is radar perception failure.

[0008] In a possible implementation, the control system data includes a path planning success rate, a number of traffic rule violations in a predetermined period, and a planning algorithm delay time, and the determining, according to the failure condition met by the vehicle data, of the target failure type of the vehicle includes: determining whether the path planning success rate is less than a success rate threshold, and if so, determining that there is a path planning algorithm abnormality phenomenon; determining whether the number of traffic rule violations in the predetermined period exceeds a number threshold, and if so, determining that there is a behavior decision logic error phenomenon; Determine whether the delay time of the planning algorithm is greater than the second time threshold. If so, it is determined that there is a real-time anomaly. If at least two of the following exist: path planning algorithm anomaly, behavioral decision-making logic error, and real-time anomaly, then the target failure type of the vehicle is determined to be decision-planning failure.

[0009] In one possible implementation, the control system data includes tracking error, actuator command and feedback discrepancies, and controller oscillation frequency. Then, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: When the tracking error is a lateral tracking error, it is determined whether the lateral tracking error is greater than a first error threshold; or, when the tracking error is a longitudinal tracking error, it is determined whether the longitudinal tracking error is greater than a second error threshold. If so, it is determined that there is an abnormal phenomenon in the control command tracking error. Determine whether the difference between the actuator command and the feedback is greater than the difference threshold. If so, it is determined that there is an abnormal actuator response. Determine whether the oscillation frequency of the controller is greater than the frequency threshold. If so, it is determined that there is a stability control failure. If at least two of the following phenomena exist: abnormal control command tracking error, abnormal actuator response, and stability control failure, then the target failure type of the vehicle is determined to be control execution failure.

[0010] In one possible implementation, the execution system data includes braking performance, braking pressure build-up time, and first fault code information. Then, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: Determine whether the braking efficiency is less than the efficiency threshold; if so, then determine that there is an abnormal braking efficiency phenomenon. Determine whether the braking pressure build-up time is greater than the third time threshold. If so, it is determined that there is an abnormal pressure build-up phenomenon. When the first fault code information indicates that the ABS and / or ESP fault codes are activated, it is determined that there is a system component error. If at least two of the following are present: abnormal braking performance, abnormal pressure build-up, and system component error, then the target failure type of the vehicle is determined to be a braking system failure.

[0011] In one possible implementation, the execution system data includes steering assist data, steering angle tracking error, and second fault code information. Then, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: When the steering assist data is the actual torque measured by the torque sensor, it is determined whether the actual torque matches the expected torque; or, when the steering assist data is the power assist motor current, it is determined whether the value of the power assist motor current is within a predetermined value range or whether the power assist motor current fluctuates abnormally; or, when the steering assist data is the response delay time, it is determined whether the response delay time is greater than the fourth time threshold. If so, it is determined that there is an abnormal steering assist phenomenon. Determine whether the steering angle tracking error is greater than the angle threshold. If so, it is determined that there is an abnormal steering angle tracking phenomenon. When the second fault code information indicates that the electric power steering system (EPS) fault code is activated, it is determined that there is an abnormality in the EPS system. If at least two of the following are present: abnormal steering assist, abnormal steering angle tracking, and abnormal EPS system, then the target failure type of the vehicle is determined to be steering system failure.

[0012] In one possible implementation, the execution system data includes throttle command and torque output error, battery or motor temperature, and transmission data. Then, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: Determine whether the error between the throttle command and the torque output is greater than the third error threshold. If so, it is determined that there is an abnormal power output phenomenon. Determine whether the temperature is greater than the temperature threshold; if so, then determine that there is an energy management anomaly. The transmission data is used to determine whether the gearbox is slipping, or whether it is unable to shift gears. If so, it is determined that there is an abnormality in the transmission system. If at least two of the following are present: abnormal power output, abnormal energy management, and abnormal transmission system, then the target failure type of the vehicle is determined to be a power system failure.

[0013] In one possible implementation, the hood system data includes latch status, hood clearance, vehicle speed, and hardware fault information. Then, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: Based on the latch status, determine whether both the primary and secondary latches are in an unlocked state. If so, it is determined that there is a latch malfunction. Determine whether the hatch gap is greater than the gap threshold and whether the vehicle speed is greater than the speed threshold. If so, it is determined that there is a gap exceeding the limit. When the hardware fault information indicates a fault in the latch motor or a fault in the hinge sensor, it is determined that a hardware fault exists. If at least two of the following are present: latch malfunction, gap overrun, and hardware failure, then the target failure type of the vehicle is determined to be a hood system failure.

