Vehicle posture detection method, device and storage medium

Abstract

The present application relates to the technical field of vehicle control, and relates to a vehicle posture detection method, device and storage medium; wherein the vehicle posture detection method comprises the following steps: monitoring a lock vehicle signal; issuing a security instruction when the lock vehicle signal is monitored; receiving vehicle reference state data and environment data collected by a multi-source sensor of the vehicle; performing reference learning by using the vehicle reference state data and the environment data to obtain reference posture data of the vehicle at a current parking position; continuously collecting real-time posture data of the vehicle, and determining an abnormality recognition result according to a comparison result of the reference posture data and the real-time posture data of the vehicle; and when the vehicle abnormally moves, performing a corresponding vehicle control action according to abnormal type information and a response level; the present application can detect abnormal movement of the vehicle without increasing the hardware deployment cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, and in particular to a vehicle posture detection method, device and storage medium. BACKGROUND

[0002] With the continuous improvement of the intelligent level of vehicles, motorcycles and other means of transportation, the means of theft they face are becoming increasingly professional and concealed. Traditional anti-theft systems, such as electronic anti-theft locks, alarms based on single inclination sensors, etc., have shown obvious shortcomings in dealing with new types of theft methods such as "towing" or "lifting". The existing technology mainly has the following defects:

[0003] Firstly, in the detection link, there are problems of detection lag and high false alarm rate. The traditional inclination sensor has difficulty in making accurate judgments in the early stage of the vehicle being slowly towed or slightly lifted. Its judgment logic is single, and it is easy to trigger the alarm due to the vehicle being parked on uneven road or the surrounding large vehicles passing by; on the contrary, when the theft occurs in a slow and gradual way, such sensors may lag in response because the change does not reach the trigger threshold, missing the best warning and intervention opportunity.

[0004] Secondly, in the response link, the response means is single and the deterrent force is limited. Most of the existing anti-theft solutions are limited to sound and light alarms. This passive response is not deterrent enough in unattended environments, and it cannot make any substantial physical intervention on the ongoing theft (such as the vehicle being towed by a tow truck or lifted by a forklift), resulting in poor anti-theft effect.

[0005] Thirdly, in the system architecture, there is a lack of coordination and information fusion across controllers. Modern vehicles usually have multiple independent controllers deployed inside, such as body control module (BCM), telematics box (TBOX), automatic parking system (APS), etc. However, the existing anti-theft technology has not effectively broken down the information barriers between these controllers, forming "information silos", and cannot comprehensively utilize the multi-sensor data (such as posture, position, image, etc.) from different systems of the vehicle for cross-validation and accurate decision-making.

[0006] In view of the above problems, the existing related technology has made some improvement attempts, but still has significant limitations:

[0007] Firstly, some solutions focus on "parking scene protection", relying on multi-modal large models (such as Transformer architecture, LSTM algorithm) to process multi-element data such as vision and audio. Although this type of solution focuses on general target recognition and behavior prediction, the high requirement of large models for computing resources is not compatible with the low power consumption and real-time operation environment required by vehicle embedded systems, making it difficult to apply.

[0008] Secondly, another scheme is based on "smart tire built-in sensor" (such as tire GPS, strain sensor) to realize vehicle condition monitoring and theft prevention. This technical path needs to additionally install special hardware inside the tire, which is high in cost, and does not involve the linkage intervention of vehicle posture abnormality and power system. SUMMARY

[0009] The present application aims to at least solve the technical problems in the prior art, and provide a vehicle posture detection method, device and storage medium.

[0010] In a first aspect, the present application provides a vehicle posture detection method, which comprises:

[0011] S1, monitoring a lock vehicle signal;

[0012] S2, issuing a security instruction when the lock vehicle signal is monitored;

[0013] S3, receiving vehicle reference state data and environmental data collected by a multi-source sensor of the vehicle in response to the security instruction controlled by a control unit of the vehicle;

[0014] S4, performing reference learning by using the vehicle reference state data and the environmental data to obtain reference posture data of the vehicle at the current parking position;

[0015] S5, collecting real-time posture data of the vehicle at a time period, comparing the reference posture data and the real-time posture data of the vehicle to obtain a comparison result, and determining an abnormality recognition result of the vehicle according to the comparison result:

[0016] If the abnormality recognition result is that the vehicle has no abnormal movement, the real-time posture data of the vehicle is collected at a time period;

[0017] If the abnormality recognition result is that the vehicle has abnormal movement, the comparison result is deeply analyzed to determine abnormal type information and a response level;

[0018] An operation instruction is generated based on the abnormal type information and the response level, and the operation instruction is sent to the control unit of the vehicle to control the control unit of the vehicle to execute a vehicle control action in response to the operation instruction;

[0019] S6, obtaining posture data of the vehicle after the control unit executes the vehicle control action;

[0020] S7, determining whether the abnormality is removed according to the posture data of the vehicle after the vehicle control action is executed by the vehicle, if the abnormality is not removed, continuously reporting the abnormality and upgrading the response until the highest response level is upgraded; if the abnormality is removed, issuing a security instruction, and executing steps S3 to S6.

