Methods, apparatuses, devices, and media for controlling a vehicle

Abstract

The present disclosure relates to a method, apparatus, device and medium for controlling a vehicle. The method comprises determining a first offset of at least one sensor in the vehicle based on first perception data of the vehicle in response to detecting a tire blowout of the vehicle. The method further comprises adjusting a vehicle suspension according to the first offset. The method further comprises controlling the vehicle based on the adjustment of the vehicle suspension. Through the method of the embodiments of the present disclosure, the vehicle suspension can be adjusted according to the offset of the sensor after the tire blowout of the vehicle, so that the perception accuracy of the sensor after the tire blowout of the vehicle can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicles, and more specifically, to methods, apparatus, devices and media for controlling vehicles. Background Technology

[0002] During vehicle operation, especially at high speeds, while cornering, changing lanes, or under conditions of asymmetrical road surface adhesion, a tire blowout causes abrupt changes in parameters such as longitudinal force, lateral force, and effective rolling radius. This significantly impacts the vehicle's dynamic characteristics, potentially leading to issues like vehicle swerving, yaw instability, abnormal vehicle posture, and deviation from the driving trajectory. Therefore, timely and effective control of the vehicle after a blowout is detected can improve driving stability and safety. Summary of the Invention

[0003] Embodiments of this disclosure provide a method, apparatus, device, and medium for controlling a vehicle.

[0004] In a first aspect of this disclosure, a method for controlling a vehicle is provided. The method includes determining a first offset of at least one sensor in the vehicle based on the first perception data of the vehicle in response to detecting a tire blowout. The method further includes adjusting the vehicle suspension according to the first offset. The method also includes controlling the vehicle based on the adjustment of the vehicle suspension.

[0005] In a second aspect of this disclosure, an apparatus for controlling a vehicle is provided. The apparatus includes an offset determination module configured to determine a first offset of at least one sensor in the vehicle based on the first perception data of the vehicle in response to detecting a tire blowout. The apparatus also includes an adjustment module configured to adjust the vehicle suspension based on the first offset. The apparatus further includes a control module configured to control the vehicle based on the adjustment of the vehicle suspension.

[0006] In a third aspect of this disclosure, a controller is provided. The controller includes one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the method provided according to a first aspect of this disclosure.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions, which are executed by a processor to implement the method provided according to a first aspect of this disclosure.

[0008] It should be understood that the description in the Summary of the Invention section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram of an example environment in which several embodiments of the present disclosure may be implemented is shown;

[0011] Figure 2 A flowchart of a method for controlling a vehicle according to some embodiments of the present disclosure is shown;

[0012] Figure 3 An example diagram of the architecture of a system for controlling a vehicle according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A flowchart is shown, illustrating a method for vehicle stability control after a tire blowout according to some embodiments of the present disclosure;

[0014] Figure 5 A flowchart of a method for suspension closed-loop extrinsic parameter recovery based on some embodiments of the present disclosure is shown;

[0015] Figure 6 A flowchart of a method for safe trajectory planning according to some embodiments of the present disclosure is shown;

[0016] Figure 7 A flowchart is shown illustrating a method for driver intent parsing and adaptive weight fusion according to some embodiments of the present disclosure;

[0017] Figure 8 A flowchart of a method for optimal multi-objective allocation according to some embodiments of the present disclosure is shown;

[0018] Figure 9 Block diagrams of apparatus for controlling a vehicle according to some embodiments of the present disclosure are shown; and

[0019] Figure 10 A schematic block diagram of a controller according to some embodiments of the present disclosure is shown. Detailed Implementation

[0020] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0021] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0022] As mentioned above, timely and effective control of the vehicle after a tire blowout is detected can improve vehicle stability and reduce safety risks. Some existing solutions use control actuators such as the steering and braking systems to counteract the huge disturbance torque and stop the vehicle safely. However, these solutions do not consider the adjustment of the suspension system after a tire blowout. In fact, after a tire blowout, the support capacity of the blown tire decreases, and the vehicle's attitude will change significantly, such as tilting towards the blowout side, changing the pitch attitude, or turning the vehicle. This may cause the attitude of the vehicle's cameras, lidar, and other sensors relative to the vehicle or the ground to deviate, which will further lead to the distortion of the sensor's perception results, such as lane line recognition deviation, obstacle position estimation error, and inaccurate road boundary judgment, thereby reducing the accuracy and reliability of vehicle control.

[0023] Therefore, embodiments of this disclosure propose a scheme for controlling a vehicle. In embodiments of this disclosure, the method includes, in response to detecting a tire blowout, determining a first offset of at least one sensor in the vehicle based on the first perception data of the vehicle. The method further includes adjusting the vehicle suspension according to the first offset. The method also includes controlling the vehicle based on the adjustment of the vehicle suspension.

[0024] In this way, after a tire blowout is detected, not only can the vehicle's stability be controlled, but the sensor offset caused by the blowout can also be determined by combining the vehicle's perception data. Based on the determined sensor offset, the vehicle's suspension can be adjusted to reduce the impact of sensor offset on perception accuracy, thereby improving the stability of vehicle control after a tire blowout.

