Vehicle control method and related device

Abstract

The embodiment of the invention provides a vehicle control method and a related device, and the method comprises the steps: determining a curve boundary parameter based on data collected by a vehicle sensor; according to the kinetic model of the vehicle and the historical trajectory of the vehicle, performing trajectory prediction on the vehicle to obtain a predicted trajectory; generating turning control parameters of the vehicle based on the curve boundary parameters, a kinetic model of the vehicle, the predicted trajectory and the state information of the vehicle; and turning control is conducted on the vehicle based on the turning control parameters, so that the driving track of the vehicle is close to the curve center line. According to the method, breakthrough of global scene coverage and high-precision curve control can be achieved, dependence on a high-cost sensor is not needed, and curve control can be achieved only through low-cost hardware such as a foresight camera and a wheel speed sensor.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a vehicle control method and related apparatus. Background Technology

[0002] Vehicles frequently encounter various types of curves while driving, and these curve scenarios place extremely high demands on the safety and stability of vehicle driving.

[0003] Current cornering assist driving systems rely on data collected by multiple sensors, which is costly. Furthermore, the stability and safety of vehicle control decrease sharply in some cornering scenarios, making it difficult to meet user needs. Summary of the Invention

[0004] This application provides a vehicle control method and related apparatus to improve the stability and safety of a vehicle when turning.

[0005] In a first aspect, embodiments of this application provide a vehicle control method, including:

[0006] Based on data collected by vehicle sensors, the curve boundary parameters are determined; the vehicle sensors include at least an image acquisition device.

[0007] Based on the vehicle's dynamics model and its historical trajectory, the vehicle's trajectory is predicted to obtain the predicted trajectory.

[0008] Based on the curve boundary parameters, the vehicle's dynamic model, the predicted trajectory, and the vehicle's state information, the vehicle's turning control parameters are generated; the turning control parameters include a vehicle speed threshold and a steering angle, and the state information includes the vehicle's longitudinal speed and yaw rate.

[0009] The vehicle is controlled to turn based on the turning control parameters so that the vehicle's trajectory is close to the center line of the curve.

[0010] In some embodiments, generating the vehicle's turning control parameters based on the curve boundary parameters, the vehicle's dynamic model, the predicted trajectory, and the vehicle's state information includes:

[0011] Based on the curve boundary parameters, the vehicle's dynamic model, and the vehicle's state information, the target trajectory of the vehicle when turning is determined;

[0012] The vehicle speed threshold is determined based on the curvature of the target trajectory and the coefficient of friction between the vehicle and the road surface.

[0013] The steering angle is determined based on the predicted trajectory and the target trajectory.

[0014] In some embodiments, determining the target trajectory for the vehicle to turn based on the curve boundary parameters, the vehicle's dynamic model, and the vehicle's state information includes:

[0015] Based on the curve boundary parameters, the reference trajectory of the vehicle when turning is determined;

[0016] Based on the reference trajectory, the dynamic model, and the state information, a trajectory optimization model is constructed.

[0017] The target trajectory is obtained by solving the trajectory optimization model with the goal of minimizing the tracking error of the reference trajectory.

[0018] In some embodiments, determining the vehicle speed threshold based on the curvature of the target trajectory and the coefficient of friction between the vehicle and the road surface includes:

[0019] A first vehicle speed threshold is determined based on the curvature of the target trajectory and the coefficient of friction between the vehicle and the road surface.

[0020] The second vehicle speed threshold is determined based on the curve width and the friction coefficient.

[0021] The vehicle speed threshold is determined based on the first vehicle speed threshold and the second vehicle speed threshold.

[0022] In some embodiments, determining the steering angle based on the predicted trajectory and the target trajectory includes:

[0023] Determine the deviation between the predicted trajectory and the target trajectory;

[0024] The deviation is processed based on a feedback control algorithm to obtain the steering angle, so that the vehicle can track the target trajectory.

[0025] In some embodiments, the method further includes:

[0026] When driving at night, if it is determined that the confidence level of the image acquired by the image acquisition device is lower than a preset threshold, the gain and exposure time of the image acquisition device when acquiring data are reduced, and the infrared fill light is turned on.