[0014] According to a second aspect of this application, a vehicle failure control device is provided, the device comprising: The data acquisition module is used to acquire vehicle data during driving, and the vehicle data includes at least one of the following: perception system data, control system data, execution system data, and hood system data. The type acquisition module is used to acquire preset failure types and at least one failure condition associated with each failure type. The failure types include at least one of perception system failure, control system failure, execution system failure, and hood system failure. The perception system failure includes visual perception failure and radar perception failure. The control system failure includes decision planning failure and control execution failure. The execution system failure includes braking system failure, steering system failure, and power system failure. The hood system failure includes hood locking failure. The type determination module is used to determine the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data. A failure control module is used to determine a control mode for the vehicle based on the target failure type, and the control mode is used to control the vehicle to stop safely.

[0015] According to a third aspect of this application, a computer-readable storage medium is provided, wherein at least one instruction is stored therein, the at least one instruction being loaded and executed by a processor to implement the vehicle failure control method as described above.

[0016] According to a fourth aspect of this application, a vehicle is provided, the vehicle including the aforementioned vehicle failure control device.

[0017] The beneficial effects of the technical solution provided in this application include at least the following: Perception system failures include visual perception failures and radar perception failures; control system failures include decision-making and planning failures and control execution failures; execution system failures include braking system failures, steering system failures, and powertrain system failures; and hood system failures include hood locking failures. Each failure type is associated with at least one failure condition. By pre-setting specific failure conditions for each failure type, the vehicle can quickly match and judge based on vehicle data, accurately locating the source of the fault, rather than just issuing a vague warning of system abnormality. This lays a solid foundation for taking the correct countermeasures. Furthermore, upon detecting a failure, it does not execute an emergency stop but dynamically determines the most suitable control mode based on different target failure types, enabling differentiated intelligent decision-making. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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 flowchart of a vehicle failure control method provided in one embodiment of this application; Figure 2 This is a structural block diagram of a vehicle failure control device provided in one embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0021] like Figure 1 The diagram illustrates a flowchart of a vehicle failure control method according to an embodiment of this application. This vehicle failure control method can be applied to vehicles. The vehicle failure control method may include: Step 101: Acquire vehicle data during driving. The vehicle data includes at least one of the following: perception system data, control system data, execution system data, and hood system data.

[0022] In this embodiment, the monitored objects in the vehicle are divided into four systems: a perception system, a control system, an execution system, and a hood system. The perception system is responsible for sensing the vehicle's external environment, acting as the vehicle's "eyes" and "ears." The control system is used to think and make decisions based on the data collected by the perception system, acting as the vehicle's "brain." The execution system controls relevant components to execute decisions issued by the control system, acting as the vehicle's "hands and feet." The hood system monitors whether the hood is popped up and obstructs the driver's view.

[0023] The sensing system, control system, execution system, and hood system each have multiple sensors. These sensors can periodically collect data during vehicle operation, and this data is called vehicle data.

[0024] Step 102: Obtain the preset failure types and at least one failure condition associated with each failure type. The failure types include at least one of the following: perception system failure, control system failure, execution system failure, and hood system failure. Perception system failure includes visual perception failure and radar perception failure. Control system failure includes decision planning failure and control execution failure. Execution system failure includes braking system failure, steering system failure, and power system failure. Hood system failure includes hood locking failure.

[0025] The perception system includes visual perception and radar perception; correspondingly, perception system failures include visual perception failures and radar perception failures. Visual perception refers to analyzing images captured by cameras to obtain perception results; radar perception refers to analyzing point cloud data collected by radar to obtain perception results.

[0026] A control system comprises decision planning and control execution; correspondingly, control system failure includes decision planning failure and control execution failure. Decision planning involves formulating and issuing decisions based on perception results, while control execution involves monitoring the implementation of those decisions.

[0027] The execution system includes the braking system, steering system, and powertrain system. Correspondingly, execution system failures include braking system failure, steering system failure, and powertrain system failure. Specifically, the braking system controls vehicle deceleration based on decisions, the steering system controls the vehicle's direction of travel based on decisions, and the powertrain system outputs the energy required for vehicle movement based on decisions.

[0028] The hood system includes the hood and latches, which secure the hood to the vehicle body to prevent it from popping up.

[0029] Step 103: Determine the target failure type of the vehicle based on the failure conditions met by the vehicle data.

[0030] The following explains the failure conditions for each failure type, as well as the process for determining whether vehicle data meets the failure conditions: (1) Visual perception failure The perception system data includes the duration of camera signal loss, image signal-to-noise ratio, image contrast, number of feature points in the image, and object tracking loss rate. Based on the failure conditions satisfied by the vehicle data, the target failure type of the vehicle can be determined, which may include: Determine whether the duration of continuous signal loss from the camera exceeds a first time threshold. If so, it is determined that there is a continuous signal loss phenomenon. Determine whether the image signal-to-noise ratio is less than the signal-to-noise ratio threshold and whether the image contrast is less than the contrast threshold. If so, it is determined that there is an image quality degradation phenomenon. Determine whether the number of feature points is less than the number threshold, or whether the tracking loss rate is greater than the loss rate threshold. If so, then it is determined that there is an abnormal phenomenon in the visual perception algorithm. If at least two of the following are present: signal continuity loss, image quality degradation, and visual perception algorithm anomalies, then the target failure type of the vehicle is determined to be a visual perception failure.