[0025] Figure 1 A schematic diagram of an example environment 100 in which various embodiments of this disclosure may be implemented is shown. For example... Figure 1 As shown, environment 100 includes vehicle 102, which refers to any type of motorized or non-motorized vehicle capable of carrying people and / or goods and being mobile. Figure 1 As shown, vehicle 102 is illustrated as a car. It should be understood that although vehicle 102 is... Figure 1 The vehicle 102 is illustrated as a car, but this is merely exemplary and far from limited to this; examples may also include buses, trucks, motorcycles, and electric vehicles. In some embodiments of this disclosure, vehicle 102 may include a controller, which may be an Electronic Control Unit (ECU), a domain controller, a central controller, or a control system consisting of multiple control units.

[0026] like Figure 1 As shown, vehicle 102 may include at least one sensor 104-1, 104-2, ..., and 104-N. Sensors 104-1, 104-2, ..., and 104-N can be distributed at different locations on vehicle 102 to collect perception data related to the road environment and vehicle motion state. For example, the sensors may include at least one of the following: a camera, a lidar, a millimeter-wave radar, an inertial measurement unit (IMU), an ultrasonic sensor, a speed sensor, or any other sensor capable of acquiring vehicle perception data. Different types of sensors can collect different types of perception data; for example, a camera can collect image data, a lidar can collect point cloud data, and an inertial measurement unit can collect vehicle attitude data.

[0027] like Figure 1 As shown, the controller of vehicle 102 can determine offsets 106-1, 106-2, ..., and 106-N (also referred to as first offsets) based on the sensing data (also referred to as first sensing data) from sensors 104-1, 104-2, ..., and 104-N. These offsets characterize the degree of sensor offset relative to a preset reference attitude and are related to the sensor's extrinsic parameter error. For example, the offset may include at least one of pitch angle offset, roll angle offset, or yaw angle offset, and may also include a vector composed of pitch angle offset, roll angle offset, and yaw angle offset. It should be understood that... Figure 1 The offsets 106-1, 106-2, ..., 106-N shown can represent the offsets corresponding to sensors 104-1, 104-2, ..., and 104-N respectively, or they can represent the offsets determined after fusing the sensing data from multiple sensors.

[0028] In some embodiments of this disclosure, under normal vehicle conditions, the vanishing point of the lane lines in the image is located in a fixed area of ​​the image. After a tire blowout, the vehicle body tilts, causing the vanishing point to shift. Therefore, the controller can determine the change in the vanishing point position of the lane lines in the image based on the image data collected by the camera, and then, based on this change in position, determine at least one of the pitch angle offset or roll angle offset corresponding to the camera based on the camera projection model, and use at least one of the pitch angle offset or roll angle offset as the camera offset.

[0029] In some embodiments of this disclosure, under normal vehicle conditions, the ground normal vector determined based on the ground point cloud is approximately [0, 0, 1]. After a tire blowout, the normal vector deflects, and the yaw angle equals the error of the pitch or roll angle of the lidar. Therefore, the controller can determine the ground normal vector based on the point cloud data collected by the lidar, and then determine the corresponding yaw angle offset of the lidar based on the ground normal vector, using the yaw angle offset as the offset of the lidar.

[0030] like Figure 1 As shown, the environment 100 also includes a vehicle suspension 108, which can be used to support the vehicle body, buffer road impacts, and adjust vehicle attitude. In some embodiments of this disclosure, the vehicle suspension 108 can be an active suspension, a semi-active suspension, or a suspension system with adjustable damping, adjustable stiffness, and / or adjustable vehicle height. The controller can adjust the vehicle suspension 108 according to 106-1, 106-2, ..., 106-N to compensate for changes in vehicle attitude caused by a tire blowout, thereby reducing sensor offset and improving the accuracy of sensor perception data. Then, the controller can control the vehicle 102 based on the adjustment of the vehicle suspension 108. For example, the controller can re-perform environmental perception, trajectory planning, and vehicle stability control based on the perception data acquired after suspension adjustment.

[0031] In this way, after a tire blowout, the offset of the sensor can be determined based on the sensor's perception data, and the vehicle suspension can be adjusted based on the offset, thereby improving the stability and safety of vehicle control after a tire blowout.

[0032] The following will combine Figures 2 to 10 Detailed description of exemplary embodiments according to this disclosure. For ease of understanding, the specific data mentioned in the following description are exemplary and not intended to limit the scope of this disclosure. It is understood that the embodiments described below may also include additional actions not shown and / or actions shown may be omitted, and the scope of this disclosure is not limited in this respect.

[0033] Figure 2A flowchart of a method 200 for controlling a vehicle according to some embodiments of the present disclosure is shown. Method 200 can be performed by a device for controlling the vehicle, which may be, for example, a standalone device or system. This device can be implemented in software and / or hardware. The method 200 will now be illustrated schematically using a device for controlling the vehicle as an example. Method 200 includes blocks 202, 204, and 206.