[0021] By adopting the technical scheme, the control unit of the vehicle controls the vehicle reference state data and the environment data collected by the multi-source sensor of the vehicle when receiving the security instruction, determines the abnormal type information and the response level by comparing the reference attitude data and the real-time attitude data of the vehicle according to the reference attitude data of the vehicle at the current parking position, and executes the corresponding vehicle control action according to the abnormal type information and the response level; the existing multi-source sensor and controller of the vehicle are used to monitor the vehicle, and no additional sensor needs to be installed, thereby saving the hardware cost, reducing the cost, detecting the abnormal movement behavior of the vehicle, and improving the anti-theft effect; the environment data is added during the reference learning, the parking environment is fully considered, the reference attitude data is more accurate, the complex parking environment such as a slope and a pothole can be adapted, the possibility of false positives caused by environmental interference is reduced, and the accuracy of the vehicle anti-theft early warning result is further improved.

[0022] Optionally, the vehicle reference state data includes reference position coordinates of the vehicle when the vehicle is locked, a reference angular velocity, a reference tire pressure of a tire, and a reference distance between a vehicle base and the ground; and the vehicle real-time attitude data includes a horizontal displacement of the vehicle relative to the reference parking position, a real-time angular velocity of the vehicle, a real-time tire pressure of the tire, and a real-time distance between the vehicle base and the ground.

[0023] By adopting the technical scheme, the specific content of the vehicle reference state data and the vehicle real-time attitude data is determined.

[0024] Optionally, if the comparison result is:

[0025] The absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is less than a first preset value;

[0026] The absolute value of the difference between the real-time angular velocity and the reference angular velocity is less than a second preset value;

[0027] The absolute value of the difference between the real-time tire pressure of the tire and the reference tire pressure of the tire is less than a third preset value;

[0028] The absolute value of the difference between the real-time distance between the vehicle base and the ground and the reference distance between the vehicle base and the ground is less than a fourth preset value, and it is determined that the abnormal recognition result is that the vehicle has no abnormal movement.

[0029] If the comparison result is:

[0030] The absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is greater than or equal to the first preset value;

[0031] And / or, the absolute value of the difference between the real-time angular velocity and the reference angular velocity is greater than or equal to the second preset value;

[0032] And / or, the absolute value of the difference between the real-time tire pressure and the reference tire pressure is greater than or equal to a third preset value;

[0033] And / or, the absolute value of the difference between the real-time distance between the vehicle base and the ground and the reference distance between the vehicle base and the ground is greater than or equal to a fourth preset value, then the abnormal identification result is determined to be that the vehicle has abnormal movement.

[0034] By adopting the above technical solution, the determination rule of the abnormal identification result is clear.

[0035] Optionally, the abnormal type includes that the vehicle is lifted and the vehicle is towed,

[0036] When the output abnormal identification result is that the vehicle has abnormal movement, the comparison result is deeply analyzed, and if the comparison result is:

[0037] The absolute value of the difference between the real-time angular velocity and the reference angular velocity is greater than or equal to a second preset value;

[0038] And the absolute value of the difference between the real-time tire pressure and the reference tire pressure is greater than or equal to a third preset value;

[0039] And the absolute value of the difference between the reference distance between the vehicle base and the ground and the reference distance between the vehicle base and the ground is greater than or equal to a fourth preset value, then the abnormal type is determined to be that the vehicle is lifted, and the abnormal type information is obtained;

[0040] If the comparison result is:

[0041] The absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is greater than or equal to a first preset value;

[0042] And the door lock of the vehicle is in a full lock state;

[0043] And the drive motor of the vehicle is in an unstarted state, then the abnormal type is determined to be that the vehicle is towed, and the abnormal type information is obtained.

[0044] By adopting the above technical solution, special judgment logic rules are set for the two core theft scenes of the vehicle being lifted and the vehicle being towed, which can realize effective detection of the vehicle being lifted and the vehicle being towed. The judgment rules of the two core theft scenes of the vehicle being lifted and the vehicle being towed can reduce the false positive rate of the vehicle abnormal situation.

[0045] Optionally, the response level includes a first response, a second response, and a third response;

[0046] When it is detected that the abnormal identification result is that the vehicle has abnormal movement, the abnormal duration is counted;

[0047] If the abnormal duration satisfies If so, the response level is determined to be a Level 1 response;

[0048] If the abnormal duration satisfy , If so, the response level is determined to be a Level II response;

[0049] If the abnormal duration satisfy If the absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is greater than or equal to the fifth preset value, then the response level is determined to be a level three response.

[0050] By adopting the above technical solution, multiple response levels are defined based on the duration of the anomaly and the distance of the abnormal vehicle movement. Different warning / anti-theft actions are executed according to the severity of the vehicle anomaly. This allows users to perceive the anomaly at the first moment and enables the control unit to select the appropriate response method according to different response levels, resulting in better performance.

