Methods, devices, equipment and media for detecting stall faults in autonomous vehicles

Abstract

This invention relates to the field of vehicle control technology, and provides a method, apparatus, device, and medium for detecting stall faults in autonomous vehicles. It can collect data from multiple sensors in real time and confirm whether stall fault detection conditions are met based on this data, avoiding the problem of false alarms caused by data from a single sensor. The judgment based on stall fault detection conditions also effectively improves reliability. Based on an odometer-command speed integrator, an odometer-wheel speed integrator, a wheel-motor speed integrator, and a wheel slippage detection integrator, it can effectively prevent misjudgments. It can detect whether the target autonomous vehicle is in a transient protection state, effectively distinguishing between speed changes caused by normal operation and actual hardware faults. Based on fault mode recognition using the odometer-wheel speed integrator, wheel-motor speed integrator, and wheel slippage detection integrator, it can accurately locate the fault after detecting vehicle stall.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a method, apparatus, device, and medium for detecting stall faults in autonomous vehicles. Background Technology

[0002] In the field of autonomous vehicles, vehicle stall refers to an abnormal state in which the actual motion of a vehicle differs from the expected motion state after receiving forward or backward control commands. Vehicle stall can be caused by a variety of hardware failures and can seriously affect the safety of autonomous driving systems.

[0003] Existing vehicle stall detection technologies mainly rely on data from a single sensor or simple threshold judgments, which has the following significant drawbacks:

[0004] 1. Poor anti-interference capability: Sensor noise and short-term fluctuations can easily lead to false alarms, making it impossible to distinguish between real faults and transient disturbances;

[0005] 2. Insufficient fault location capability: It can only detect stall phenomena, but cannot determine which part of the power system the fault occurred in;

[0006] 3. Lack of odometer reliability verification mechanism: When the odometer sensor itself malfunctions, the odometer-based detection method will fail;

[0007] 4. Lack of transient event suppression mechanism: Due to the inherent play in the vehicle chassis, a large number of false alarms will be generated in normal operating scenarios such as emergency stopping and rapid deceleration.

[0008] Therefore, there is an urgent need for an intelligent vehicle stall detection method that can accurately detect vehicle stall, precisely locate the fault type, verify the effectiveness of the odometer, and suppress transient false alarms. Summary of the Invention

[0009] In view of the above, it is necessary to provide a method, device, equipment and medium for detecting stall faults in autonomous vehicles, in order to solve the problem of the inability to accurately detect stall faults in autonomous vehicles.

[0010] A stall fault detection method for an autonomous vehicle, the method comprising:

[0011] In response to the stall fault detection command of the target autonomous vehicle, chassis data, control command data and odometer data are collected in real time as multi-sensor data;

[0012] Confirm whether the stall fault detection conditions are met based on the data from the multiple sensors.

[0013] When the stall fault detection conditions are confirmed to be met, an odometer-command speed integrator, an odometer-wheel speed integrator, a wheel-motor speed integrator, and a wheel slippage detection integrator are constructed using a double-ended queue based on the multi-channel sensor data and including timestamp-value pairs.

[0014] Real-time detection of whether the odometer-command speed integrator is triggered, and when the odometer-command speed integrator is detected to be triggered, confirmation that the target autonomous vehicle is in a primary stall state;

[0015] Detect whether the target autonomous vehicle is in a transient protection state;

[0016] When the target autonomous vehicle is not in the transient protection state, the target fault mode of the target autonomous vehicle is obtained by fault mode identification based on the odometer-wheel speed integrator, the wheel-motor speed integrator and the wheel slippage detection integrator.

[0017] A stall fault detection device for an autonomous vehicle, the stall fault detection device for an autonomous vehicle comprising:

[0018] The data acquisition unit is used to respond to the stall fault detection command of the target autonomous vehicle and collect chassis data, control command data and odometer data in real time as multi-sensor data.

[0019] The confirmation unit is used to confirm whether the stall fault detection conditions are met based on the multi-channel sensor data.

[0020] The acquisition unit is used to acquire, when it is confirmed that the stall fault detection conditions are met, an odometer-command speed integrator, an odometer-wheel speed integrator, a wheel-motor speed integrator and a wheel slippage detection integrator constructed based on the multi-channel sensor data using a double-ended queue.

[0021] The detection unit is used to detect in real time whether the odometer-command speed integrator is triggered, and when the odometer-command speed integrator is detected to be triggered, confirm that the target autonomous vehicle is in a main stall state.

[0022] The detection unit is also used to detect whether the target autonomous vehicle is in a transient protection state;

[0023] The identification unit is used to identify the target fault mode of the target autonomous vehicle based on the odometer-wheel speed integrator, the wheel-motor speed integrator and the wheel slippage detection integrator when the target autonomous vehicle is not in the transient protection state.

[0024] A computer device, the computer device comprising:

[0025] A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the stall fault detection method for the autonomous vehicle.

[0026] A computer-readable storage medium storing at least one instruction, which is executed by a processor in a computer device to implement a stall fault detection method for an autonomous vehicle.