[0034] like Figure 2 As shown, in block 202, method 200 is capable of determining a first offset of at least one sensor in the vehicle based on first perception data of the vehicle in response to detecting a tire blowout. For example, in... Figure 1 In the environment 100 shown, one or more sensors 104-1, 104-2, ..., 104-N of the vehicle 102 can collect perception data related to the vehicle's state and the surrounding environment. The controller can determine the offset of at least one sensor 106-1, 106-2, ..., 106-N based on the perception data. Sensors can include at least one of the following: cameras, lidar, millimeter-wave radar, IMU, ultrasonic sensors, speed sensors, or any other sensors capable of acquiring vehicle perception data. Different types of sensors can collect different types of perception data; for example, cameras can collect image data, lidar can collect point cloud data, and inertial measurement units can collect vehicle attitude data. The offset can be used to characterize the degree of displacement of the sensor relative to a preset reference attitude and is related to the sensor's extrinsic parameter error. For example, the offset can include at least one of pitch offset, roll offset, or yaw offset, and the offset can also include a vector composed of pitch offset, roll offset, and yaw offset.

[0035] In box 204, method 200 can adjust the vehicle suspension based on a first offset. For example, in... Figure 1 In the environment 100 shown, the controller can adjust the vehicle suspension 108 according to the offsets 106-1, 106-2, ..., and 106-N. The vehicle suspension 108 can be used to support the vehicle body, buffer road impacts, and adjust the vehicle attitude.

[0036] In box 206, method 200 can control the vehicle based on adjustments to the vehicle suspension. For example, in... Figure 1In the environment 100 shown, the controller can control the vehicle 102 based on the adjustment of the vehicle suspension 108. For example, the controller can re-perform environmental perception, trajectory planning, and vehicle stability control based on the perception data acquired after suspension adjustment. In some embodiments of this disclosure, the controller can determine a first adjustment amount of the vehicle suspension based on a first offset, and then adjust the vehicle suspension based on the first adjustment amount. In some embodiments of this disclosure, the controller can inversely solve for the required vertical displacement of each wheel based on the sensor offset and the vehicle suspension mounting geometry. For example, it can determine the position parameters of multiple wheels of the vehicle based on the vehicle's center of gravity, then determine the vertical displacement of each wheel based on the position parameters of the multiple wheels, and then determine the first adjustment amount of the vehicle suspension based on the vertical displacement.

[0037] In this way, method 200 can determine the sensor offset based on sensor perception data after a tire blowout, and then adjust the vehicle suspension based on the offset, thereby improving the stability and safety of vehicle control after a tire blowout.

[0038] Figure 3 An example diagram of the architecture of a system 300 for controlling a vehicle according to some embodiments of the present disclosure is shown. Figure 3 As shown, in system 300, system 300 may include a perception input layer 302, a cockpit domain controller 304, a left domain controller 306, and an execution layer 308. The perception input layer 302 can be used to acquire perception data of a tire blowout. The cockpit domain controller 304 can be used to acquire driver input information and perform human-machine interaction. The left domain controller 306 can be used for vehicle control decisions and send control commands to the execution layer 308. The execution layer 308 can be used to execute the control commands sent by the left domain controller 306.

[0039] like Figure 3 As shown, the perception input layer 302 may include a sensor 310 and a controller 320. The sensor 310 may include at least one of a camera 314, a millimeter-wave radar 316, and a lidar 318. The camera 314 can be used to acquire image data of the surrounding environment, the millimeter-wave radar 316 can be used to acquire distance information, relative speed information, and orientation information of targets around the vehicle, and the lidar 318 can be used to acquire point cloud data of the environment around the vehicle. The controller 320 can communicate with the sensor 310, receive the perception data acquired by the sensor 310, preprocess the perception data, and then send the preprocessed perception data to the left domain controller 306.

[0040] like Figure 3As shown, the cockpit domain controller 304 may include a human-machine interface module 322, a strobe light 324, and a communication module 326. The human-machine interface module 322 can be used to interact with the driver. The strobe light 324 can be used to provide light cues; for example, the strobe light 324 can send a warning signal to the outside of the vehicle after a tire blowout to remind surrounding road users to take evasive action. The communication module 326 can be used for the driver to interact with the outside world via voice.

[0041] like Figure 3 As shown, the left domain controller 306 may include a suspension closed-loop compensation and recovery module 328, a conservative tire constraint module 330, a driver intent fusion module 332, and a multi-objective optimal allocation module 334. The suspension closed-loop compensation and recovery module 328 can be used to determine the offset of at least one sensor based on perception data, and adjust the vehicle suspension according to the determined offset. In some embodiments of this disclosure, the suspension closed-loop compensation and recovery module 328 can determine the adjustment amount of the vehicle suspension based on the determined sensor offset, and then adjust the vehicle suspension based on the adjustment amount.

[0042] In some embodiments of this disclosure, the suspension closed-loop compensation and recovery module 328 can further determine the sensor offset (also called the second offset) based on new sensing data (also called the second sensing data) after adjusting the vehicle suspension once. If the second offset does not meet a preset condition and the vehicle meets a first condition, the adjustment amount of the vehicle suspension (also called the second adjustment amount) is determined based on the re-determined offset. The preset condition may be that the second offset is not less than a preset threshold, and the first condition may be that the number of suspension recovery cycles is less than a preset value. Then, the suspension is adjusted again based on the second adjustment amount. If the second offset meets the preset condition, the planned trajectory of the vehicle can be determined based on the vehicle's second sensing data. If the second offset does not meet the preset condition and the vehicle does not meet the first condition, the vehicle can be controlled by a preset control strategy. The preset control strategy may be reducing the desired vehicle speed, increasing the safety distance margin, or prohibiting lane changes. In this way, closed-loop compensation and recovery of sensor extrinsic parameters can be achieved.