[0031] The first time threshold, signal-to-noise ratio threshold, contrast threshold, quantity threshold, and loss rate threshold can be set according to actual business needs, and are not limited in this embodiment.

[0032] In one instance, if the first time threshold is 100ms, the signal-to-noise ratio threshold is 15dB, the contrast threshold is 0.1, the number threshold is 50, and the tracking loss rate threshold is 50%, then visual perception is determined to be in failure if at least two of the following conditions are met: signal loss duration > 100ms; image signal-to-noise ratio < 15dB; contrast < 0.1; number of feature points < 50; or tracking loss rate > 50%; otherwise, visual perception is determined to be not in failure.

[0033] (2) Radar sensing failure The perception system data includes radar self-test status, point cloud density, and detection accuracy. Based on the failure conditions satisfied by the vehicle data, the target failure type of the vehicle can be determined, which may include: Determine if the radar self-test status is abnormal; if so, then confirm that there is an abnormal hardware status. Determine if the point cloud density is less than the density threshold; if so, then it is determined that there is an anomaly in the point cloud data. When the detection accuracy is the target false negative rate, determine whether the target false negative rate is greater than the false negative rate threshold. Or, when the detection accuracy is the false alarm rate, determine whether the false alarm rate is greater than the false alarm rate threshold. If so, it is determined that there is an abnormal detection performance. If at least two of the following are present: abnormal hardware status, abnormal point cloud data, and abnormal detection performance, then the target failure type of the vehicle is determined to be radar perception failure.

[0034] The density threshold, false alarm rate threshold, and false alarm rate threshold can be set according to actual business needs, and are not limited in this embodiment.

[0035] In one instance, with a density threshold of 20 points / square meter, a false alarm rate threshold of 30%, and a false alarm rate threshold of 20%, the radar is determined to be ineffective if at least two of the following conditions are met: the radar self-test state is not NORMAL; the point cloud density is <20 points / square meter; the target false alarm rate is >30% or the false alarm rate is >20%; otherwise, the radar is determined to be effective.

[0036] (3) Failure of decision-making and planning Control system data includes path planning success rate, number of traffic rule violations within a predetermined time period, and planning algorithm delay time. Based on the failure conditions satisfied by the vehicle data, the target failure type of the vehicle is determined, including: Determine if the success rate of path planning is less than the success rate threshold. If so, it is determined that there is an abnormal phenomenon in the path planning algorithm. Determine whether the number of traffic rule violations within the predetermined time period exceeds the threshold. If so, it is determined that there is a problem with the behavioral decision-making logic. Determine whether the delay time of the planning algorithm is greater than the second time threshold. If so, it is determined that there is a real-time anomaly. If at least two of the following are present: path planning algorithm anomalies, behavioral decision-making logic errors, and real-time anomalies, then the vehicle's target failure type is determined to be decision-planning failure.

[0037] The success rate threshold, the scheduled time period, the number of times threshold, and the second time threshold can be set according to actual business needs, and are not limited in this embodiment.

[0038] In one instance, with a success rate threshold of 80%, a predetermined time period of 1 minute, a number of violations threshold of 1, and a second time threshold of 200ms, the decision planning is determined to be ineffective if at least two of the following conditions are met: the success rate of path planning is <80%; the number of traffic rule violations within 1 minute is >1; and the planning algorithm delay time is >200ms. Otherwise, the decision planning is determined to be effective.

[0039] (4) Control execution failure Control system data includes tracking error, actuator command and feedback discrepancies, and controller oscillation frequency. Based on the failure conditions satisfied by the vehicle data, the target failure type of the vehicle can be determined, which may include: When the tracking error is a lateral tracking error, determine whether the lateral tracking error is greater than the first error threshold; or, when the tracking error is a longitudinal tracking error, determine whether the longitudinal tracking error is greater than the second error threshold. If so, it is determined that there is an abnormal phenomenon in the control command tracking error. Determine whether the difference between the actuator command and the feedback is greater than the difference threshold. If so, it is determined that there is an abnormal actuator response. Determine if the controller oscillation frequency is greater than the frequency threshold. If so, then it is determined that there is a stability control failure. If at least two of the following phenomena exist: abnormal control command tracking error, abnormal actuator response, and stability control failure, then the target failure type of the vehicle is determined to be control execution failure.

[0040] The first error threshold, the second error threshold, the difference threshold, and the frequency threshold can be set according to actual business needs, and are not limited in this embodiment.