[0027] As can be seen from the above technical solutions, the present invention can collect multi-channel sensor data in real time and confirm whether the stall fault detection conditions are met based on the multi-channel sensor data, avoiding the problem of false alarms caused by single sensor data. The judgment based on the stall fault detection conditions also effectively improves reliability. Based on the odometer-command speed integrator, odometer-wheel speed integrator, wheel-motor speed integrator and wheel slippage detection integrator constructed by using a dual-end queue, it can effectively prevent false judgments. It can detect whether the target autonomous vehicle is in a transient protection state and can effectively distinguish between speed changes caused by normal operation and real hardware faults. Based on the odometer-wheel speed integrator, wheel-motor speed integrator and wheel slippage detection integrator, fault mode recognition can be performed to accurately locate the fault after the vehicle stall is detected. Attached Figure Description

[0028] Figure 1 This is a flowchart of a preferred embodiment of the stall fault detection method for autonomous vehicles of the present invention;

[0029] Figure 2 This is a functional block diagram of a preferred embodiment of the stall fault detection device for autonomous vehicles of the present invention;

[0030] Figure 3 This is a schematic diagram of the structure of a computer device that implements a stall fault detection method for autonomous vehicles according to the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] like Figure 1 The diagram shown is a flowchart of a preferred embodiment of the stall fault detection method for autonomous vehicles according to the present invention. The order of the steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements.

[0033] The stall fault detection method for autonomous vehicles is applied to one or more computer devices. The computer device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0034] The computer device can be any electronic product that can interact with the user, such as a personal computer, tablet computer, smartphone, personal digital assistant (PDA), game console, interactive network television (IPTV), smart wearable device, etc.

[0035] The computer equipment may also include network equipment and / or user equipment. The network equipment includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0036] The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0037] Artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0038] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0039] The network in which the computer device is located includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, and virtual private network (VPN).

[0040] S10, in response to a stall fault detection command for the target autonomous vehicle, collects chassis data, control command data, and odometer data in real time as multi-sensor data.

[0041] In this embodiment, when the target autonomous vehicle starts, detection parameters (such as sliding window duration of 0.5 seconds, integral threshold of 0.3-0.4 meters, protection duration of 1.0 second, etc.) and vehicle parameters (wheelbase, track width, wheel radius, reduction ratio, etc.) can be loaded from the configuration file, and each core module is initialized. The Cyber ​​RT (Cyber ​​Real-Time, vehicle-road cooperative real-time system) node is started to subscribe to chassis data, control command data, and odometer data for positioning, a total of three sensor data.

[0042] The values ​​of various parameters and integrator thresholds involved in this embodiment (such as sliding window duration, integration threshold, protection duration, minimum protection interval, etc.) can be recommended values ​​determined based on a large amount of road test data and engineering calibration experience of actual autonomous vehicles. In actual use, they can be adjusted according to different vehicle models and application scenarios.

[0043] Specifically, when chassis data arrives (100Hz), the angular velocities of the left and right rear wheels, motor angular velocity, steering wheel angle, and emergency stop signal are extracted. The average linear velocity of the wheels and the linear velocity of the motor are calculated. If an emergency stop signal is detected (the estop flag in the chassis message is true), transient protection can be activated directly. When control command data arrives (50Hz), the desired speed is extracted (this speed is calculated and generated by the planning and decision module of the autonomous driving system based on the path planning results and sent to the chassis actuators through control command messages; this field can be read directly from the control command messages). If a speed mutation is detected (i.e., |current speed - previous speed| > 0.5 m / s and the current speed is close to 0), transient protection is activated. When odometer data arrives (100Hz), the odometer speed is extracted, triggering subsequent processing procedures.

[0044] In this embodiment, the stall fault detection command can be automatically triggered after the target autonomous vehicle starts, so as to achieve comprehensive protection of the target autonomous vehicle during operation.

[0045] In this embodiment, the chassis data may include, but is not limited to, wheel speed, motor speed, steering wheel angle, etc. The sampling frequency of the chassis data may be 100Hz.

[0046] In this embodiment, the control command data may include the desired speed, etc. The sampling frequency of the control command data may be 50Hz.

[0047] In this embodiment, the odometer data may include the actual vehicle speed estimated by a positioning module (such as an odometer). The sampling frequency of the odometer data may be 100Hz.

[0048] This embodiment collects data from multiple sensors, which provides a comprehensive data foundation for subsequent processing and avoids misjudgments caused by single data points.

[0049] S11, confirm whether the stall fault detection conditions are met based on the multi-channel sensor data.

[0050] In this embodiment, confirming whether the stall fault detection conditions are met based on the multi-sensor data includes:

[0051] Calculate the timestamp difference between any consecutive preset frames of data in the multi-channel sensor data;

[0052] When the timestamp difference is less than the duration threshold, it is confirmed that the multi-channel sensor data has passed the data synchronization verification.

[0053] Establish a sliding window for gear selection that includes a preset sample size;

[0054] The preset sample size of odometer speed is obtained from the odometer data based on the gear position determination sliding window;

[0055] When the odometer speeds of the preset sample size all have the same value, the current gear of the target autonomous vehicle is detected based on the odometer speeds of the preset sample size.

[0056] When the current gear is a forward gear or a reverse gear, the validity of the odometer of the target autonomous vehicle is detected based on the chassis data and the odometer data;

[0057] When the odometer is valid, it is confirmed that the stall fault detection conditions are met.

[0058] For example, the system can detect if the timestamp difference between the three sensor data streams is less than 0.3 seconds. If it is, the data is synchronized. Then, gear inference is performed, maintaining a 3-sample sliding window. The gear is inferred based on the odometer speed, and the gear status is updated only when all three samples are consistent. Specifically, a speed absolute value < 0.1 m / s indicates a parking gear, > 0 indicates a forward gear, and < 0 indicates a reverse gear. This embodiment only initiates the stall detection process when the target autonomous vehicle is in forward or reverse gear (i.e., the expected state of motion). Stall detection is not performed when the vehicle is in parking gear, thus avoiding false alarms when the vehicle is stationary.

[0059] Among them, using a 3-sample sliding window for gear inference can effectively perform de-jitter processing.