[0027] In some embodiments, the method further includes:

[0028] The slip ratio of the vehicle is determined based on data collected by wheel speed sensors;

[0029] When the slip ratio of the vehicle is greater than a preset value, the upper limit of the lateral acceleration of the vehicle is reduced to a target value, and the braking force distribution ratio of the inner drive wheel of the vehicle is increased to a target ratio.

[0030] In some embodiments, the method further includes:

[0031] When the vehicle's travel path is determined to be a series of curves, the planned turning length of the vehicle is determined based on the length of the current curve.

[0032] The steering angle is planned in advance based on the planned turning length.

[0033] In some embodiments, the method further includes:

[0034] When the vehicle speed is greater than the vehicle speed threshold, deceleration control parameters for the vehicle are generated based on a preset deceleration gradient.

[0035] The vehicle is decelerated based on the aforementioned deceleration control parameters.

[0036] Secondly, embodiments of this application provide an electronic device, including a processor, a transceiver, and a memory; the processor is communicatively connected to both the transceiver and the memory.

[0037] The memory stores computer-executed instructions;

[0038] The transceiver communicates and interacts with external devices.

[0039] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0040] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method of any of the first aspects.

[0041] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method of any one of the first aspects.

[0042] The vehicle control method and related apparatus provided in this application determine curve boundary parameters based on data collected by vehicle sensors. The vehicle sensors include at least an image acquisition device. The vehicle's trajectory is predicted based on its dynamic model and historical trajectory to obtain a predicted trajectory. Turning control parameters are generated based on the curve boundary parameters, the vehicle's dynamic model, the predicted trajectory, and the vehicle's state information. These turning control parameters include a vehicle speed threshold and a steering angle, while the state information includes the vehicle's longitudinal speed and yaw rate. The vehicle is then turned based on these turning control parameters to bring its trajectory closer to the curve's centerline. This method, through a combination of algorithm and hardware adaptation, achieves breakthroughs in full-field scene coverage and high-precision curve control. It eliminates the need for high-cost sensors, requiring only low-cost hardware such as a forward-facing camera and wheel speed sensors to implement curve control. Attached Figure Description

[0043] Figure 1 A flowchart illustrating a vehicle control method provided in this application embodiment. Figure 1 ;

[0044] Figure 2 A flowchart illustrating a vehicle control method provided in this application embodiment. Figure 2 ;

[0045] Figure 3 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application;

[0046] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0048] In the embodiments of this application, the terms "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect, without limiting their order. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" do not necessarily imply that they are different.

[0049] It should be noted that, in the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0050] In real-world traffic environments, vehicles frequently encounter various types of curves, such as sharp bends on mountain roads (radius < 100 meters), continuous S-shaped curves on urban overpasses, and irregular curves caused by temporary construction. These scenarios place extremely high demands on vehicle trajectory control. For example, in sharp bends, it is necessary to accurately predict the curvature of the curve and dynamically adjust the vehicle speed and steering to avoid skidding or loss of control due to excessive centrifugal force; in continuous S-shaped curves, it is necessary to achieve smooth trajectory following, reducing sudden changes in lateral acceleration to improve ride comfort; in scenarios without lane markings or where lane markings are covered by snow, it is necessary to rely on multi-source data fusion and vehicle trajectory prediction algorithms to maintain the vehicle's centered driving.

[0051] Currently, solutions for curve control are mainly divided into three categories:

[0052] 1. Dynamic speed adjustment scheme based on monocular vision: This scheme identifies lane lines using a forward-facing camera and combines this with pre-stored curve curvature data from a high-precision map to dynamically adjust vehicle speed to adapt to the curve radius. However, this scheme relies on the coverage of the high-precision map and is ineffective on uncollected mountain roads or curves under temporary construction. Furthermore, its accuracy decreases in low-light conditions or when lane lines are blurred.

[0053] 2. Track correction assistance scheme based on electronic power steering (EPS): This scheme uses the EPS system to apply steering torque to keep the vehicle within the lane. It works well in gentle curves, but has a lower success rate in correcting deviations in sharp curves, and suffers from understeer or oversteer.

[0054] 3. Multimodal perception fusion solution: This solution uses LiDAR and 4D millimeter-wave radar to cross-verify curve boundaries, maintaining a high recognition rate even in adverse weather conditions (such as heavy rain). However, this solution relies on high-cost sensors, and its recognition rate drops sharply in low-reflectivity scenarios covered by snow, limiting its adoption in mid-to-low-end vehicles.