[0051] Optionally, the step of generating an operation command based on the exception type information and response level, and sending the operation command to the vehicle's control unit to control the vehicle's control unit to respond to the operation command and execute vehicle control actions includes:

[0052] When the response level is Level 1, a first warning message is generated based on the anomaly type information and real-time location coordinates. A first operation command is generated based on the first warning message and sent to the vehicle's control unit to control the control unit to send the first warning message to the client corresponding to the vehicle owner.

[0053] When the response level is Level 2, the abnormality type information and real-time attitude data are uploaded to the cloud platform, a second operation command is generated, and the second operation command is sent to the vehicle's control unit so that the control unit controls the vehicle's audible and visual alarm module to issue an audible and visual alarm.

[0054] When the response level is Level 3, the anomaly type information and real-time attitude data are uploaded to the cloud platform, a third operation command is generated, and the third operation command is sent to the vehicle's control unit to control the vehicle's control unit to set the torque output of the drive motor to limp mode, thereby increasing the vehicle's drag resistance.

[0055] By adopting the above technical solution, the control unit can perform different early warning / anti-theft actions according to different response levels, and select appropriate response methods to warn thieves; when the response level is level three, the theft can be directly stopped through active intervention, thereby improving the anti-theft effect.

[0056] Optionally, the vehicle's control unit enters the armed state upon receiving an armed command, and after entering the armed state, the vehicle... (The sentence is incomplete and ends abruptly.) Vehicle baseline status data and environmental data are periodically re-collected;

[0057] The reference attitude data of the vehicle is updated by using the newly acquired vehicle baseline state data and environmental data for baseline learning.

[0058] By adopting the above technical solution, the reference attitude data can be dynamically updated, which can reduce the impact of the environment on the parking environment and improve the accuracy of the reference attitude data.

[0059] Optionally, the vehicle's horizontal displacement is obtained by analyzing and processing the vehicle's three-axis acceleration collected by the inertial measurement unit; the real-time angular velocity is obtained by the vehicle's inertial measurement unit; the real-time tire pressure is obtained by the vehicle's tire pressure monitoring system; and the real-time distance between the vehicle's base and the ground is obtained by the radar sensor of the automatic parking system.

[0060] By adopting the above technical solution, the specific method for collecting real-time vehicle attitude data has been clarified.

[0061] In a second aspect, the present invention provides an electronic device, the electronic device comprising:

[0062] At least one processor; and,

[0063] A memory communicatively connected to the at least one processor; wherein,

[0064] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the vehicle attitude detection method described above.

[0065] Thirdly, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the vehicle attitude detection method described above.

[0066] In summary, this application includes the following beneficial technical effects:

[0067] When the vehicle's control unit receives an arming command, it controls the vehicle's built-in multi-source sensors to collect vehicle baseline state data and environmental data. Based on the vehicle's reference attitude data at its current parking position, the reference attitude data and real-time vehicle attitude data are compared to determine the anomaly type and response level. Corresponding vehicle control actions are then executed based on the anomaly type and response level. The vehicle's existing multi-source sensors and controllers are used for anti-theft monitoring, eliminating the need for additional sensors and saving hardware costs. This reduces costs while simultaneously monitoring abnormal vehicle movement, improving anti-theft effectiveness. Incorporating environmental data during baseline learning fully considers the parking environment, making the reference attitude data more accurate and adaptable to complex parking environments such as slopes and potholes. This reduces the possibility of false alarms due to environmental interference, further improving the accuracy of vehicle anti-theft warning results. Attached Figure Description

[0068] Figure 1 This is a flowchart illustrating a vehicle attitude detection method according to an embodiment of the present invention.

[0069] Figure 2 This is a system architecture diagram of the anti-theft system used to implement the vehicle attitude detection method of this application;

[0070] Figure 3 This is a flowchart illustrating an anomaly type determination and graded response control method provided in an embodiment of the present invention.

[0071] Figure 4 This is a schematic diagram of the structure of an electronic device for implementing the vehicle attitude detection method according to an embodiment of the present invention.

[0072] Reference numerals: 10, processor; 11, memory; 12, communication bus; 13, communication interface.

[0073] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0074] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0075] In the description of this invention, it should be understood that the terms "longitudinal", "lateral", "up", "down", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0076] In the description of this invention, unless otherwise specified and limited, it should be noted that the terms "installation", "connection" and "linking" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal connections between two components. They can be direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0077] Reference Figure 1 The diagram shown is a flowchart illustrating a vehicle attitude detection method according to an embodiment of the present invention. The vehicle can be a motorcycle, a gasoline-powered vehicle, an electric vehicle (EV), a hybrid electric vehicle, a plug-in hybrid electric vehicle (HEV), a range-extended electric vehicle (EV), a hybrid electric vehicle (HEV), a natural gas vehicle, a methanol vehicle, a solar-powered vehicle, or other new energy vehicles, etc. This application does not impose specific limitations on this.

[0078] In this embodiment, a vehicle attitude detection method includes:

[0079] S1. Monitor the vehicle locking signal.

[0080] S2. When a vehicle locking signal is detected, an arming command is issued.