[0043] In some embodiments of this disclosure, the conservative tire constraint module 330 can be used to limit the available force on the blown tire after a tire blowout. The conservative tire constraint module 330 can configure the model so that the blown tire provides no control force or only limited control force, and generate constraint conditions adapted to the state of the blown tire. In this way, Model Prediction Control (MPC) can be prevented from treating the blown tire as a normal tire after a blowout, thereby improving the safety and reliability of vehicle control.

[0044] In some embodiments of this disclosure, the driver intent fusion module 332 can be used to acquire driver operation data and fuse the driver's intent with the control of the autonomous driving system. The driver's operation data may include steering torque, steering angular velocity, brake pedal change rate, accelerator pedal input, and other information characterizing the driver's operating state. The driver intent fusion module 332 can determine the driver's state based on this operation data; for example, it can determine whether the driver is in a panic state (also known as a target state) or a calm state. In some embodiments of this disclosure, the driver intent fusion module 332 can determine the fusion weight between a first weight corresponding to the driver's input and a second weight corresponding to the autonomous driving control based on the driver's state. For example, when the driver is in a panic state, the driver intent fusion module 332 can reduce the first weight of the driver's input and increase the second weight of the autonomous driving control, making the first weight less than the second weight, thereby reducing the adverse effects of unreasonable human operation on vehicle stability control after a tire blowout. In some embodiments of this disclosure, a driver may be determined to be in a state of panic if at least one of the following conditions is met: the number of times the steering torque crosses zero within a preset time window exceeds a first threshold, the steering angular velocity exceeds a second threshold, the brake pedal change rate exceeds a third threshold, or the driver's input direction is in continuous conflict with the safe direction.

[0045] like Figure 3 As shown, the multi-objective optimal allocation module 334 can generate vehicle control quantities based on the output results of the suspension closed-loop compensation and recovery module 328, the conservative tire constraint module 330, and the driver intention fusion module 332. In some embodiments of this disclosure, the multi-objective optimal allocation module 334 can determine at least one of the vehicle's yaw moment, longitudinal force, vertical force, or steering amount based on the vehicle attitude information after suspension compensation, the tire constraint conditions corresponding to the blown tire, and the driver intention fusion results, and allocate these control quantities to the various execution components in the execution layer 308.

[0046] like Figure 3As shown, the execution layer 308 may include a fully active suspension 336, a steering system 338, a drive system 340, and a braking system 342. The fully active suspension 336 can adjust the suspension actuators corresponding to each wheel to compensate for changes in vehicle posture after a tire blowout and restore the sensing accuracy of the sensors. The steering system 338 can adjust the vehicle's steering angle to counteract yaw disturbances caused by a tire blowout. The drive system 340 can adjust the vehicle's drive torque output, for example, by reducing drive torque or coordinating the drive forces of the left and right wheels to help the vehicle maintain stability. The braking system 342 can apply corresponding braking forces to each wheel and decelerate the vehicle until it comes to a safe stop when necessary. In some embodiments of this disclosure, after the execution layer 308 performs corresponding control, the vehicle's dynamic response changes. This vehicle dynamic response can be sent to the left domain controller 306 and the sensing input layer 302, thereby enabling continuous closed-loop adjustment of the vehicle's posture, sensor offset, and vehicle motion state after a tire blowout.

[0047] In this way, the system 300 can compensate for the changes in vehicle posture caused by the tire blowout through the fully active suspension 336 after the tire blowout, so as to reduce or eliminate the impact of sensor posture offset on perception accuracy. In addition, the left domain controller 306 can perform trajectory planning and control decisions for the vehicle based on the posture-compensated perception data, thereby improving the stability of vehicle control after the tire blowout.

[0048] Figure 4 A flowchart of a method 400 for vehicle stability control after a tire blowout, according to some embodiments of the present disclosure, is shown. Figure 4 As shown in block 402, method 400 can receive a tire blowout detection signal input, which can be output by a sensor in the vehicle and can be used to indicate that a tire blowout has occurred or that there is a risk of a tire blowout.

[0049] In box 404, the central domain controller can control the execution of at least one of the following: human machine interface (HMI) alarm, hazard light activation, and emergency call, to alert the driver and surrounding road users that the vehicle is in an abnormal state and to initiate rescue or emergency contact if necessary.

[0050] In box 406, method 400 can perform suspension closed-loop extrinsic parameter recovery. For example, the vehicle can estimate the extrinsic parameter offset of at least one sensor based on the perception data after a tire blowout, determine the adjustment amount of the vehicle suspension based on the extrinsic parameter offset, and then adjust the suspension based on the adjustment amount to recover the perception deviation of the sensor caused by attitude changes such as body roll, pitch, and yaw. The extrinsic parameter offset may include at least one of the pitch angle offset, roll angle offset, and yaw angle offset corresponding to the sensor. For ease of description, the following will combine... Figure 5 Describe, Figure 5 A flowchart of a method 500 based on suspension closed-loop extrinsic parameter recovery according to some embodiments of the present disclosure is shown.