[0055] To address the aforementioned issues, this application provides a vehicle control method and related apparatus. Based on vehicle dynamics models and historical trajectory data, it constructs a vehicle trajectory prediction framework that does not rely on high-cost sensors (such as LiDAR). Simultaneously, through spatiotemporal alignment and confidence-weighted fusion of multi-source data (cameras, wheel speed sensors, gyroscopes, etc.), it dynamically corrects the trajectory prediction results and combines special scenario optimization strategies to achieve full-domain curve perception and human-like control with low-cost hardware, thereby balancing safety, economy, and user experience.

[0056] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0057] Figure 1 This is a flowchart illustrating a vehicle control method provided in an embodiment of this application, as shown below. Figure 1 As shown, it includes:

[0058] S101. Determine the curve boundary parameters based on the data collected by the vehicle sensors.

[0059] In some embodiments, vehicle sensors include image acquisition devices (such as cameras), wheel speed sensors, and gyroscopes.

[0060] Curve boundary parameters (referred to as curve boundaries) may include, but are not limited to, curve left and right boundary line model parameters (such as cubic polynomials), boundary line curvature, boundary line type (such as solid line, dashed line, etc.), boundary line confidence, lane width, and other information.

[0061] In some embodiments, the data collected by each sensor can be spatiotemporally aligned and then fused using a preset fusion algorithm to obtain the curve boundary parameters.

[0062] For example, based on the preset confidence levels of each sensor, Kalman filtering and Bayesian networks can be used to fuse the data collected by each sensor to obtain the curve boundary parameters.

[0063] For example, interpolation methods are used to synchronize data to the same time base and unify the data collected by various sensors to the vehicle coordinate system. Kalman filters are then used to process the spatiotemporally aligned data from each sensor. The output of the Kalman filters, along with the confidence scores of each sensor (e.g., 0.85 for the camera, 0.95 for the gyroscope, and 0.92 for the wheel speed sensor), are input into a Bayesian network for fusion to obtain the curve boundary parameters.

[0064] Optionally, in some higher-spec models, vehicle sensors may also include lidar, millimeter-wave radar, positioning devices, etc.

[0065] Optionally, in some high-end models, the vehicle can also communicate with the roadside unit to obtain road curve topology data, and obtain curve boundary parameters based on the curve topology data and the data collected by the vehicle's sensors.

[0066] S102. Based on the vehicle's dynamics model and historical trajectory, predict the vehicle's trajectory to obtain the predicted trajectory.

[0067] In some embodiments, the vehicle's historical trajectory may include trajectory point data from time tm to time t; wherein, the data for each trajectory point may include information such as the vehicle's speed, position, and acceleration at that trajectory point. Here, time t is the current time.

[0068] Vehicle dynamics models can be used to describe the basic geometric relationships of vehicle motion; for example, a two-degree-of-freedom vehicle model.

[0069] In some embodiments, the vehicle's historical trajectory can be obtained from the vehicle's recorded historical driving data.

[0070] A two-degree-of-freedom vehicle model can be shown as follows:

[0071]

[0072] Where m is the mass of the vehicle, r is the yaw rate of the vehicle, The integral of r , These are the vehicle's longitudinal speed and lateral speed, respectively. for Points, , Let be the lateral forces of the front and rear wheels of the vehicle, respectively, and let a and b be the distances from the vehicle's center of gravity to the front and rear axles, respectively. Let be the moment of inertia of the vehicle about the z-axis.

[0073] In some embodiments, the vehicle's historical trajectory can be processed based on a pre-trained trajectory prediction model to obtain the vehicle's predicted trajectory from time t+1 to time t+n.

[0074] The trajectory prediction model can be a model based on a long short-term memory network (LSTM), or a GRU-AM model consisting of two main components: a gated recurrent unit (GRU) and an attention mechanism (AM).

[0075] After obtaining the trajectory predicted by the model, a future trajectory can be directly derived using the dynamic model based on the vehicle's current state (such as position and speed) and assuming a constant control input in the future. The derived trajectory and the predicted trajectory sequence are then fused through a learnable weight network to obtain the final predicted trajectory. For example, the final trajectory = α * LSTM trajectory + (1-α) * dynamic model trajectory.