[0081] After detecting that the vehicle is legally locked, an arming command is issued; when the body control module confirms that the door lock is closed and the power control module confirms that the high voltage of the drive motor used to drive the vehicle is de-energized, the conditions for legally locking the vehicle are determined to be met.

[0082] S3. Receive vehicle baseline status data and environmental data collected by the vehicle's control unit in response to the arming command.

[0083] Vehicle baseline state data includes the vehicle's reference angular velocity when locked, reference tire pressure, and reference distance between the vehicle's base and the ground.

[0084] Reference Figure 2In this embodiment, three types of sensors built into the vehicle body are used to obtain the vehicle's baseline state data. The vehicle attitude detection method of this application is applicable to vehicles equipped with anti-theft systems. The anti-theft system used to implement the vehicle attitude detection method of this application includes an information acquisition layer, a central processing layer, and an execution response layer. The information acquisition layer includes an Inertial Measurement Unit (IMU), a Tire Pressure Monitoring System (TPMS), and an Automated Parking System (APS). The central processing layer is referred to as the vehicle's control unit. The execution response layer includes a Telematics Box (TBOX), a Body Control Module (BCM), and a Vehicle Control Unit (VCU). The Telematics Box is used to realize information interaction between the vehicle and the cloud platform and the user software program (the client program corresponding to the vehicle owner). The cloud platform is used to receive real-time vehicle attitude data uploaded by the Telematics Box and push warning information to the user. The Body Control Module is used to control the headlights, horn, and other audio-visual equipment, as well as accessories such as doors, windows, and locks. The Vehicle Control Module is used to control the torque of the drive motor and the brake-by-wire system to control the start and stop of the vehicle.

[0085] The inertial measurement unit can collect the vehicle's three-axis angular velocity (unit: ° / s) and three-axis acceleration (unit: m / s²), thereby enabling the detection of the vehicle's attitude angles (pitch angle, roll angle) static offset and horizontal displacement;

[0086] The tire pressure monitoring system can obtain the real-time tire pressure (unit: bar) and temperature (unit: °C) of each tire of the vehicle. Based on the real-time tire pressure and temperature of each tire, it can determine whether the wheel has lost pressure after leaving the ground.

[0087] The automatic parking system includes radar sensors, which can collect the vertical distance (in cm) between the vehicle chassis and the ground and the radar detection angle (in meters). The vertical distance between the vehicle chassis and the ground, and the radar detection angle collected by the radar sensors, can be used to determine whether the vehicle has been lifted.

[0088] When the vehicle's control unit receives the arming command, it collects the vehicle's baseline status data and environmental data.

[0089] S4. Use vehicle baseline state data and environmental data to perform baseline learning to obtain reference attitude data of the vehicle at the current parking position;

[0090] The vehicle's acceleration, angular velocity, tire pressure, and distance between the vehicle's base and the ground are collected at the current parking position. Based on the above baseline state data of the vehicle, baseline learning is performed, and an initial baseline attitude model for the parking position is constructed.

[0091] Environmental data refers to data used to represent the parking environment of a vehicle. In this embodiment, three-dimensional point cloud data of the ground near the current parking position of the vehicle can be collected by LiDAR, or images of the ground near the current parking position of the vehicle can be collected by image acquisition equipment to obtain environmental data.

[0092] S4. Use vehicle baseline state data and environmental data to perform baseline learning to obtain reference attitude data of the vehicle at the current parking position.

[0093] Based on the vehicle's baseline state data, baseline learning is performed to construct an initial baseline attitude model for the parking position. This initial baseline attitude model is then optimized using environmental data to reduce the impact of environmental disturbances such as uneven ground and slope on the vehicle's attitude, resulting in the final baseline attitude model. This baseline attitude model is not a traditional 3D model, but rather a set of data representing the vehicle's attitude at the current parking position (including pitch angle, roll angle, real-time tire pressure of each tire, and the distance between the vehicle's base and the ground).

[0094] The vehicle reference state data is determined based on the vehicle's baseline attitude model. The vehicle reference state data includes the vehicle's reference angular velocity when the vehicle is locked, the tire reference tire pressure, and the reference distance between the vehicle base and the ground.

[0095] In a preferred embodiment of this example, the vehicle attitude detection method further includes: the vehicle's control unit enters a armed state upon receiving an armed command; after entering the armed state, the vehicle... (The sentence is incomplete and ends abruptly). Vehicle baseline status data and environmental data are periodically re-collected;

[0096] The reference attitude data of the vehicle is updated by using the newly acquired vehicle baseline state data and environmental data for baseline learning.

[0097] The vehicle baseline state data is time-series data. To facilitate understanding by those skilled in the art, the baseline learning execution steps are described below with specific examples:

[0098] 1) After the vehicle is legally locked, the body control module sends an "arming command" to the central processing module, triggering baseline learning;

[0099] 2) The data input layer synchronously controls the radar sensors of the inertial measurement unit, tire pressure monitoring system, and automatic parking system to collect real-time vehicle attitude data for 120 seconds to ensure that the collected vehicle attitude data covers the static stable state, thus obtaining time-stamped vehicle reference state data.