[0041] In one example, the first error threshold is 0.5m, the second error threshold is 2.0m, the difference threshold is 15%, and the frequency threshold is 2Hz. Then, if at least two of the following conditions are met: lateral tracking error > 0.5m or longitudinal tracking error > 2.0m; difference between actuator command and feedback > 15%; and continuous oscillation frequency of the control system > 2Hz, the control execution is determined to be ineffective; otherwise, the control execution is determined to be effective.

[0042] (5) Braking system failure The execution system data includes braking performance, brake pressure build-up time, and first fault code information. Based on the failure conditions met by the vehicle data, the target failure type of the vehicle is determined, including: Determine if the braking efficiency is less than the efficiency threshold; if so, then an abnormal braking efficiency phenomenon is confirmed. Determine whether the braking pressure build-up time is greater than the third time threshold. If so, it is determined that there is an abnormal pressure build-up phenomenon. When the first fault code information indicates that the Anti-lock Braking System (ABS) and / or Electronic Stability Program (ESP) fault codes are activated, it is determined that there is a system component error. If at least two of the following are present: abnormal braking performance, abnormal pressure build-up, and system component error, then the target failure type of the vehicle is determined to be braking system failure.

[0043] The performance threshold and the third time threshold can be set according to actual business needs, and are not limited in this embodiment.

[0044] In one instance, with an efficiency threshold of 50% (compared to the normal value) and a third time threshold of 300ms, if at least two of the following conditions are met: braking efficiency <50%; braking pressure build-up time >300ms; and ABS / ESP fault code is activated, then control execution is determined to have failed; otherwise, control execution is determined to have not failed.

[0045] (6) Steering system failure The execution system data includes steering assist data, steering angle tracking error, and second fault code information. Based on the failure conditions met by the vehicle data, the target failure type of the vehicle can be determined, which may include: When the power steering data is the actual torque measured by the torque sensor, it is determined whether the actual torque matches the expected torque; or, when the power steering data is the power steering motor current, it is determined whether the value of the power steering motor current is within the predetermined value range or whether the power steering motor current fluctuates abnormally; or, when the power steering data is the response delay time, it is determined whether the response delay time is greater than the fourth time threshold. If so, it is determined that there is a power steering abnormality. Determine if the steering angle tracking error is greater than the angle threshold. If so, then an abnormal steering angle tracking phenomenon is confirmed. When the second fault code information indicates that the Electric Power Steering (EPS) system fault code is activated, it is determined that there is an abnormality in the EPS system. If at least two of the following are present: abnormal steering assist, abnormal steering angle tracking, and abnormal EPS system, then the target failure type of the vehicle is determined to be steering system failure.

[0046] The expected torque, predetermined numerical range, fourth time threshold, and angle threshold can be set according to actual business needs, and are not limited in this embodiment.

[0047] Actual torque mismatch refers to a situation where the driver applies a small amount of the desired torque, but the actual torque is large; or, the driver applies a large amount of the desired torque, but the actual torque is small.

[0048] When the current of the assist motor is less than the minimum value of the predetermined range, it indicates that the current is too low; when the current of the assist motor is greater than the maximum value of the predetermined range, it indicates that the current is too high. Both of these situations are considered abnormal assist motor current.

[0049] If the actual torque does not match the expected torque and the power assist motor current is abnormal, then the power assist torque is abnormal; otherwise, the power assist torque is normal.

[0050] In one instance, with a fourth time threshold of 100ms and an angle threshold of 5°, the steering system is determined to have failed if at least two of the following conditions are met: abnormal power assist torque or response delay time > 100ms; steering angle tracking error > 5°; or EPS reported fault codes. Otherwise, the steering system is determined not to have failed.

[0051] (7) Power system failure The execution system data includes throttle command and torque output error, battery or motor temperature, and transmission data. Based on the failure conditions met by the vehicle data, the target failure type of the vehicle can be determined, which may include: Determine whether the error between the throttle command and the torque output is greater than the third error threshold. If so, it is determined that there is an abnormal power output phenomenon. Determine if the temperature exceeds the temperature threshold; if so, then an energy management anomaly is identified. Determine whether the gearbox is slipping based on the transmission data, or whether it is unable to shift gears based on the transmission data. If so, it is determined that there is an abnormality in the transmission system. If at least two of the following are present: abnormal power output, abnormal energy management, and abnormal transmission system, then the target failure type of the vehicle is determined to be a power system failure.

[0052] The third error threshold and temperature threshold can be set according to actual business needs, and are not limited in this embodiment.