[0051] like Figure 5 As shown in block 502, method 500 can estimate the extrinsic parameter offset online. In some embodiments of this disclosure, method 500 can estimate the extrinsic parameter offset of the sensor online based on the sensor's sensing data. The extrinsic parameter offset may include at least one of pitch angle offset, roll angle offset, and yaw angle offset. The extrinsic parameter offset may also include a vector composed of pitch angle offset, roll angle offset, and yaw angle offset. For example, the vector may be represented as... For example, in some embodiments, the vanishing point position offset of the lane line in the image is determined based on the image captured by the camera, and the pitch angle offset and / or roll angle offset of the camera is determined based on the position offset. In other embodiments, the ground normal vector is determined based on the point cloud data captured by the lidar, and the yaw angle offset, pitch angle offset or roll angle offset of the lidar is determined based on the ground normal vector.

[0052] In block 504, method 500 can perform inverse kinematics of the suspension pose. For example, after obtaining the extrinsic parameter offset, method 500 can determine the suspension adjustment amount used to recover the sensor attitude based on the extrinsic parameter offset. In some embodiments of this disclosure, method 500 can determine the position parameters of multiple wheels of the vehicle based on the vehicle's center of gravity, then determine the vertical displacement amount corresponding to each of the multiple wheels based on the position parameters of the multiple wheels, and then determine the adjustment amount of the vehicle suspension based on the vertical displacement amount of the multiple wheels, wherein the vertical displacement amount corresponding to each of the multiple wheels can be expressed as... , Where Δroll and Δpitch are in radians, approximated by a small angle sin(θ)≈θ. xi is the longitudinal coordinate of wheel i (positive in front of the center of mass), and yi is the lateral coordinate of wheel i. To eliminate this vertical displacement, each suspension needs to be adjusted in the opposite direction: The vertical displacement adjustment of the four wheels can be expressed in matrix form: The 4×2 matrix M represents fixed parameters for the vehicle model. After offline calibration, these parameters are stored in the left domain controller. The left domain controller will... The commands are sent to the fully active suspension controller via the Controller Area Network (CAN) bus, and then converted into specific actuator stroke commands based on the lever ratio ri of each suspension and the actuator characteristics.

[0053] In some embodiments of this disclosure, the left domain controller acts as the upper-level domain controller, outputting only the vertical displacement required by each wheel. It does not focus on the lever ratio of the underlying actuators. The fully active suspension controller receives... Then, based on the ri (actuator travel / wheel vertical travel, offline calibration) of each suspension, automatically calculate the actuator displacement Δhi = / ri. This method decouples the pose inverse algorithm of the left domain controller from the specific suspension hardware, allowing adaptation to different vehicle models by simply updating the ri parameter in the fully active suspension controller. The suspension needs to be kept within its usable travel range. If the calculated value for a particular wheel... If the suspension exceeds the available range (corresponding to full extension or full retraction), the entire suspension will be scaled proportionally. It is marked as "partially recovered", and the accuracy threshold is relaxed accordingly in subsequent closed-loop verification.

[0054] In box 506, method 500 can perform fully active suspension execution. For example, the left domain controller can send a four-wheel target height command to the fully active suspension controller. The fully active suspension controller can actively apply a vertical force on the blown tire side through hydraulic or electromagnetic actuators to adjust the vehicle body attitude in the horizontal direction. The suspension on the non-blown tire side can adjust in coordination to share the load.

[0055] In box 408, method 500 can determine whether the extrinsic parameter offset is less than a preset threshold. If the result is "yes," it means that after suspension adjustment, the sensor extrinsic parameter offset has recovered to an acceptable range, and the vehicle sensors can continue to provide perception input for subsequent control with high confidence. Then, box 410 is executed for model predictive control safety trajectory planning. If the result is "no," box 412 is executed to determine whether the number of iterations is not less than a preset number. The preset number can be a threshold used to limit the maximum number of attempts to recover the suspension closed-loop extrinsic parameters. If the result is "no," meaning the current number of iterations has not reached the preset number, method 500 can return to box 502 to re-execute online estimation of extrinsic parameter offset, suspension pose inverse kinematics, and fully active suspension execution to further reduce the extrinsic parameter offset. If the result is "yes," meaning that after the preset number of closed-loop adjustments, the extrinsic parameter offset has still not decreased below the preset threshold, then box 414 is executed to mark the perception degradation state and switch to a conservative control strategy.

[0056] Continue back Figure 4 In box 408, method 400 can determine whether the extrinsic parameter offset is less than a preset threshold. If the extrinsic parameter offset is less than the preset threshold, then execute box 410; if the extrinsic parameter offset is not less than the preset threshold, then execute box 412. In box 410, method 400 can generate a safe trajectory plan based on model predictive control. For ease of description, the following will combine... Figure 6 Describe, Figure 6A flowchart of a method 600 for safe trajectory planning according to some embodiments of the present disclosure is shown.