[0100] 3) The preprocessing layer performs noise reduction and calibration processing (such as IMU filtering and APS coordinate unification) on the real-time vehicle attitude data collected by various sensors to obtain preprocessed real-time vehicle attitude data; in low-computing-power in-vehicle environments (original vehicle Android infotainment system, computing power... Under these conditions, high-frequency interference (such as vibrations from passing vehicles and transient noise from minor ground bumps) in the IMU-acquired data is filtered out, and smooth three-axis angular velocity / acceleration data is output. This provides a stable input for subsequent calculations of pitch and roll angles, ultimately ensuring the accuracy of the "reference attitude model" and avoiding misjudgments of abnormal movements caused by environmental interference.

[0101] 4) Extract features from environmental data to identify the parking environment (e.g., if a pitch angle θ0 = 3° is detected, it is determined to be a ramp environment and marked as an interference parameter).

[0102] 5) The baseline generation layer calculates the average of the vehicle's real-time attitude data and physical quantities over 120 seconds to generate the final baseline attitude model (e.g., pitch angle). roll angle Tire reference tire pressure Reference distance between the vehicle base and the ground );

[0103] 6) The storage update layer compares the baseline model with the current GPS coordinates (e.g., latitude and north). East longitude Bind storage and start adaptive verification every 30 minutes.

[0104] The baseline learning model in this application supports dynamic updates. Environmental data is incorporated during baseline learning, enabling the generated baseline learning model to adapt to complex parking environments such as ramps and potholes, thereby reducing the possibility of false alarms caused by environmental interference.

[0105] S5, by time To periodically and continuously collect real-time vehicle attitude data, compare the reference attitude data with the real-time vehicle attitude data to obtain comparison results, and determine the anomaly identification results of the vehicle based on the comparison results:

[0106] If the anomaly detection result indicates that the vehicle did not move abnormally, then time will be used as the time factor. The vehicle's real-time attitude data is collected periodically.

[0107] If the anomaly identification result indicates that the vehicle is moving abnormally, the deep analysis comparison result will determine the anomaly type information and response level. The anomaly types include vehicle being lifted and vehicle being towed, and the response levels include Level 1 response, Level 2 response and Level 3 response.

[0108] Vehicle being lifted refers to a theft scenario where thieves use professional or simple lifting equipment (such as jacks, hydraulic jacks, small cranes, etc.) to lift the vehicle and then damage or manipulate it from underneath. Vehicle being dragged refers to a theft scenario where thieves use tools such as trailers, ropes, and chains to directly apply external force to the vehicle and move it from one place to another.

[0109] Reference Figure 3 Based on the anomaly type information and response level, an operation command is generated and sent to the vehicle's control unit to control the vehicle's control unit to respond to the operation command and execute vehicle control actions.

[0110] Specifically, the central processing module continuously receives real-time vehicle attitude data collected by multiple sensors at a frequency of 10Hz, and performs anomaly detection based on "rule-based logic and benchmark comparison":

[0111] Real-time vehicle attitude data includes the vehicle's horizontal displacement relative to the reference parking position, the vehicle's real-time angular velocity, real-time tire pressure, and the real-time distance between the vehicle's base and the ground. The horizontal displacement relative to the reference parking position is obtained by analyzing and processing the vehicle's three-axis acceleration collected by the inertial measurement unit; the real-time angular velocity is obtained by the vehicle's inertial measurement unit; the real-time tire pressure is obtained by the vehicle's tire pressure monitoring system; and the real-time distance between the vehicle's base and the ground is obtained by the radar sensors of the automatic parking system.

[0112] The steps for determining the anomaly identification result of the vehicle based on the comparison results are as follows:

[0113] If the comparison result is: the absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is less than the first preset value;

[0114] Furthermore, the absolute value of the difference between the real-time angular velocity and the reference angular velocity is less than the second preset value;

[0115] Furthermore, the absolute value of the difference between the real-time tire pressure and the reference tire pressure is less than the third preset value;

[0116] Furthermore, if the absolute value of the difference between the real-time distance between the vehicle base and the ground and the reference distance between the vehicle base and the ground is less than the fourth preset value, then the abnormal identification result is determined to be that the vehicle has no abnormal movement.

[0117] If the comparison result is: the absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is greater than or equal to the first preset value;

[0118] And / or, the absolute value of the difference between the real-time angular velocity and the reference angular velocity is greater than or equal to the second preset value;

[0119] And / or, the absolute value of the difference between the real-time tire pressure and the tire reference tire pressure is greater than or equal to a third preset value;

[0120] And / or, if the absolute value of the difference between the real-time distance between the vehicle base and the ground and the reference distance between the vehicle base and the ground is greater than or equal to the fourth preset value, the abnormal identification result is determined to be that the vehicle is moving abnormally.

[0121] When the output anomaly identification result indicates that the vehicle is moving abnormally, the result is first analyzed and compared to determine the anomaly type information. The anomaly types include the vehicle being lifted and the vehicle being towed.