[0053] When determining whether the transmission is slipping or unable to shift gears based on transmission data, the following specific checks can be performed: Is the ratio of the transmission's input shaft speed (turbo speed) to its output shaft speed (vehicle speed) abnormal? Does the engine torque match the vehicle acceleration? Check if the feedback signal of the shift actuator is abnormal, such as shift timeout or shift incomplete. Check if the transmission oil temperature or oil pressure is abnormal; If so, it indicates that the transmission is slipping or unable to shift gears, indicating an abnormality in the transmission system; otherwise, it indicates that there is no abnormality in the transmission system.

[0054] In one instance, if the third error threshold is 30%, then the powertrain is determined to have failed if at least two of the following conditions are met: the deviation between the throttle command and the torque output is >30%; the battery or motor temperature exceeds the limit; or the transmission slips or cannot shift gears; otherwise, the powertrain is determined not to have failed.

[0055] (8) Failure of the front canopy system The hood system data includes latch status, hood clearance, vehicle speed, and hardware fault information. Based on the failure conditions met by the vehicle data, the target failure type of the vehicle can be determined, which may include: Determine whether both the primary and secondary latches are unlocked based on their status. If so, then there is a latch malfunction. Determine whether the hatch clearance is greater than the clearance threshold and the vehicle speed is greater than the speed threshold. If so, it is determined that there is a clearance exceeding the limit. When the hardware fault information indicates a fault in the latch motor or a fault in the hinge sensor, it is confirmed that a hardware fault exists. If at least two of the following are present: latch malfunction, gap overrun, and hardware failure, then the target failure type of the vehicle is determined to be a hood system failure.

[0056] The gap threshold and vehicle speed threshold can be set according to actual business needs, and are not limited in this embodiment.

[0057] In one example, with a gap threshold of 30mm and a vehicle speed threshold of 60km / h, the hood system is determined to be faulty if at least two of the following conditions are met: the first-level latch is not LOCKED and the second-level latch is not LOCKED; the hood gap is greater than 30mm and the vehicle speed is greater than 60km / h; or the latch motor or hinge sensor is faulty. Otherwise, the hood system is determined to be not faulty.

[0058] Step 104: Determine the control mode for the vehicle based on the target failure type. This control mode is used to control the safe parking of the vehicle.

[0059] For example, when the vehicle's perception system fails but the actuators are intact, the corresponding control mode is: decelerate to a stop within the current lane.

[0060] In summary, the vehicle failure control method provided in this application includes the following: perception system failures include visual perception failures and radar perception failures; control system failures include decision-making and planning failures and control execution failures; execution system failures include braking system failures, steering system failures, and power system failures; and hood system failures include hood locking failures. Each failure type is associated with at least one failure condition. By pre-setting specific failure conditions for each failure type, the vehicle can quickly match and judge based on vehicle data, accurately locate the source of the fault, rather than just giving a vague alarm about system abnormalities. This lays a solid foundation for taking correct countermeasures. Furthermore, after detecting a failure, it does not execute an emergency stop, but dynamically determines the most suitable control mode according to different target failure types, enabling differentiated intelligent decision-making.

[0061] like Figure 2 The diagram illustrates a structural block diagram of a vehicle failure control device according to an embodiment of this application. This vehicle failure control device can be applied to a vehicle, and the device includes: The data acquisition module 210 is used to acquire vehicle data during driving. The vehicle data includes at least one of the following: perception system data, control system data, execution system data, and hood system data. The type acquisition module 220 is used to acquire preset failure types and at least one failure condition associated with each failure type. The failure types include at least one of the following: perception system failure, control system failure, execution system failure, and hood system failure. Perception system failure includes visual perception failure and radar perception failure. Control system failure includes decision planning failure and control execution failure. Execution system failure includes braking system failure, steering system failure, and power system failure. Hood system failure includes hood locking failure. The type determination module 230 is used to determine the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data. The failure control module 240 is used to determine the control mode of the vehicle based on the target failure type. The control mode is used to control the safe parking of the vehicle.

[0062] In an optional embodiment, if the perception system data includes camera signal loss duration, image signal-to-noise ratio, image contrast, number of feature points in the image, and object tracking loss rate, then the type determination module 230 is further configured to: Determine whether the duration of continuous signal loss from the camera exceeds a first time threshold. If so, it is determined that there is a continuous signal loss phenomenon. Determine whether the image signal-to-noise ratio is less than the signal-to-noise ratio threshold and whether the image contrast is less than the contrast threshold. If so, it is determined that there is an image quality degradation phenomenon. Determine whether the number of feature points is less than the number threshold, or whether the tracking loss rate is greater than the loss rate threshold. If so, then it is determined that there is an abnormal phenomenon in the visual perception algorithm. If at least two of the following are present: signal continuity loss, image quality degradation, and visual perception algorithm anomalies, then the target failure type of the vehicle is determined to be a visual perception failure.