[0057] like Figure 6 As shown in block 602, method 600 can perform rolling time-domain optimized trajectory planning based on conservative tire force constraints, environmental constraints, and safety distances. For example, an Advanced Driver Assistance System (ADAS) controller can perform rolling time-domain optimized trajectory planning based on the following inputs: a LiDAR point cloud or camera image after extrinsic parameter recovery correction; a vehicle model using conservative tire force constraints and normal tire models for the other three normal tires; environmental constraints such as lane boundaries, shoulder positions, and adjacent vehicle positions; dynamic constraints consisting of a conservative tire force ellipse (i.e., the blown tire ellipse degenerates into a unidirectional line segment along the longitudinal direction) and actuator physical limits; optimization objectives including a smooth transition of lateral displacement to the emergency lane, a decrease in longitudinal velocity according to a safety curve, and convergence of yaw rate to zero; and a preset control period. In block 604, method 600 can output a desired trajectory including a lateral displacement sequence, a longitudinal velocity sequence, and a heading angle sequence.

[0058] In box 412, method 400 can determine whether the number of iterations is less than a preset number. The preset number can be a threshold set to limit the maximum number of adjustments for suspension extrinsic parameter recovery. The preset number can be 3, 5, or other calibrable numbers. When the determination result is "yes," it means that the maximum number of iterations has not been reached, and method 400 can return to box 406 to continue executing the next round of suspension closed-loop extrinsic parameter recovery to further reduce the extrinsic parameter offset. When the determination result is "no," it means that the extrinsic parameter offset has not been recovered to the preset range after the preset number of iterations, and then box 414 is executed. In box 414, method 400 can mark the perception degradation state and switch to a conservative control strategy. The conservative control strategy can include reducing the desired vehicle speed, increasing the safety distance margin, and prohibiting lane changes, etc.

[0059] In box 416, method 400 can analyze the driver's intent. For ease of description, it will be combined with the following. Figure 7 Describe, Figure 7 A flowchart of a method 700 for safe trajectory planning according to some embodiments of the present disclosure is shown.

[0060] like Figure 7 As shown in block 702, method 700 can acquire steering torque and pedal signals. In some embodiments of this disclosure, method 700 can also acquire steering angular velocity and brake pedal rate of change.

[0061] In box 704, method 700 can determine whether there is high-frequency oscillation in the steering torque or whether the pedal rate is abnormal. For example, the steering torque crosses zero too many times within a preset time window, the steering torque change frequency is higher than a preset frequency threshold, or the steering angular velocity exceeds a preset threshold. The brake pedal change rate or accelerator pedal change rate exceeds the corresponding threshold, or there are conflicting changes between braking and acceleration inputs that do not conform to normal driving logic.

[0062] If the judgment result is "No", then execute box 706. In box 706, method 700 can parse the driver's intention into the desired torque, and then execute box 418. In box 418, method 700 performs multi-objective optimal allocation. If the judgment result is "Yes", then execute box 708. In box 708, method 700 can reduce the first weight corresponding to the driver's input and increase the second weight of the system's automatic control.

[0063] Continue back Figure 4 In box 418, method 400 can perform multi-objective optimal allocation. For example, method 400 can comprehensively allocate vehicle control objectives based on the planned trajectory and adaptive weights determined based on the driver's state. For ease of description, the following will combine... Figure 8 Describe, Figure 8 A flowchart of a method 800 for safe trajectory planning according to some embodiments of the present disclosure is shown.

[0064] like Figure 8 As shown, in block 802, method 800 can perform constrained multi-objective optimization based on yaw tracking, minimum tire load, minimum impact, and driver soft constraints. In block 804, method 800 can distribute actuator commands among the braking system, steering system, drive system, and fully active suspension. In some embodiments of this disclosure, method 800 can determine vehicle control quantities based on a planned trajectory, which may include at least one of yaw moment, longitudinal force, and vertical force, and then generate control commands for the braking system, steering system, drive system, and active suspension system respectively based on the vehicle control quantities.

[0065] Continue back Figure 4In box 420, method 400 can perform actuator closed-loop response. For example, the central domain controller or chassis domain controller can issue control commands to multiple actuators based on the multi-objective optimal allocation result to achieve vehicle stability control. In box 422, method 400 can control the braking system to output four-wheel differential braking force. In box 424, method 400 can control the steering system to output active steering angle or steering assist compensation. In box 426, method 400 can control the fully active suspension system to adjust suspension stiffness, damping, or height. In box 428, method 400 can control the drive system to set the drive torque to zero.

[0066] In box 430, the vehicle generates a dynamic response under the combined action of the braking system, steering system, fully active suspension system, and drive system. In box 432, method 400 can determine whether the vehicle has reached a safe stopping state. A safe stopping state can indicate that the vehicle has decelerated to below a preset safe speed or has come to a complete stop and is within a target parking area, emergency lane, shoulder, or other safe area. If the determination result is "no," return to box 406 and continue to execute the suspension closed-loop extrinsic parameter recovery. If the determination result is "yes," execute box 434. In box 434, method 400 can terminate control and bring the vehicle to a safe stop.

[0067] In this way, Method 400 can actively adjust the vehicle's attitude through a fully active suspension system and perform closed-loop recovery of sensor extrinsic parameter offsets, thereby improving the accuracy of perception data after a tire blowout. In addition, through model-predicted trajectory planning, driver intent analysis, and multi-actuator multi-objective collaborative control, it can improve the stability and safety of vehicle control after a tire blowout.