[0060] Furthermore, the step of validating the odometer of the target autonomous vehicle based on the chassis data and the odometer data includes:

[0061] Calculate the virtual speed of each left rear wheel and the virtual speed of each right rear wheel based on the odometer data;

[0062] The actual speeds of the left and right rear wheels of the target autonomous vehicle are obtained from the chassis data.

[0063] Calculate the difference between the virtual speed of each left rear wheel and the actual speed of the corresponding left rear wheel to obtain the speed difference of each left rear wheel, and input each speed difference of the left rear wheel into the left rear wheel speed difference integrator in sequence according to the time sequence;

[0064] Calculate the difference between the virtual speed of each right rear wheel and the actual speed of the corresponding right rear wheel to obtain the speed difference of each right rear wheel, and input each speed difference of the right rear wheel into the right rear wheel speed difference integrator in sequence according to the time order;

[0065] When the left rear wheel speed difference integrator and the right rear wheel speed difference integrator are triggered simultaneously, the odometer is determined to be invalid; or

[0066] When the left rear wheel speed difference integrator and the right rear wheel speed difference integrator are not triggered simultaneously, the odometer is determined to be valid.

[0067] The left rear wheel speed difference integrator and the right rear wheel speed difference integrator adopt the GREATER_THAN greater than mode and have the same time window and threshold.

[0068] In this embodiment, calculating the virtual speed of each left rear wheel and the virtual speed of each right rear wheel based on the odometer data includes:

[0069] The distance between the front and rear axles of the target autonomous vehicle is obtained as the wheelbase, and the steering wheel angle of the target autonomous vehicle is obtained from the chassis data;

[0070] The turning radius is obtained by calculating the quotient between the wheelbase and the tangent of the steering wheel angle.

[0071] Obtain the speed of each odometer from the odometer data;

[0072] Calculate the quotient of each odometer speed and the turning radius to obtain each angular velocity of the target autonomous vehicle around the instantaneous turning center;

[0073] The distance between the left and right rear wheels of the target autonomous vehicle is obtained as the wheelbase.

[0074] Calculate the product of each angular velocity and the wheel track, and then calculate the quotient of the product with 2 to obtain each target value;

[0075] Calculate the difference between each odometer speed and the corresponding target value to obtain the virtual speed of each left rear wheel;

[0076] Calculate the sum of the speed of each odometer and the corresponding target value to obtain the virtual speed of each right rear wheel.

[0077] In the above embodiment, two sliding window integrators are constructed to calculate the difference between the virtual and actual speeds of the left and right wheels, respectively. The odometer data is deemed invalid only when both integrators are triggered simultaneously (e.g., a threshold of 0.1 meters; that is, if the integral value within the sliding window is consistently greater than 0.1 meters, then the corresponding integrator is triggered). The reason for requiring simultaneous triggering on both sides is that single-sided triggering may be caused by a fault in a single wheel sensor or local road surface anomalies. Odometer malfunctions will cause the virtual speeds calculated based on the odometer to deviate from their actual values ​​simultaneously. Therefore, simultaneous anomalies on both sides are necessary to reliably indicate a problem with the odometer itself. This embodiment utilizes vehicle kinematic constraints to achieve the odometer's self-test function without additional sensors, thereby avoiding the problem of odometer-based detection methods failing when the odometer sensor itself malfunctions.

[0078] This embodiment can also support timely marking and alarming when the odometer fails, thereby preventing false judgments of stall based on erroneous positioning data.

[0079] In the above embodiments, the odometer verification method based on the vehicle kinematics model can detect positioning system faults without the need for additional redundant sensors. Independent verification of odometer data is achieved by comparing virtual wheel speeds with actual wheel speeds.

[0080] S12, when it is confirmed that the stall fault detection condition is met, acquire the odometer-command speed integrator, odometer-wheel speed integrator, wheel-motor speed integrator and wheel slippage detection integrator constructed based on the multi-channel sensor data using a dual-end queue.

[0081] In this embodiment, each integrator is a parallel sliding window integrator.

[0082] In this embodiment, when new data is input into each integrator, the time when the new data enters each integrator is used as a timestamp, and a new timestamp-value pair is constructed using the new data as the value.

[0083] Specifically, the new timestamp-value pairs are written into the data queues of each integrator in chronological order; when the time span of a data queue exceeds the maximum duration threshold (e.g., 0.5 seconds), the earliest written data (e.g., the old data at the head of the queue) is removed from the data queue to maintain the validity of the data.

[0084] In this embodiment, the mean of the new data and the previous frame data is calculated, and the time interval between the new data and the previous frame data is calculated; the product of the mean and the time interval is calculated as the integral increment corresponding to the new data; the integral increment is accumulated based on the previous integral to obtain the integral value corresponding to the new data.

[0085] For example, the formula for calculating the integral increment can be: integral_value += (current_value + previous_value) × Δt / 2.

[0086] Where, integral_value+ represents the integral increment; current_value represents the current data value; previous_value represents the data value of the previous frame; Δt represents the time interval between two adjacent data points, that is, the difference between the current data timestamp and the previous frame data timestamp.

[0087] Each integrator uses a double-ended queue to store timestamp-value pairs, and robust anomaly detection is achieved through trapezoidal integration within the time window.

[0088] In this embodiment, the odometer-command speed integrator takes the absolute speed difference between the odometer speed in the odometer data and the control command speed in the control command data as input; the odometer-wheel speed integrator takes the absolute speed difference between the odometer speed in the odometer data and the wheel linear speed in the chassis data as input; the wheel-motor speed integrator takes the absolute speed difference between the wheel linear speed and the motor linear speed in the chassis data as input; and the wheel slippage detection integrator takes the absolute value of the odometer speed in the odometer data as input.