[0063] In an optional embodiment, if the sensing system data includes radar self-test status, point cloud density, and detection accuracy, then the type determination module 230 is further used for: Determine if the radar self-test status is abnormal; if so, then confirm that there is an abnormal hardware status. Determine if the point cloud density is less than the density threshold; if so, then it is determined that there is an anomaly in the point cloud data. When the detection accuracy is the target false negative rate, determine whether the target false negative rate is greater than the false negative rate threshold. Or, when the detection accuracy is the false alarm rate, determine whether the false alarm rate is greater than the false alarm rate threshold. If so, it is determined that there is an abnormal detection performance. If at least two of the following are present: abnormal hardware status, abnormal point cloud data, and abnormal detection performance, then the target failure type of the vehicle is determined to be radar perception failure.

[0064] In an optional embodiment, if the control system data includes path planning success rate, number of traffic rule violations within a predetermined time period, and planning algorithm delay time, then the type determination module 230 is further used for: Determine if the success rate of path planning is less than the success rate threshold. If so, it is determined that there is an abnormal phenomenon in the path planning algorithm. Determine whether the number of traffic rule violations within the predetermined time period exceeds the threshold. If so, it is determined that there is a problem with the behavioral decision-making logic. Determine whether the delay time of the planning algorithm is greater than the second time threshold. If so, it is determined that there is a real-time anomaly. If at least two of the following are present: path planning algorithm anomalies, behavioral decision-making logic errors, and real-time anomalies, then the vehicle's target failure type is determined to be decision-planning failure.

[0065] In an optional embodiment, if the control system data includes tracking error, actuator command and feedback discrepancy, and controller oscillation frequency, then the type determination module 230 is further configured to: When the tracking error is a lateral tracking error, determine whether the lateral tracking error is greater than the first error threshold; or, when the tracking error is a longitudinal tracking error, determine whether the longitudinal tracking error is greater than the second error threshold. If so, it is determined that there is an abnormal phenomenon in the control command tracking error. Determine whether the difference between the actuator command and the feedback is greater than the difference threshold. If so, it is determined that there is an abnormal actuator response. Determine if the controller oscillation frequency is greater than the frequency threshold. If so, then it is determined that there is a stability control failure. If at least two of the following phenomena exist: abnormal control command tracking error, abnormal actuator response, and stability control failure, then the target failure type of the vehicle is determined to be control execution failure.

[0066] In an optional embodiment, if the system data includes braking performance, braking pressure build-up time, and first fault code information, then the type determination module 230 is further configured to: Determine if the braking efficiency is less than the efficiency threshold; if so, then an abnormal braking efficiency phenomenon is confirmed. Determine whether the braking pressure build-up time is greater than the third time threshold. If so, it is determined that there is an abnormal pressure build-up phenomenon. When the first fault code information indicates that the ABS and / or ESP fault codes are activated, it is determined that there is a system component error. If at least two of the following are present: abnormal braking performance, abnormal pressure build-up, and system component error, then the target failure type of the vehicle is determined to be braking system failure.

[0067] In an optional embodiment, if the system data includes steering assist data, steering angle tracking error, and second fault code information, then the type determination module 230 is further configured to: When the power steering data is the actual torque measured by the torque sensor, it is determined whether the actual torque matches the expected torque; or, when the power steering data is the power steering motor current, it is determined whether the value of the power steering motor current is within the predetermined value range or whether the power steering motor current fluctuates abnormally; or, when the power steering data is the response delay time, it is determined whether the response delay time is greater than the fourth time threshold. If so, it is determined that there is a power steering abnormality. Determine if the steering angle tracking error is greater than the angle threshold. If so, then an abnormal steering angle tracking phenomenon is confirmed. When the second fault code information indicates that the EPS fault code is activated, it is determined that there is an abnormality in the EPS system. If at least two of the following are present: abnormal steering assist, abnormal steering angle tracking, and abnormal EPS system, then the target failure type of the vehicle is determined to be steering system failure.

[0068] In an optional embodiment, if the execution system data includes throttle command and torque output error, battery or motor temperature, and transmission data, then the type determination module 230 is further configured to: Determine whether the error between the throttle command and the torque output is greater than the third error threshold. If so, it is determined that there is an abnormal power output phenomenon. Determine if the temperature exceeds the temperature threshold; if so, then an energy management anomaly is identified. Determine whether the gearbox is slipping based on the transmission data, or whether it is unable to shift gears based on the transmission data. If so, it is determined that there is an abnormality in the transmission system. If at least two of the following are present: abnormal power output, abnormal energy management, and abnormal transmission system, then the target failure type of the vehicle is determined to be a power system failure.