[0076] S103. Based on the curve boundary parameters, the vehicle's dynamic model, the predicted trajectory, and the vehicle's state information, generate the vehicle's turning control parameters.

[0077] In some embodiments, the turning control parameters include a vehicle speed threshold and a steering angle, and the status information includes the vehicle's longitudinal speed and yaw rate.

[0078] In some embodiments, the cornering boundary parameters, the vehicle's dynamics model, the predicted trajectory, and the vehicle's state information can be output to a pre-trained prediction model (e.g., a model built based on reinforcement learning or a recurrent neural network) to obtain the turning control parameters output by the model.

[0079] In some embodiments, the target trajectory for vehicle turning can be determined based on the curve boundary parameters, the vehicle's dynamics model, and the vehicle's state information; the vehicle's turning control parameters can be determined based on the target trajectory and the predicted trajectory.

[0080] The target trajectory can refer to the ideal trajectory of a vehicle when turning.

[0081] For example, cubic spline interpolation or polynomial fitting can be used to fit the curve boundary parameters, obtaining the curve centerline parametric equation, and using the curve centerline as the vehicle's reference trajectory. Based on the vehicle's dynamics model and current state information, the vehicle's state (position, heading angle, etc.) at the next n time points is predicted, and the deviation between the vehicle's state at the next n time points and its state at the corresponding time points on the reference trajectory is obtained. Based on the deviation, a trajectory optimization function is constructed, and the target trajectory is obtained by solving it using sequential quadratic programming (SQP) or the interior point method with the objective of minimizing the deviation.

[0082] In some embodiments, after obtaining the target trajectory, vehicle turning control parameters can be obtained based on the deviation between the target trajectory and the predicted trajectory.

[0083] For example, the lateral deviation and rate of change of deviation at each identical point in the target trajectory and the predicted trajectory can be calculated, and the steering angle can be calculated using a controller (such as a PID controller). For example: Steering angle = Kp * lateral deviation + Kd * rate of change of lateral deviation.

[0084] For example, the curvature on the target trajectory can be used to obtain the velocity threshold according to a preset mapping relationship (the greater the curvature, the smaller the velocity threshold).

[0085] S104. Perform turning control on the vehicle based on the turning control parameters so that the vehicle's trajectory is close to the center line of the curve.

[0086] In some embodiments, after obtaining the turning control parameters, the steering torque of the vehicle can be adjusted based on the steering angle during the vehicle's turning process, and the vehicle can be controlled to decelerate when the vehicle's speed reaches a certain threshold.

[0087] The vehicle control method provided in this application determines curve boundary parameters based on data collected by vehicle sensors. The vehicle sensors include at least an image acquisition device. The vehicle's trajectory is predicted based on its dynamic model and historical trajectory. Turning control parameters are generated based on the curve boundary parameters, the vehicle's dynamic model, the predicted trajectory, and the vehicle's state information. These parameters include a speed threshold and a steering angle, while the state information includes the vehicle's longitudinal speed and yaw rate. The vehicle is then controlled to turn based on these parameters, ensuring its trajectory approaches the curve's centerline. This method, through a combination of algorithm and hardware adaptation, achieves breakthroughs in full-field scene coverage and high-precision curve control. It eliminates the need for high-cost sensors (such as LiDAR), requiring only low-cost hardware such as a forward-facing camera and wheel speed sensors to implement curve control.

[0088] Below Figure 1 Based on the embodiments shown, the vehicle control method provided in this application will be further described.

[0089] Figure 2 A flowchart illustrating a vehicle control method provided in this application embodiment. Figure 2 ,like Figure 2 As shown, it includes:

[0090] S201. Determine the curve boundary parameters based on the data collected by the vehicle sensors.

[0091] The specific implementation method of step S201 in the embodiments of this application is the same as Figure 1 The specific implementation methods in the illustrated embodiments are similar and will not be described again here.

[0092] In some embodiments, when vehicles are driving at night, reflections from road signs, guardrails, etc., on curves can severely interfere with the visual camera, causing overexposure and glare, leading to lane line recognition failure or inaccurate distance judgment. Therefore, this situation needs to be optimized to avoid collision risks caused by abnormal curve boundary parameters.