[0122] When a vehicle is lifted by a jack / trailer, the anomaly type is considered to be "vehicle lifted"; if the comparison results simultaneously meet the following three conditions, and the duration is... (Excluding momentary interference), the determination is "the vehicle was lifted":

[0123] The absolute value of the difference between the real-time angular velocity and the reference angular velocity is greater than or equal to the second preset value;

[0124] Furthermore, the absolute value of the difference between the real-time tire pressure and the tire reference tire pressure is greater than or equal to the third preset value;

[0125] Furthermore, if the absolute value of the difference between the reference distance between the vehicle base and the ground and the reference distance between the vehicle base and the ground is greater than or equal to the fourth preset value, then the abnormal type is determined to be that the vehicle is being lifted.

[0126] For example, in one example of this embodiment, the TPMS detects that the pressure of one or more vehicle tires is within a range of 10 consecutive seconds, compared to a tire reference pressure. Decline And the absolute value of the tire pressure after the drop (Passenger vehicle standard; commercial vehicles may be configured as) Meanwhile, the interfering scenario of "slow tire pressure leakage" (a decrease of ≤5% within 1 minute) was excluded;

[0127] APS condition: The APS radar detects the ground distance of at least two diagonal radars ( Compared to the baseline distance ( The distance increases by ≥8cm, and the rate of change of distance is ≥2cm / s (excluding slow bumps);

[0128] IMU condition: The IMU detects a pitch angle ( ) or roll angle ( Compared to the reference angle ( The static offset of ) is ≥ Furthermore, there is no horizontal acceleration (excluding normal vehicle movement).

[0129] When a vehicle is towed, the anomaly type is considered to be vehicle being lifted; if the comparison results simultaneously meet the following three conditions, and the duration is... (Excluding momentary interference), the determination is "the vehicle was towed":

[0130] The absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is greater than or equal to the first preset value;

[0131] Furthermore, the vehicle's doors are fully locked;

[0132] Furthermore, if the vehicle's drive motor is not running, the abnormality type is determined to be that the vehicle is being towed.

[0133] For example, in one example of this embodiment, the IMU condition is: the IMU detects horizontal (X / Y axis) acceleration. And accompanied by continuous horizontal displacement (displacement calculated by integration) );

[0134] BCM condition: The BCM has not received a valid unlock signal (such as passive keyless entry), and the door lock is in the closed state;

[0135] VCU conditions: The VCU confirms that the vehicle's high-voltage system is not powered on (the motor is not started) and there is no valid start command (such as key turning or one-button start signal).

[0136] This application focuses on the core theft scenario of "trailer / lifting", with more accurate judgment logic, which can reduce the false alarm rate of anti-theft alarms.

[0137] The response level is confirmed as follows:

[0138] When the anomaly identification result is determined to be abnormal vehicle movement, the duration of the anomaly is recorded.

[0139] If the abnormal duration satisfy If so, the response level is determined to be a Level 1 response;

[0140] If the abnormal duration satisfy , If so, the response level is determined to be a Level II response;

[0141] If the abnormal duration satisfy If the absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is greater than or equal to the fifth preset value, then the response level is determined to be a level three response.

[0142] In this embodiment, an operation command is generated based on the anomaly type information and response level, and the operation command is sent to the vehicle's control unit to control the vehicle's control unit to respond to the operation command and execute vehicle control actions, including:

[0143] When the response level is Level 1, a first warning message is generated based on the anomaly type information and real-time location coordinates. A first operation command is generated based on the first warning message and sent to the vehicle's control unit to control the control unit to send the first warning message to the client corresponding to the vehicle owner. When the response level is Level 1, the warning / anti-theft action is to push a warning notification to the user's mobile APP (including the vehicle's GPS location and anomaly type: "suspected lifting / towing"), and at the same time display real-time tire pressure and IMU attitude data on the APP. This achieves "early warning" so that the user can perceive the anomaly as soon as possible.

[0144] When the response level is Level 2, the anomaly type information and real-time attitude data are uploaded to the cloud platform, a second operation command is generated, and the second operation command is sent to the vehicle's control unit, causing the control unit to control the vehicle's audible and visual alarm module to issue an audible and visual alarm; when the response level is Level 2, the warning / anti-theft action is to control the BCM to sound the horn (1.5kHz frequency). (Interval), hazard lights flashing (1Hz frequency); TBOX uploads vehicle GPS location, IMU real-time attitude, and TPMS tire pressure data to the cloud platform every 2 seconds; the purpose is to deter theft through "audio-visual deterrence" while retaining abnormal data.

[0145] When the response level is Level 3, the anomaly type information and real-time attitude data are uploaded to the cloud platform, generating a third operation command. This command is then sent to the vehicle's control unit (VCU) to control the VCU to switch the drive motor's torque output to limp mode, increasing the vehicle's drag resistance. When the response level is Level 3, the warning / anti-theft action is to send a command to the VCU to limit the drive motor's torque output to "limp mode" (torque). 20% of the rated torque; for gasoline vehicles, the engine speed is limited. If the vehicle is equipped with a brake-by-wire system, it can generate periodic braking force (500N, 2s interval) to increase drag resistance and noise; TBOX sends an "emergency help" signal to the cloud platform, which then pushes information about nearby security personnel; and "active intervention" can directly prevent theft (such as when the vehicle cannot move normally while being towed), achieving a better anti-theft effect.