[0069] In an optional embodiment, if the hood system data includes latch status, hood clearance, vehicle speed, and hardware fault information, then the type determination module 230 is further used for: Determine whether both the primary and secondary latches are unlocked based on their status. If so, then there is a latch malfunction. Determine whether the hatch clearance is greater than the clearance threshold and the vehicle speed is greater than the speed threshold. If so, it is determined that there is a clearance exceeding the limit. When the hardware fault information indicates a fault in the latch motor or a fault in the hinge sensor, it is confirmed that a hardware fault exists. If at least two of the following are present: latch malfunction, gap overrun, and hardware failure, then the target failure type of the vehicle is determined to be a hood system failure.

[0070] In summary, the vehicle failure control device provided in this application embodiment perceives system failures including visual perception failures and radar perception failures, control system failures including decision-making and planning failures and control execution failures, execution system failures including braking system failures, steering system failures, and power system failures, and hood system failures including hood locking failures. Each failure type is associated with at least one failure condition. Thus, by pre-setting specific failure conditions for each failure type, the vehicle can quickly match and judge based on vehicle data, accurately locate the source of the fault, rather than just giving a vague alarm about system abnormalities. This lays a solid foundation for taking correct countermeasures. Furthermore, after detecting a failure, it does not execute an emergency stop, but dynamically determines the most suitable control mode according to different target failure types, enabling differentiated intelligent decision-making.

[0071] One embodiment of this application provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the vehicle failure control method described above.

[0072] One embodiment of this application provides a vehicle that includes a failure control device for any of the above-described vehicles.

[0073] It should be noted that the vehicle failure control device provided in the above embodiments is only illustrated by the division of the above functional modules when performing vehicle failure control. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the vehicle failure control device can be divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle failure control device and the vehicle failure control method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0074] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0075] The above description is not intended to limit the embodiments of this application. Any adjustments, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A vehicle failure control method, characterized in that, The method includes: Vehicle data is acquired during driving, and the vehicle data includes at least one of the following: perception system data, control system data, execution system data, and hood system data; Obtain preset failure types and at least one failure condition associated with each failure type. The failure types include at least one of perception system failure, control system failure, execution system failure, and hood system failure. The perception system failure includes visual perception failure and radar perception failure. The control system failure includes decision planning failure and control execution failure. The execution system failure includes braking system failure, steering system failure, and power system failure. The hood system failure includes hood locking failure. Based on the failure conditions satisfied by the vehicle data, determine the target failure type of the vehicle; The control mode for the vehicle is determined based on the target failure type, and the control mode is used to control the safe parking of the vehicle.

2. The vehicle failure control method according to claim 1, characterized in that, The perception system data includes camera signal loss duration, image signal-to-noise ratio, image contrast, number of feature points in the image, and object tracking loss rate. Therefore, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: Determine whether the duration of continuous signal loss from the camera exceeds a first time threshold; if so, then it is determined that there is a continuous signal loss phenomenon. Determine whether the image signal-to-noise ratio is less than the signal-to-noise ratio threshold, and determine whether the image contrast is less than the contrast threshold. If so, it is determined that there is an image quality degradation phenomenon. Determine whether the number of feature points is less than a number threshold, or determine whether the tracking loss rate is greater than a loss rate threshold. If so, it is determined that there is an abnormal phenomenon in the visual perception algorithm. If at least two of the following exist: signal continuity loss, image quality degradation, and visual perception algorithm anomalies, then the target failure type of the vehicle is determined to be a visual perception failure.

3. The vehicle failure control method according to claim 1, characterized in that, The perception system data includes radar self-test status, point cloud density, and detection accuracy. Therefore, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: Determine whether the radar self-test status is abnormal; if so, then it is determined that there is an abnormal hardware status. Determine whether the point cloud density is less than the density threshold. If so, it is determined that there is an abnormal point cloud data phenomenon. When the detection accuracy is the target false alarm rate, it is determined whether the target false alarm rate is greater than the false alarm rate threshold. Alternatively, when the detection accuracy is the false alarm rate, it is determined whether the false alarm rate is greater than the false alarm rate threshold. If so, it is determined that there is an abnormal detection performance. If at least two of the following are present: abnormal hardware status, abnormal point cloud data, and abnormal detection performance, then the target failure type of the vehicle is determined to be radar perception failure.

4. The vehicle failure control method according to claim 1, characterized in that, The control system data includes path planning success rate, number of traffic rule violations within a predetermined time period, and planning algorithm delay time. Therefore, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: Determine whether the success rate of the path planning is less than the success rate threshold. If so, it is determined that there is an abnormal phenomenon in the path planning algorithm. Determine whether the number of traffic rule violations within the predetermined time period exceeds the threshold. If so, it is determined that there is a behavioral decision-making logic error. Determine whether the delay time of the planning algorithm is greater than the second time threshold. If so, it is determined that there is a real-time anomaly. If at least two of the following exist: path planning algorithm anomaly, behavioral decision-making logic error, and real-time anomaly, then the target failure type of the vehicle is determined to be decision-planning failure.