[0068] Figure 9 A block diagram of a device 900 for controlling a vehicle according to some embodiments of the present disclosure is shown. Figure 9 As shown, the device 900 includes an offset determination module 902, configured to determine a first offset of at least one sensor in the vehicle based on first perception data of the vehicle in response to detecting a tire blowout. The device 900 also includes an adjustment module 904, configured to adjust the vehicle suspension based on the first offset. The device 900 further includes a control module 906, configured to control the vehicle based on the adjustment of the vehicle suspension.

[0069] In some embodiments, the adjustment module 904 includes an adjustment amount determination module configured to determine a first adjustment amount of the vehicle suspension based on a first offset. The adjustment module 904 also includes an adjustment amount usage module configured to adjust the vehicle suspension based on the first adjustment amount.

[0070] In some embodiments, the device 900 further includes a second offset determination module configured to determine a second offset of at least one sensor in the vehicle based on second sensing data of the vehicle after adjusting the vehicle suspension based on a first adjustment amount. The device 900 also includes a second adjustment amount determination module configured to determine a second adjustment amount of the vehicle suspension based on the second offset amount in response to a second offset amount not meeting a preset condition and the vehicle meeting a first condition. The device 900 further includes a second adjustment amount usage module configured to readjust the vehicle suspension based on the second adjustment amount.

[0071] In some embodiments, the first offset includes at least one of pitch angle offset, roll angle offset, or yaw angle offset.

[0072] In some embodiments, the offset determination module 902 includes a displacement offset determination module, configured to determine the position offset of the vanishing point of the lane line in the image based on the image captured by the camera. The offset determination module 902 also includes a displacement offset usage module, configured to use at least one of the pitch angle offset or roll angle offset corresponding to the camera determined based on the position offset as the first offset.

[0073] In some embodiments, the offset determination module 902 further includes a ground normal vector determination module, configured to determine the ground normal vector based on the point cloud data acquired by the vehicle's lidar. The offset determination module 902 also includes a ground normal vector usage module, configured to use the yaw angle offset corresponding to the lidar determined based on the ground normal vector as the first offset.

[0074] In some embodiments, the adjustment amount determination module includes a position parameter determination module configured to determine position parameters of a plurality of wheels of the vehicle based on the vehicle's center of gravity. The adjustment amount determination module also includes a vertical displacement determination module configured to determine vertical displacements corresponding to each of the plurality of wheels based on the position parameters of the plurality of wheels. The adjustment amount determination module further includes a vertical displacement usage module configured to determine a first adjustment amount of the vehicle suspension based on the vertical displacements.

[0075] In some embodiments, the device 900 further includes a trajectory planning module configured to determine the planned trajectory of the vehicle based on the vehicle's second perception data in response to a second offset satisfying a preset condition.

[0076] In some embodiments, the device 900 further includes a preset control strategy usage module, configured to control the vehicle through a preset control strategy in response to a second offset not meeting a preset condition and the vehicle not meeting a first condition.

[0077] In some embodiments, the trajectory planning module includes a model usage module configured to determine the planned trajectory based on the model and second sensing data, wherein the model is configured to provide no control force in the event of a tire blowout.

[0078] In some embodiments, the control module 906 includes a vehicle control quantity determination module configured to determine vehicle control quantities based on a planned trajectory. The vehicle control quantities include at least one of yaw moment, longitudinal force, and vertical force. The control module 906 also includes a vehicle control quantity usage module configured to generate control commands for the braking system, steering system, drive system, and active suspension system, respectively, based on the vehicle control quantities.

[0079] In some embodiments, the device 900 further includes a driver state determination module configured to determine the driver's state based on driver operation data, including at least one of steering torque, steering angular velocity, brake pedal rate of change, and accelerator pedal input. The device 900 also includes a fusion weight determination module configured to determine a fusion weight of a first weight and a second weight in response to the driver being in a target state, the first weight being associated with driver input and the second weight being associated with autonomous driving control, the first weight being less than the second weight. The device 900 also includes a fusion weight usage module configured to control the vehicle based on the fusion weight.

[0080] In some embodiments, the driver state determination module includes a target state determination module, configured to determine that the driver is in a target state in response to at least one of the following: the number of times the steering torque crosses zero within a preset time window exceeds a first threshold, the steering angular velocity exceeds a second threshold, the brake pedal change rate exceeds a third threshold, or the driver's input direction continuously conflicts with the safe direction.

[0081] It is understood that by utilizing the device 900 of this disclosure, at least one of the many advantages achievable by the methods or processes described above can be realized. For example, the device 900 can actively adjust the vehicle's attitude through a fully active suspension system and perform closed-loop recovery of sensor extrinsic parameter offsets, thereby improving the accuracy of perception data after a tire blowout. Furthermore, the device 900 can enhance the stability and safety of vehicle control after a tire blowout through model prediction trajectory planning, driver intent analysis, and multi-actuator multi-objective cooperative control.