[0089] The odometer-command speed integrator, the odometer-wheel speed integrator, and the wheel-motor speed integrator all use the GREATER_THAN greater than mode, while the wheel slippage detection integrator uses the LESS_THAN less than mode.

[0090] In the GREATER_THAN mode, when the integral value within the corresponding time window is continuously greater than the configured threshold, the corresponding sliding window integrator is triggered, indicating a continuous speed deviation anomaly. In the LESS_THAN mode, when the integral value within the corresponding time window is continuously less than the configured threshold, the corresponding sliding window integrator is triggered. If the integral value within the window is continuously less than the set threshold, it indicates that the actual wheel speed is continuously at an abnormally low value (e.g., the wheel hardly rotates), which is determined to be wheel slippage.

[0091] In other words, the detection result is only output when the window duration reaches the set value and the integral value meets the triggering condition, which can effectively prevent misjudgment when the window is not full.

[0092] For example, four integrators can be represented as follows:

[0093] Odometer-command speed integrator (GREATER_THAN mode, input |odometer speed - control command speed|, threshold 0.4 meters) is used to detect main stall phenomenon;

[0094] Odometer-wheel speed integrator (GREATER_THAN mode, input |odometer speed - wheel linear speed|, threshold 0.3 meters) is used to detect drivetrain disconnection;

[0095] Wheel-motor speed integrator (GREATER_THAN mode, input |wheel linear speed - motor linear speed|, threshold 0.3 m) is used to detect transmission faults from the motor to the wheel;

[0096] The wheel slip detection integrator (LESS_THAN mode, input odometer speed absolute value, threshold 0.1 m / s) is used to detect wheel slippage. It is triggered when the odometer speed remains below the threshold for a continuous period of time within the slip window, indicating that although the vehicle has received a motion command, the wheels are hardly turning.

[0097] Wherein, the wheel linear velocity = (left rear wheel angular velocity + right rear wheel angular velocity) / 2 × wheel radius, and the motor linear velocity = motor angular velocity × wheel radius / reduction ratio.

[0098] This embodiment uses a sliding window integral algorithm instead of instantaneous threshold judgment. By filtering sensor noise and short-term fluctuations through the cumulative effect within the time window, it can effectively reduce the false alarm rate. The dual threshold triggering mechanism also ensures that only continuous anomalies will trigger an alarm, effectively distinguishing between transient disturbances and real faults, and has high robustness and anti-interference capability.

[0099] S13, Real-time detection of whether the odometer-command speed integrator is triggered, and when the odometer-command speed integrator is detected to be triggered, confirmation that the target autonomous vehicle is in a primary stall state.

[0100] For example, the difference between the calculated odometer speed and the control command speed can be detected (due to the different sampling frequencies of the three data streams, the most recently received control command speed and chassis data are used for calculation when the odometer data arrives; the aforementioned data synchronization verification ensures that the time difference between these data is within an acceptable range), and input into the odometer-command speed integrator. If the odometer-command speed integrator is triggered, it indicates that a primary stall has occurred.

[0101] S14, detect whether the target autonomous vehicle is in a transient protection state.

[0102] In this embodiment, detecting whether the target autonomous vehicle is in a transient protection state includes:

[0103] Detect whether an emergency stop sign is present in the chassis data;

[0104] When the emergency stop sign is detected in the chassis data, an emergency stop event is confirmed.

[0105] Obtain the current frame control command speed and the previous frame control command speed from the control command data, and calculate the absolute difference between the current frame control command speed and the previous frame control command speed;

[0106] When the absolute difference is greater than the difference threshold and the speed of the current frame control command is less than a preset value, a speed change event is confirmed to have occurred.

[0107] When the emergency stop event and / or the speed change event are confirmed to occur, the system enters the transient protection state, records the current timestamp, and provides transient protection for the target autonomous vehicle.

[0108] Specifically, when providing transient protection for the target autonomous vehicle, alarms based on the main stall state are prohibited during the protection period starting from the current timestamp.

[0109] Specifically, if the transient protection state is confirmed to have been entered again within the minimum protection interval starting from the current timestamp, transient protection for the target autonomous vehicle will be refused.

[0110] The emergency stop flag can be the estop signal included in the chassis data. This signal is set by the vehicle chassis controller when the driver presses the emergency stop button. Emergency stop events can be detected by reading this flag in the chassis message.

[0111] Among them, the speed of the control command of the previous frame can be cached. When the absolute value of the speed difference between two adjacent frames exceeds 0.5m / s and the current command speed is close to 0, it can be determined as a rapid deceleration or emergency stop command, confirming that a speed change event has occurred.

[0112] Protection can be triggered when any of the above conditions are met.

[0113] Specifically, the odometer-command speed integrator is prohibited from outputting a fault alarm during the protection period (e.g., 1.0 second). A minimum protection interval (e.g., 10.0 seconds) can also be set; if protection is triggered again within 10 seconds, protection is denied, and the event is determined to be a genuine fault rather than a transient event.

[0114] In the above embodiments, by combining a time window with a state machine, a dual-flag state machine manages the protection state, enabling automatic identification of normal operating scenarios such as emergency stops and rapid deceleration, and intelligently distinguishing between speed changes caused by normal operations and actual hardware faults. Furthermore, it suppresses false alarms during the protection period, effectively mitigating false alarms caused by normal transient events. In addition, the minimum protection interval mechanism prevents actual faults from being misjudged as transient events, effectively reducing the false alarm rate and maintaining a 100% fault detection rate.

[0115] In this embodiment, if the transient protection period is in effect, the subsequent judgment is skipped.