5. The vehicle failure control method according to claim 1, characterized in that, The control system data includes tracking error, actuator command and feedback discrepancies, and controller oscillation frequency. Therefore, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: When the tracking error is a lateral tracking error, it is determined whether the lateral tracking error is greater than a first error threshold; or, when the tracking error is a longitudinal tracking error, it is determined whether the longitudinal tracking error is greater than a second error threshold. If so, it is determined that there is an abnormal phenomenon in the control command tracking error. Determine whether the difference between the actuator command and the feedback is greater than the difference threshold. If so, it is determined that there is an abnormal actuator response. Determine whether the oscillation frequency of the controller is greater than the frequency threshold. If so, it is determined that there is a stability control failure. If at least two of the following phenomena exist: abnormal control command tracking error, abnormal actuator response, and stability control failure, then the target failure type of the vehicle is determined to be control execution failure.

6. The vehicle failure control method according to claim 1, characterized in that, The execution system data includes braking performance, braking pressure build-up time, and first fault code information. Therefore, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: Determine whether the braking efficiency is less than the efficiency threshold; if so, then determine that there is an abnormal braking efficiency phenomenon. Determine whether the braking pressure build-up time is greater than the third time threshold. If so, it is determined that there is an abnormal pressure build-up phenomenon. When the first fault code information indicates that the ABS and / or ESP fault codes are activated, it is determined that there is a system component error. If at least two of the following are present: abnormal braking performance, abnormal pressure build-up, and system component error, then the target failure type of the vehicle is determined to be a braking system failure.

7. The vehicle failure control method according to claim 1, characterized in that, The execution system data includes steering assist data, steering angle tracking error, and second fault code information. Therefore, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: When the steering assist data is the actual torque measured by the torque sensor, it is determined whether the actual torque matches the expected torque; or, when the steering assist data is the power assist motor current, it is determined whether the value of the power assist motor current is within a predetermined value range or whether the power assist motor current fluctuates abnormally; or, when the steering assist data is the response delay time, it is determined whether the response delay time is greater than the fourth time threshold. If so, it is determined that there is an abnormal steering assist phenomenon. Determine whether the steering angle tracking error is greater than the angle threshold. If so, it is determined that there is an abnormal steering angle tracking phenomenon. When the second fault code information indicates that the electric power steering system (EPS) fault code is activated, it is determined that there is an abnormality in the EPS system. If at least two of the following are present: abnormal steering assist, abnormal steering angle tracking, and abnormal EPS system, then the target failure type of the vehicle is determined to be steering system failure.

8. The vehicle failure control method according to claim 1, characterized in that, The execution system data includes throttle command and torque output error, battery or motor temperature, and transmission data. The step of determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: Determine whether the error between the throttle command and the torque output is greater than the third error threshold. If so, it is determined that there is an abnormal power output phenomenon. Determine whether the temperature is greater than the temperature threshold; if so, then determine that there is an energy management anomaly. The transmission data is used to determine whether the gearbox is slipping, or whether it is unable to shift gears. If so, it is determined that there is an abnormality in the transmission system. If at least two of the following are present: abnormal power output, abnormal energy management, and abnormal transmission system, then the target failure type of the vehicle is determined to be a power system failure.

9. The vehicle failure control method according to claim 1, characterized in that, The hood system data includes latch status, hood clearance, vehicle speed, and hardware fault information. Therefore, determining the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data includes: Based on the latch status, determine whether both the primary and secondary latches are in an unlocked state. If so, it is determined that there is a latch malfunction. Determine whether the hatch gap is greater than the gap threshold and whether the vehicle speed is greater than the speed threshold. If so, it is determined that there is a gap exceeding the limit. When the hardware fault information indicates a fault in the latch motor or a fault in the hinge sensor, it is determined that a hardware fault exists. If at least two of the following are present: latch malfunction, gap overrun, and hardware failure, then the target failure type of the vehicle is determined to be a hood system failure.

10. A vehicle failure control device, characterized in that, The device includes: The data acquisition module is used to acquire vehicle data during driving, wherein the vehicle data includes at least one of the following: perception system data, control system data, execution system data, and hood system data. The type acquisition module is used to acquire preset failure types and at least one failure condition associated with each failure type. The failure types include at least one of perception system failure, control system failure, execution system failure, and hood system failure. The perception system failure includes visual perception failure and radar perception failure. The control system failure includes decision planning failure and control execution failure. The execution system failure includes braking system failure, steering system failure, and power system failure. The hood system failure includes hood locking failure. The type determination module is used to determine the target failure type of the vehicle based on the failure conditions satisfied by the vehicle data. A failure control module is used to determine a control mode for the vehicle based on the target failure type, and the control mode is used to control the vehicle to stop safely.

Images