[0082] Figure 10 A block diagram of a controller 1000 that can implement various embodiments of the present disclosure is shown. (See reference...) Figure 10As shown, the controller 1000 includes a processor 1001, which can perform various appropriate actions and processes based on computer program instructions loaded into random access memory (RAM) 1003 according to computer program instructions stored in read-only memory (ROM) 1002. The RAM 1003 may also store various programs and data required for the operation of the controller 1000. The processor 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0083] Processor 1001 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 1001 performs the various methods and processes described above, such as method 200. For example, in some embodiments, method 200 may be implemented as a computer software program tangibly contained in a machine-readable medium. In some embodiments, part or all of the computer program may be loaded and / or mounted to controller 1000 via ROM 1002. When the computer program is loaded into RAM 1003 and executed by processor 1001, one or more steps of method 200 described above may be performed. Alternatively, in other embodiments, processor 1001 may be configured to perform method 200 by any other suitable means (e.g., by means of firmware).

[0084] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload programmable logic devices (CPLDs), and so on.

[0085] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0086] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. Furthermore, although operations are depicted in a specific order, this should be understood as requiring that such operations be performed in the specific order shown or in sequential order, or requiring that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented individually or in any suitable sub-combination in multiple implementations.

[0087] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for controlling a vehicle, comprising: In response to detecting a tire blowout in a vehicle, a first offset of at least one sensor in the vehicle is determined based on first perception data of the vehicle. Adjust the vehicle suspension based on the first offset; as well as The vehicle is controlled based on the adjustment of the vehicle suspension.

2. The method according to claim 1, wherein adjusting the vehicle suspension based on the first offset comprises: The first adjustment amount of the vehicle suspension is determined based on the first offset; as well as The vehicle suspension is adjusted based on the first adjustment amount.

3. The method according to claim 2, further comprising: After adjusting the vehicle suspension based on the first adjustment amount, a second offset of at least one sensor in the vehicle is determined based on the second perception data of the vehicle; In response to the second offset not meeting the preset condition and the vehicle meeting the first condition, a second adjustment amount of the vehicle suspension is determined based on the second offset; as well as The vehicle suspension is adjusted again based on the second adjustment amount.

4. The method according to claim 1, wherein the first offset includes at least one of pitch angle offset, roll angle offset, or yaw angle offset.

5. The method according to claim 4, wherein determining the first offset of at least one sensor in the vehicle based on the first perception data of the vehicle comprises: The position offset of the vanishing point of the lane line in the image is determined based on the image captured by the camera. The first offset is determined by taking at least one of the pitch angle offset or tilt angle offset of the camera based on the position offset.

6. The method of claim 4, wherein determining a first offset of at least one sensor in the vehicle based on first perception data of the vehicle comprises: The ground normal vector is determined based on the point cloud data collected by the vehicle's lidar. as well as The yaw angle offset corresponding to the lidar is determined based on the ground normal vector and used as the first offset.

7. The method according to claim 4, wherein determining the first adjustment amount of the vehicle suspension based on the first offset includes: The position parameters of multiple wheels of the vehicle are determined based on the vehicle's center of gravity. Based on the position parameters of the plurality of wheels, the vertical displacement corresponding to each of the plurality of wheels is determined; as well as The first adjustment amount of the vehicle suspension is determined based on the vertical displacement.

8. The method according to claim 3, further comprising: In response to the second offset satisfying the preset condition, the planned trajectory of the vehicle is determined based on the second perception data of the vehicle.

9. The method according to claim 8, further comprising: In response to the second offset not meeting the preset condition and the vehicle not meeting the first condition, the vehicle is controlled by a preset control strategy.

10. The method according to claim 8, wherein determining the planned trajectory of the vehicle based on the second perception data of the vehicle comprises: The planned trajectory is determined based on the model and the second sensing data, wherein the model is configured to not provide control when a tire blows out.

11. The method of claim 8, wherein controlling the vehicle based on the adjustment of the vehicle suspension comprises: The vehicle control parameters are determined based on the planned trajectory, and the vehicle control parameters include at least one of yaw moment, longitudinal force, and vertical force. as well as Based on the vehicle control quantities, control commands are generated for the braking system, steering system, drive system, and active suspension system, respectively.

12. The method according to claim 8, further comprising: The driver's state is determined based on the driver's operation data, which includes at least one of steering torque, steering angular velocity, brake pedal rate of change, and accelerator pedal input. In response to the driver being in a target state, a fusion weight of a first weight and a second weight is determined, wherein the first weight is associated with the driver input and the second weight is associated with the autonomous driving control, and the first weight is less than the second weight; as well as The vehicle is controlled based on the fusion weights.

13. The method according to claim 12, wherein determining the driver's state based on the driver's operation data includes: The driver is determined to be in a target state in response to at least one of the following: The number of times the steering torque crosses zero within a preset time window exceeds a first threshold. The steering angular velocity exceeds the second threshold; The rate of change of the brake pedal exceeds the third threshold; or The driver's input direction continuously conflicts with the safe direction.

14. A device for vehicle control, comprising: An offset determination module is configured to determine a first offset of at least one sensor in the vehicle based on first perception data of the vehicle in response to detecting a tire blowout in the vehicle. The adjustment module is configured to adjust the vehicle suspension based on the first offset. as well as The control module is configured to control the vehicle based on the adjustment of the vehicle suspension.

15. A controller, comprising: At least one processor; as well as A memory coupled to the at least one processor and having instructions stored thereon, which, when executed by the at least one processor, cause the controller to perform the method according to any one of claims 1 to 13.

16. A computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, cause the method according to any one of claims 1 to 13 to be performed.

Images