[0116] S15, when the target autonomous vehicle is not in the transient protection state, fault mode identification is performed based on the odometer-wheel speed integrator, the wheel-motor speed integrator and the wheel slippage detection integrator to obtain the target fault mode of the target autonomous vehicle.

[0117] In this embodiment, the step of identifying the target fault mode of the target autonomous vehicle based on the odometer-wheel speed integrator, the wheel-motor speed integrator, and the wheel slippage detection integrator includes:

[0118] Detect whether the wheel slip detection integrator is triggered, and if the wheel slip detection integrator is detected to be triggered, determine that the target fault mode is wheel slip; or

[0119] When the wheel slippage detection integrator is not triggered, and the odometer-wheel speed integrator is not triggered but the wheel-motor speed integrator is triggered, the target fault mode is determined to be motor shaft breakage; or

[0120] When the wheel slippage detection integrator is not triggered, and the odometer-wheel speed integrator is triggered while the wheel-motor speed integrator is not triggered, the target fault mode is determined to be a drivetrain breakage; or

[0121] When the wheel slip detection integrator, the odometer-wheel speed integrator, and the wheel-motor speed integrator are all detected as not being triggered, the target fault mode is determined to be brake failure.

[0122] If other situations occur (such as the odometer-wheel speed integrator and the wheel-motor speed integrator being triggered, but the wheel slippage detection integrator not being triggered), it is determined to be an unknown fault. This situation indicates that multiple sensor data are abnormal but do not conform to the known fault mode. The data of each sensor and the status of the integrator at that time can be recorded for subsequent offline analysis, and a safe parking process can be triggered to ensure safety.

[0123] For example, if a main stall is triggered, the first step is to determine if wheel slippage is the cause (whether the wheel slippage detection integrator is triggered, i.e., whether the odometer speed is consistently below a threshold). If not slippage, the fault mode identification process begins: calculating the odometer-wheel speed difference and the wheel-motor speed difference, and inputting them into the corresponding integrators. Fault classification is then performed based on the combination of the trigger states of the three integrators. Specifically, if the odometer-wheel speed integrator is not triggered but the wheel-motor speed integrator is triggered, it indicates a broken motor shaft; if the odometer-wheel speed integrator is triggered but the wheel-motor speed integrator is not triggered, it indicates a broken drivetrain; if neither is triggered, it indicates brake failure; other situations are considered unknown faults.

[0124] In the above embodiments, the fault classification decision tree based on the combination of multiple integrator states compares the three integrators pairwise, enabling precise fault location through logical combination. Specifically, the fault classification decision tree can accurately identify five fault types (motor shaft breakage, transmission chain breakage, brake failure, wheel slippage, and unknown fault). Unlike traditional methods that can only detect stall phenomena, this embodiment directly locates the faulty component, effectively shortening the maintenance and diagnosis time, and also achieving a high fault classification accuracy.

[0125] In this embodiment, after obtaining the target fault mode of the target autonomous vehicle, the method further includes:

[0126] When the target fault mode is wheel slippage, reduce the target speed of the target autonomous vehicle and trigger traction control; or

[0127] When the target fault mode is a broken motor shaft or a broken drivetrain, control the target autonomous vehicle to perform a safe stop; or

[0128] When the target fault mode is brake failure, control the target autonomous vehicle to perform emergency braking and send an alarm notification to the remote monitoring center;

[0129] When no fault mode is detected, the target autonomous vehicle is controlled to perform a safe stop and all sensor data of the target autonomous vehicle is recorded.

[0130] For example, corresponding response measures can be taken for different fault modes: when the wheels slip, the planning module is notified to reduce the target speed and trigger traction control; when the motor shaft breaks or the transmission chain breaks, the safety stop procedure is immediately triggered because the power transmission link has been disconnected and the vehicle cannot be driven normally; when the brakes fail, emergency braking (such as activating electromagnetic braking or parking brake) is triggered and the remote monitoring center is notified; when there is an unknown fault, a safety stop can be performed and all sensor data can be recorded for offline diagnostic analysis.

[0131] The following practical application case illustrates the overall technical solution: During operation, the motor shaft of an autonomous vehicle suddenly breaks. The control command speed is 2.0 m / s, the motor's idle linear speed is 2.0 m / s, but the wheel rotation speed is 0, and the odometer speed is 0. Between 0.1 and 0.6 seconds, the cumulative difference between the main stall integrator (odometer-command speed integrator) and the actual stall speed reaches 0.5 meters, exceeding the 0.4-meter threshold and triggering detection. Simultaneously, the cumulative difference between the wheel-motor speed integrator reaches 1.0 meter and triggers, while the odometer-wheel speed integrator does not trigger (both are 0). The decision tree determines the fault as a motor shaft breakage, outputs the fault type, sends an event notification, and the vehicle safely stops. This method has been deployed and run on actual vehicles for over 10,000 kilometers and has detected multiple real-world faults without any missed detections or false alarms, further validating the effectiveness of the solution.

[0132] Furthermore, the detection results (including fault mode, integral value, odometer validity flag, instantaneous protection status flag, etc.) can be written into a thread-safe state container, and an event notification can be sent if a fault is detected.

[0133] The complete status message can also be published to a message topic in the Cyber ​​RT (CyberReal-Time, Vehicle-Road Cooperative Real-Time System) communication framework at a frequency of 10Hz via the status publisher. Cyber ​​RT is a real-time communication middleware framework used in autonomous driving systems, employing a publish-subscribe model for inter-module communication. A message topic is a named communication channel within this framework. The status publisher sends messages to a designated topic, and other modules that have subscribed to that topic (such as the planning and decision-making module, remote monitoring module, and logging module) can receive stall detection results in real time, thereby achieving decoupled communication and collaborative response between the various modules of the system.