[0146] S6. Acquire the vehicle's attitude data after the control unit executes the vehicle control action;

[0147] S7. Determine whether the anomaly has been cleared based on the vehicle's attitude data after the vehicle performs the vehicle control action. If the anomaly has not been cleared, continue to report the anomaly and escalate the response until it reaches the highest response level. If the anomaly has been cleared, issue an arming command and execute steps S3 to S6.

[0148] This application uses existing onboard sensors and controllers (IMU, TPMS, APS, BCM / VCU / TBOX) to acquire and process vehicle baseline state data and real-time vehicle attitude data, eliminating the need for additional tire-embedded GPS devices or high-performance computing chips, thus saving hardware costs.

[0149] This application also discloses an electronic device, such as Figure 4 The diagram shown is a schematic representation of an electronic device for a vehicle attitude detection method according to an embodiment of the present invention. The electronic device may include at least one processor 10, a memory 11 communicatively connected to the at least one processor, a communication bus 12, and a communication interface 13. It may also include a computer program, such as a vehicle attitude detection method program, stored in the memory 11 and executable on the processor 10.

[0150] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits 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 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., methods for vehicle attitude detection) and calls data stored in the memory 11 to perform various functions and process data within the electronic device.

[0151] The memory 11 includes at least one type of readable storage medium, including 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 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of a vehicle attitude detection method program, but also to temporarily store data that has been output or will be output.

[0152] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0153] Communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or optionally, a standard wired or 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 electronic device and to display a visual user interface.

[0154] Figure 4 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 4The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0155] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to at least one processor 10 via 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 electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0156] It should be understood that the embodiments are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0157] Furthermore, if the modules / units integrated into the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile.

[0158] This application provides a computer-readable storage medium, including, for example, any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM). The computer-readable storage medium stores a computer program that can be loaded by a processor and execute the vehicle attitude detection method of the above embodiments.

[0159] In the description of this specification, the references to terms such as "an embodiment," "some embodiments," "example," "specific example," "a implementation," "a preferred implementation," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0160] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A vehicle attitude detection method, characterized in that, The method includes: S1. Monitor vehicle locking signals; S2. When a vehicle locking signal is detected, an arming command is issued; S3. The vehicle's control unit receives the arming command and controls the vehicle's built-in multi-source sensors to collect vehicle reference state data and environmental data. The vehicle reference state data includes the vehicle's reference angular velocity when the vehicle is locked, the tire reference tire pressure, and the reference distance between the vehicle base and the ground. The environmental data is data used to represent the vehicle's parking environment. The environmental data is obtained by collecting three-dimensional point cloud data of the ground near the vehicle's current parking position using LiDAR, or by collecting images of the ground near the vehicle's current parking position using image acquisition equipment. S4. Perform baseline learning using vehicle baseline state data and environmental data to obtain reference attitude data of the vehicle at the current parking position; perform baseline learning based on vehicle baseline state data and construct an initial baseline attitude model for the parking position; optimize the initial baseline attitude model based on environmental data to obtain the final baseline attitude model, which is a set of data that can represent the attitude of the vehicle at the current parking position. The reference attitude data is determined based on the vehicle's baseline attitude model. The reference attitude data includes the vehicle's reference angular velocity when the vehicle is locked, the tire reference tire pressure, and the reference distance between the vehicle's base and the ground. S5, by time To periodically and continuously collect real-time vehicle attitude data, compare the reference attitude data with the real-time vehicle attitude data to obtain comparison results, and determine the anomaly identification results of the vehicle based on the comparison results: If the anomaly detection result indicates that the vehicle did not move abnormally, then time will be used as the time factor. The vehicle's real-time attitude data is collected periodically. If the anomaly identification result indicates that the vehicle is moving abnormally, the deep analysis comparison result will be used to determine the anomaly type information and response level. An operation command is generated based on the anomaly type information and response level, and the operation command is sent to the vehicle's control unit to control the vehicle's control unit to respond to the operation command and execute vehicle control actions. S6. Acquire the vehicle's attitude data after the control unit executes the vehicle control action; S7. Determine whether the anomaly has been cleared based on the vehicle's attitude data after the vehicle performs the vehicle control action. If the anomaly has not been cleared, continue to report the anomaly and escalate the response until it reaches the highest response level. If the anomaly has been cleared, issue an arming command and execute steps S3 to S6.

2. The vehicle attitude detection method as described in claim 1, characterized in that, Vehicle baseline state data includes the vehicle's reference angular velocity when locked, reference tire pressure, and reference distance between the vehicle's base and the ground. Real-time vehicle attitude data includes the vehicle's horizontal displacement relative to the reference parking position, the vehicle's real-time angular velocity, the tire pressure, and the vehicle's base distance from the ground.