[0093] For example, when driving at night, if it is determined that the confidence level of the image acquired by the image acquisition device is lower than a preset threshold, the gain and exposure time of the image acquisition device when acquiring data are reduced, and the infrared fill light is turned on.

[0094] For example, when using a visual processing algorithm to process data collected by a camera to identify lane lines, the confidence level of the recognition result output by the visual processing algorithm is obtained simultaneously. If the average confidence level of the lane lines remains below a threshold within a preset time period (e.g., 5 seconds), or if the number of effectively identified targets remains insufficient (e.g., only one lane line can be identified, or even none can be identified at all), it is determined that the confidence level of the image collected by the image acquisition device is below the preset threshold.

[0095] In this situation, the image acquisition device can be controlled to reduce its gain and exposure time (e.g., to 1 / 1000s) to reduce the total amount of light entering the sensor, avoid saturation in bright areas, and thus retain more details in dark areas. Simultaneously, an infrared fill light is activated to emit near-infrared light of a preset wavelength (e.g., 850nm) to provide active illumination for the image acquisition device, compensating for the light lost due to the shortened exposure and ensuring that road surface details ahead are clearly captured while suppressing reflections.

[0096] S202. Based on the vehicle's dynamics model and historical trajectory, predict the vehicle's trajectory to obtain the predicted trajectory.

[0097] The specific implementation method of step S202 in the embodiments of this application is the same as Figure 1 The specific implementation methods in the illustrated embodiments are similar and will not be described again here.

[0098] S203. Based on the curve boundary parameters, the vehicle's dynamic model, and the vehicle's state information, determine the target trajectory of the vehicle when turning.

[0099] In some embodiments, the target trajectory of a vehicle turning can be obtained as follows:

[0100] For example, a reference trajectory for the vehicle when turning is determined based on the curve boundary parameters; a trajectory optimization model is constructed based on the reference trajectory, dynamic model, and state information; the trajectory optimization model is solved with the goal of minimizing the tracking error of the reference trajectory to obtain the target trajectory.

[0101] For example, based on the curve boundary parameters, a reference trajectory for the vehicle during turning is obtained by fitting the boundary center using a polynomial curve. A trajectory optimization model is then constructed based on the vehicle's dynamics model and current state information. An optimization solver (such as IPOPT or CasaADi) is used to solve the constructed trajectory optimization model to obtain the target trajectory.

[0102] The optimization problem can include:

[0103] State variables: vehicle position, speed, heading angle, front wheel steering angle, etc.;

[0104] Controlled variables: acceleration, rate of change of front wheel steering angle, etc.;

[0105] Objective function: Minimize tracking error (such as position error, heading error) and control variable changes (to smooth control), etc.

[0106] Constraints include vehicle dynamics constraints, control quantity constraints (such as maximum steering angle and maximum acceleration), state constraints (such as speed limits), and collision avoidance constraints (such as road boundary constraints).

[0107] For example, the objective function can be as follows:

[0108]

[0109] Where x and y are the vehicle's position in the global coordinate system, x_ref and y_ref are the positions on the reference trajectory, ψ is the vehicle's heading angle, ψ_ref is the heading angle on the reference trajectory, U is the control input vector, including steering wheel angle δ and acceleration a, etc., w_ψ is the weight of the heading error. If heading tracking is important, a larger w_ψ is set. w_u is the weight of the control quantity, used to penalize excessive control input and make the control smooth.

[0110] S204. Determine the vehicle speed threshold based on the curvature of the target trajectory and the friction coefficient between the vehicle and the road surface.

[0111] In some embodiments, when solving the trajectory optimization model to obtain the target trajectory, the curvature of the target trajectory can be obtained simultaneously.

[0112] After determining the curvature of the target trajectory, the vehicle speed threshold can be determined based on the following method.

[0113] For example, the vehicle speed threshold satisfies the following formula:

[0114]

[0115] in, Let be the coefficient of friction, and k be the curvature of the target trajectory. Where is the acceleration due to gravity, and h is a preset safety factor, such as 0.8.

[0116] In some embodiments, the turning speed of a vehicle can be affected by the width of the curve when it turns in different bends. For example, the wider the curve, the higher the speed at which the vehicle can be driven.

[0117] For example, a first vehicle speed threshold is determined based on the curvature of the target trajectory and the friction coefficient between the vehicle and the road surface; a second vehicle speed threshold is determined based on the curve width and the friction coefficient; and a vehicle speed threshold is determined based on the first and second vehicle speed thresholds.