[0134] In this embodiment, atomic operations (i.e., non-interruptible memory read / write instructions provided by the CPU, such as compare-and-swap) can also be used to achieve thread-safe state updates, ensuring data consistency when concurrently accessing shared state data between the data acquisition thread (chassis data callback, control instruction callback, and odometer callback run in their respective callback threads) and the state publication thread.

[0135] The steps described above in this embodiment can be implemented using a modular design system. This system mainly includes seven core components: a data acquisition module, a sliding window integrator module, an odometer validity detection module, a stall detection module, a fault mode recognition module, a transient event protection module, and a status release module. This system features low single-frame processing latency, low memory footprint, supports 100Hz high-frequency data processing, and also exhibits low fault detection latency, meeting the real-time requirements of autonomous driving. The modular design facilitates integration into existing autonomous driving systems. Furthermore, as mentioned earlier, all key parameters can be flexibly adjusted through configuration files, supporting various vehicle dynamics parameter configurations, further enhancing system adaptability.

[0136] As can be seen from the above technical solutions, the present invention can collect multi-channel sensor data in real time and confirm whether the stall fault detection conditions are met based on the multi-channel sensor data, avoiding the problem of false alarms caused by single sensor data. The judgment based on the stall fault detection conditions also effectively improves reliability. Based on the odometer-command speed integrator, odometer-wheel speed integrator, wheel-motor speed integrator and wheel slippage detection integrator constructed by using a dual-end queue, it can effectively prevent false judgments. It can detect whether the target autonomous vehicle is in a transient protection state and can effectively distinguish between speed changes caused by normal operation and real hardware faults. Based on the odometer-wheel speed integrator, wheel-motor speed integrator and wheel slippage detection integrator, fault mode recognition can be performed to accurately locate the fault after the vehicle stall is detected.

[0137] like Figure 2 The diagram shown is a functional block diagram of a preferred embodiment of the stall fault detection device for autonomous vehicles according to the present invention. The stall fault detection device 11 for autonomous vehicles includes a data acquisition unit 110, a confirmation unit 111, an acquisition unit 112, a detection unit 113, and an identification unit 114. The module / unit referred to in this invention is a series of computer program segments that can be executed by a processor and perform a fixed function, and which are stored in memory. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0138] The acquisition unit 110 is used to collect chassis data, control command data and odometer data in real time as multi-channel sensor data in response to the stall fault detection command of the target autonomous vehicle.

[0139] The confirmation unit 111 is used to confirm whether the stall fault detection conditions are met based on the multi-channel sensor data.

[0140] The acquisition unit 112 is used to acquire, when it is confirmed that the stall fault detection conditions are met, an odometer-command speed integrator, an odometer-wheel speed integrator, a wheel-motor speed integrator and a wheel slip detection integrator constructed based on the multi-channel sensor data using a double-ended queue.

[0141] The detection unit 113 is used to detect in real time whether the odometer-command speed integrator is triggered, and when the odometer-command speed integrator is detected to be triggered, confirm that the target autonomous vehicle is in a main stall state.

[0142] The detection unit 113 is also used to detect whether the target autonomous vehicle is in a transient protection state;

[0143] The identification unit 114 is used to identify the target fault mode of the target autonomous vehicle based on the odometer-wheel speed integrator, the wheel-motor speed integrator and the wheel slippage detection integrator when the target autonomous vehicle is not in the transient protection state.

[0144] As can be seen from the above technical solutions, the present invention can collect multi-channel sensor data in real time and confirm whether the stall fault detection conditions are met based on the multi-channel sensor data, avoiding the problem of false alarms caused by single sensor data. The judgment based on the stall fault detection conditions also effectively improves reliability. Based on the odometer-command speed integrator, odometer-wheel speed integrator, wheel-motor speed integrator and wheel slippage detection integrator constructed by using a dual-end queue, it can effectively prevent false judgments. It can detect whether the target autonomous vehicle is in a transient protection state and can effectively distinguish between speed changes caused by normal operation and real hardware faults. Based on the odometer-wheel speed integrator, wheel-motor speed integrator and wheel slippage detection integrator, fault mode recognition can be performed to accurately locate the fault after the vehicle stall is detected.

[0145] like Figure 3 The diagram shown is a schematic representation of the computer device used in a preferred embodiment of the method for detecting stall faults in autonomous vehicles according to the present invention.

[0146] The computer device 1 may include a memory 12, a processor 13, and a bus (the arrow in the figure represents the bus), and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a stall fault detection program for an autonomous vehicle.

[0147] Those skilled in the art will understand that the schematic diagram is merely an example of computer device 1 and does not constitute a limitation on computer device 1. Computer device 1 can be either a bus topology or a star topology. Computer device 1 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, computer device 1 may also include input / output devices, network access devices, etc.

[0148] It should be noted that the computer device 1 described is merely an example. Other existing or future electronic products that are adaptable to this invention should also be included within the scope of protection of this invention and are incorporated herein by reference.

[0149] The memory 12 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the computer device 1, such as a portable hard drive of the computer device 1. In other embodiments, the memory 12 can be an external storage device of the computer device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the computer device 1. Furthermore, the memory 12 can include both internal storage units and external storage devices of the computer device 1. The memory 12 can be used not only to store application software and various types of data installed on the computer device 1, such as the code of a stall fault detection program for an autonomous vehicle, but also to temporarily store data that has been output or will be output.

[0150] In some embodiments, the processor 13 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 13 is the control unit of the computer device 1, connecting various components of the computer device 1 via various interfaces and lines. It executes programs or modules stored in the memory 12 (e.g., executing a stall fault detection program for an autonomous vehicle) and calls data stored in the memory 12 to perform various functions of the computer device 1 and process data.