3. The vehicle attitude detection method as described in claim 2, characterized in that, If the comparison result is: The absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is less than the first preset value; Furthermore, the absolute value of the difference between the real-time angular velocity and the reference angular velocity is less than the second preset value; Furthermore, the absolute value of the difference between the real-time tire pressure and the reference tire pressure is less than the third preset value; Furthermore, if the absolute value of the difference between the real-time distance between the vehicle base and the ground and the reference distance between the vehicle base and the ground is less than the fourth preset value, then the abnormal identification result is determined to be that the vehicle has no abnormal movement. If the comparison result is: The absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is greater than or equal to the first preset value; And / or, the absolute value of the difference between the real-time angular velocity and the reference angular velocity is greater than or equal to the second preset value; And / or, the absolute value of the difference between the real-time tire pressure and the tire reference tire pressure is greater than or equal to a third preset value; And / or, if the absolute value of the difference between the real-time distance between the vehicle base and the ground and the reference distance between the vehicle base and the ground is greater than or equal to the fourth preset value, the abnormal identification result is determined to be that the vehicle is moving abnormally.

4. The vehicle attitude detection method as described in claim 3, characterized in that, Abnormal types include vehicles being lifted and vehicles being towed. When the output anomaly identification result indicates that the vehicle is moving abnormally, the deep analysis comparison result is as follows: The absolute value of the difference between the real-time angular velocity and the reference angular velocity is greater than or equal to the second preset value; Furthermore, the absolute value of the difference between the real-time tire pressure and the tire reference tire pressure is greater than or equal to the third preset value; Furthermore, if the absolute value of the difference between the reference distance between the vehicle base and the ground and the reference distance between the vehicle base and the ground is greater than or equal to the fourth preset value, then the abnormality type is determined to be that the vehicle is being lifted, and abnormality type information is obtained. If the comparison result is: The absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is greater than or equal to the first preset value; Furthermore, the vehicle's doors are fully locked; Furthermore, if the vehicle's drive motor is not running, the anomaly type is determined to be that the vehicle is being towed, and anomaly type information is obtained.

5. The vehicle attitude detection method according to any one of claims 2 to 4, characterized in that, The response levels include Level 1, Level 2, and Level 3. When an anomaly is detected and the vehicle is found to be moving abnormally, the duration of the anomaly is recorded. If the abnormal duration satisfy If so, the response level is determined to be a Level 1 response; If the abnormal duration satisfy , If so, the response level is determined to be a Level II response; If the abnormal duration satisfy If the absolute value of the difference between the real-time position coordinates and the reference position coordinates in the horizontal direction is greater than or equal to the fifth preset value, then the response level is determined to be a level three response.

6. The vehicle attitude detection method as described in claim 5, characterized in that, The process of generating operation instructions based on anomaly type information and response level, and sending the operation instructions to the vehicle's control unit to control the vehicle's control unit to respond to the operation instructions and execute vehicle control actions includes: When the response level is Level 1, a first warning message is generated based on the anomaly type information and real-time location coordinates. A first operation command is generated based on the first warning message and sent to the vehicle's control unit to control the control unit to send the first warning message to the client corresponding to the vehicle owner. When the response level is Level 2, the abnormality type information and real-time attitude data are uploaded to the cloud platform, a second operation command is generated, and the second operation command is sent to the vehicle's control unit so that the control unit controls the vehicle's audible and visual alarm module to issue an audible and visual alarm. When the response level is Level 3, the anomaly type information and real-time attitude data are uploaded to the cloud platform, a third operation command is generated, and the third operation command is sent to the vehicle's control unit to control the vehicle's control unit to set the torque output of the drive motor to limp mode, thereby increasing the vehicle's drag resistance.

7. The vehicle attitude detection method as described in claim 6, characterized in that, The vehicle's control unit enters armed state upon receiving an arming command. After entering armed state, the vehicle... (The sentence is incomplete and ends abruptly.) Vehicle baseline status data and environmental data are periodically re-collected; The reference attitude data of the vehicle is updated by using the newly acquired vehicle baseline state data and environmental data for baseline learning.

8. The vehicle attitude detection method as described in claim 6, characterized in that, The vehicle's horizontal displacement is obtained by analyzing and processing the vehicle's three-axis acceleration collected by the inertial measurement unit; the real-time angular velocity is obtained by the vehicle's inertial measurement unit; the real-time tire pressure is obtained by the vehicle's tire pressure monitoring system; and the real-time distance between the vehicle's base and the ground is obtained by the radar sensor of the automatic parking system.

9. An electronic device, characterized in that, The electronic device includes: At least one processor (10); and, A memory (11) communicatively connected to the at least one processor (10); The memory (11) stores a computer program that can be executed by the at least one processor (10) to enable the at least one processor (10) to perform the vehicle attitude detection method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program; when the computer program is executed by a processor, it implements the vehicle attitude detection method as described in any one of claims 1 to 8.

Images