[0151] The processor 13 executes the operating system of the computer device 1 and various installed applications. The processor 13 executes these applications to implement the steps in the above embodiments of the stall fault detection method for autonomous vehicles, for example... Figure 1 The steps are shown.

[0152] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of performing a specific function, which describe the execution process of the computer program in the computer device 1. For example, the computer program may be divided into a collection unit 110, a confirmation unit 111, an acquisition unit 112, a detection unit 113, and an identification unit 114.

[0153] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute portions of the stall fault detection method for autonomous vehicles described in the various embodiments of the present invention.

[0154] If the modules / units integrated in the computer device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0155] The computer program includes computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, etc.

[0156] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0157] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0158] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, in... Figure 3 The bus is represented by only one straight line, but this does not mean that there is only one bus or one type of bus. The bus is configured to enable communication between the memory 12 and at least one processor 13, etc.

[0159] Although not shown, the computer device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 13 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The computer device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0160] Furthermore, the computer device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the computer device 1 and other computer devices.

[0161] Optionally, the computer device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the computer device 1 and to display a visual user interface.

[0162] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0163] It will be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the computer device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0164] Combination Figure 1 The memory 12 in the computer device 1 stores multiple instructions to implement a stall fault detection method for an autonomous vehicle, and the processor 13 can execute the multiple instructions to achieve the following:

[0165] In response to the stall fault detection command of the target autonomous vehicle, chassis data, control command data and odometer data are collected in real time as multi-sensor data;

[0166] Confirm whether the stall fault detection conditions are met based on the data from the multiple sensors.

[0167] When the stall fault detection conditions are confirmed to be met, an odometer-command speed integrator, an odometer-wheel speed integrator, a wheel-motor speed integrator, and a wheel slippage detection integrator are constructed using a double-ended queue based on the multi-channel sensor data and including timestamp-value pairs.

[0168] Real-time detection of whether the odometer-command speed integrator is triggered, and when the odometer-command speed integrator is detected to be triggered, confirmation that the target autonomous vehicle is in a primary stall state;

[0169] Detect whether the target autonomous vehicle is in a transient protection state;

[0170] When the target autonomous vehicle is not in the transient protection state, the target fault mode of the target autonomous vehicle is obtained by fault mode identification based on the odometer-wheel speed integrator, the wheel-motor speed integrator and the wheel slippage detection integrator.

[0171] Specifically, the processor 13's implementation method for the above instructions can be found in [reference needed]. Figure 1 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0172] It should be noted that all the data involved in this case was legally obtained.

[0173] If any AI models, software tools, or components not belonging to this company appear in the embodiments of this invention, they are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this invention has been obtained by an entity authorized (with the knowledge and consent) or fully authorized by all parties through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.

[0174] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0175] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0176] 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 achieve the purpose of this embodiment according to actual needs.

[0177] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0178] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0179] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0180] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in this invention can also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A stall fault detection method for an autonomous vehicle, the method comprising: The stall fault detection method for the autonomous vehicle includes: In response to the stall fault detection command of the target autonomous vehicle, chassis data, control command data and odometer data are collected in real time as multi-sensor data; Confirm whether the stall fault detection conditions are met based on the data from the multiple sensors. When the stall fault detection conditions are confirmed to be met, an odometer-command speed integrator, an odometer-wheel speed integrator, a wheel-motor speed integrator, and a wheel slippage detection integrator are constructed using a double-ended queue based on the multi-channel sensor data and including timestamp-value pairs. Real-time detection of whether the odometer-command speed integrator is triggered, and when the odometer-command speed integrator is detected to be triggered, confirmation that the target autonomous vehicle is in a primary stall state; Detect whether the target autonomous vehicle is in a transient protection state; When the target autonomous vehicle is not in the transient protection state, the target fault mode of the target autonomous vehicle is obtained by fault mode identification based on the odometer-wheel speed integrator, the wheel-motor speed integrator and the wheel slippage detection integrator.

2. The stall failure detection method of an autonomous vehicle according to claim 1, wherein The step of confirming whether the stall fault detection conditions are met based on the multi-sensor data includes: Calculate the timestamp difference between any consecutive preset frames of data in the multi-channel sensor data; When the timestamp difference is less than the duration threshold, it is confirmed that the multi-channel sensor data has passed the data synchronization verification. Establish a sliding window for gear selection that includes a preset sample size; The preset sample size of odometer speed is obtained from the odometer data based on the gear position determination sliding window; When the odometer speeds of the preset sample size all have the same value, the current gear of the target autonomous vehicle is detected based on the odometer speeds of the preset sample size. When the current gear is a forward gear or a reverse gear, the validity of the odometer of the target autonomous vehicle is detected based on the chassis data and the odometer data; When the odometer is valid, it is confirmed that the stall fault detection conditions are met.

3. The stall fault detection method for autonomous vehicles as described in claim 2, characterized in that, The step of validating the odometer of the target autonomous vehicle based on the chassis data and the odometer data includes: Calculate the virtual speed of each left rear wheel and the virtual speed of each right rear wheel based on the odometer data; The actual speeds of the left and right rear wheels of the target autonomous vehicle are obtained from the chassis data. Calculate the difference between the virtual speed of each left rear wheel and the actual speed of the corresponding left rear wheel to obtain the speed difference of each left rear wheel, and input each speed difference of the left rear wheel into the left rear wheel speed difference integrator in sequence according to the time sequence; Calculate the difference between the virtual speed of each right rear wheel and the actual speed of the corresponding right rear wheel to obtain the speed difference of each right rear wheel, and input each speed difference of the right rear wheel into the right rear wheel speed difference integrator in sequence according to the time order; When the left rear wheel speed difference integrator and the right rear wheel speed difference integrator are triggered simultaneously, the odometer is determined to be invalid; or When the left rear wheel speed difference integrator and the right rear wheel speed difference integrator are not triggered simultaneously, the odometer is determined to be valid. The left rear wheel speed difference integrator and the right rear wheel speed difference integrator adopt the GREATER_THAN greater than mode and have the same time window and threshold.

4. The stall fault detection method for autonomous vehicles as described in claim 3, characterized in that: Each integrator is a parallel sliding window integrator; When new data is input into each integrator, a new timestamp-value pair is constructed using the time when the new data enters each integrator as the timestamp and the new data as the value. Calculate the average of the new data and the previous frame data, and calculate the time interval between the new data and the previous frame data; The product of the mean and the time interval is calculated as the integral increment corresponding to the new data; the integral increment is accumulated based on the previous integral to obtain the integral value corresponding to the new data; Specifically, the odometer-command speed integrator takes as input the absolute speed difference between the odometer speed in the odometer data and the control command speed in the control command data; the odometer-wheel speed integrator takes as input the absolute speed difference between the odometer speed in the odometer data and the wheel linear speed in the chassis data; the wheel-motor speed integrator takes as input the absolute speed difference between the wheel linear speed and the motor linear speed in the chassis data; and the wheel slippage detection integrator takes as input the absolute value of the odometer speed in the odometer data. The odometer-command speed integrator, the odometer-wheel speed integrator, and the wheel-motor speed integrator all use the GREATER_THAN greater than mode, while the wheel slippage detection integrator uses the LESS_THAN less than mode.

5. The stall fault detection method for autonomous vehicles as described in claim 1, characterized in that, The detection of whether the target autonomous vehicle is in a transient protection state includes: Detect whether an emergency stop sign is present in the chassis data; When the emergency stop sign is detected in the chassis data, an emergency stop event is confirmed. Obtain the current frame control command speed and the previous frame control command speed from the control command data, and calculate the absolute difference between the current frame control command speed and the previous frame control command speed; When the absolute difference is greater than the difference threshold and the speed of the current frame control command is less than a preset value, a speed change event is confirmed to have occurred. When the emergency stop event and / or the speed change event are confirmed to occur, the system enters the transient protection state, records the current timestamp, and provides transient protection for the target autonomous vehicle. Specifically, when providing transient protection for the target autonomous vehicle, alarms based on the main stall state are prohibited during the protection period starting from the current timestamp. Specifically, if the transient protection state is confirmed to have been entered again within the minimum protection interval starting from the current timestamp, transient protection for the target autonomous vehicle will be refused.

6. The stall fault detection method for an autonomous vehicle as described in claim 1, characterized in that, The fault mode identification process based on the odometer-wheel speed integrator, the wheel-motor speed integrator, and the wheel slippage detection integrator, to obtain the target fault mode of the target autonomous vehicle, includes: Detect whether the wheel slip detection integrator is triggered, and if the wheel slip detection integrator is detected to be triggered, determine that the target fault mode is wheel slip; or When the wheel slippage detection integrator is not triggered, and the odometer-wheel speed integrator is not triggered but the wheel-motor speed integrator is triggered, the target fault mode is determined to be motor shaft breakage; or When the wheel slippage detection integrator is not triggered, and the odometer-wheel speed integrator is triggered while the wheel-motor speed integrator is not triggered, the target fault mode is determined to be a drivetrain breakage; or When the wheel slip detection integrator, the odometer-wheel speed integrator, and the wheel-motor speed integrator are all detected as not being triggered, the target fault mode is determined to be brake failure.

7. The stall fault detection method for an autonomous vehicle as described in claim 6, characterized in that, After obtaining the target fault mode of the target autonomous vehicle, the method further includes: When the target fault mode is wheel slippage, reduce the target speed of the target autonomous vehicle and trigger traction control; or When the target fault mode is a broken motor shaft or a broken drivetrain, control the target autonomous vehicle to perform a safe stop; or When the target fault mode is brake failure, control the target autonomous vehicle to perform emergency braking and send an alarm notification to the remote monitoring center; When no fault mode is detected, the target autonomous vehicle is controlled to perform a safe stop and all sensor data of the target autonomous vehicle is recorded.

8. A stall fault detection device for an autonomous vehicle, characterized in that, The stall fault detection device for the autonomous vehicle includes: The data acquisition unit is used to respond to the stall fault detection command of the target autonomous vehicle and collect chassis data, control command data and odometer data in real time as multi-sensor data. The confirmation unit is used to confirm whether the stall fault detection conditions are met based on the multi-channel sensor data. The acquisition unit is used to acquire, when it is confirmed that the stall fault detection conditions are met, an odometer-command speed integrator, an odometer-wheel speed integrator, a wheel-motor speed integrator and a wheel slippage detection integrator constructed based on the multi-channel sensor data using a double-ended queue. The detection unit is used to detect in real time whether the odometer-command speed integrator is triggered, and when the odometer-command speed integrator is detected to be triggered, confirm that the target autonomous vehicle is in a main stall state. The detection unit is also used to detect whether the target autonomous vehicle is in a transient protection state; The identification unit is used to identify the target fault mode of the target autonomous vehicle based on the odometer-wheel speed integrator, the wheel-motor speed integrator and the wheel slippage detection integrator when the target autonomous vehicle is not in the transient protection state.

9. A computer device, characterized in that, The computer device includes: A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the stall fault detection method for an autonomous vehicle as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, which is executed by a processor in a computer device to implement the stall fault detection method for an autonomous vehicle as described in any one of claims 1 to 7.

Images