[0118] For example, the vehicle speed threshold satisfies the following formula:

[0119]

[0120] Where f is the width coefficient and R is the curve radius. f can be set according to the width of the curve; the larger the width, the larger the value of f.

[0121] S205. Determine the steering angle based on the predicted trajectory and the target trajectory.

[0122] In some embodiments, the steering angle of a vehicle when turning can be obtained based on the following method.

[0123] For example, the deviation between the predicted trajectory and the target trajectory can be determined; the deviation is processed based on a feedback control algorithm to obtain the steering angle so that the vehicle can track the target trajectory.

[0124] For example, the deviation between the predicted trajectory and the target trajectory can include lateral position deviation and heading deviation. The obtained deviations are input into a feedback control algorithm, which calculates the vehicle's steering angle in real time based on the magnitude and trend of the deviations. The feedback control algorithm can employ algorithms such as PID control, feedforward-feedback composite control, or model predictive control.

[0125] In some embodiments, in the case of continuous curves, in order to ensure the stability of the vehicle when passing through continuous curves and reduce the problem of the vehicle swaying from side to side, the steering angle can also be adjusted based on the continuous curves.

[0126] For example, when the vehicle's driving path is determined to be a series of curves, the vehicle's turning planning length is determined based on the length of the current curve; the steering angle is planned in advance based on the turning planning length.

[0127] For example, the planned turning length of the vehicle can be 1.5 times or 2 times the current turning length, and this application embodiment does not limit this.

[0128] Starting from the point where the vehicle's current position is on the target trajectory, the arc length is accumulated forward along the target trajectory until the accumulated length equals the planned turning length. The state information (such as position, heading angle, curvature, etc.) corresponding to this point (called the preview point) is obtained. Based on the aforementioned method, the steering angle of the vehicle passing through the preview point is obtained. The lateral and heading deviations between the vehicle's current position and the preview point are determined. A proportional-derivative or linear quadratic regulator is used to process the lateral and heading deviations to obtain the correction value for the steering angle. The sum of the steering angle of the vehicle passing through the preview point and the correction value of the steering angle is used as the output steering angle of the preview point. By setting the preview point, the vehicle can plan the steering angle for passing through continuous curves in advance, i.e., a predictive steering angle, rather than correcting the vehicle's steering angle based on the current curve. This controls the vehicle to turn the steering wheel in advance and smoothly according to the predicted curve, allowing the car to naturally enter the curve and improving the smoothness and stability of the vehicle when cornering.

[0129] S206. Vehicle turning control is performed based on vehicle speed threshold and steering angle.

[0130] In some embodiments, the electronic stability program (ESP) can be used to control the braking force of the four wheels by applying a corresponding steering torque to the vehicle's motor based on the obtained steering angle and a safe speed threshold.

[0131] In some embodiments, when the vehicle speed is greater than a vehicle speed threshold, deceleration control parameters for the vehicle are generated based on a preset deceleration gradient; and deceleration control of the vehicle is performed based on the deceleration control parameters.

[0132] For example, a deceleration gradient of ≤-0.3g ensures a smoother deceleration process for the vehicle, avoiding emergency braking and improving the user experience.

[0133] In some embodiments, when the vehicle is turning, if the road surface is covered with snow or has low adhesion, the vehicle can be controlled to enter an anti-skid control mode to avoid sideslipping when turning.

[0134] For example, based on data collected by wheel speed sensors, the vehicle's slip ratio is determined; when the vehicle's slip ratio is greater than a preset value, the upper limit of the vehicle's lateral acceleration is reduced to a target value, and the braking force distribution ratio of the vehicle's inner drive wheels is increased to a target ratio.

[0135] For example, the slip ratio of a vehicle can satisfy the following formula:

[0136]

[0137] in, For the lateral speed of the wheel, For wheel radius, This represents the angular velocity of the wheel.

[0138] When the slip ratio exceeds a preset value (e.g., 5%), it indicates significant slippage between the tires and the road surface, and the system identifies it as a low-traction surface. This can reduce the upper limit of the vehicle's lateral acceleration (e.g., from 0.4g to 0.3g) to avoid excessive lateral force leading to skidding; and increase the braking force distribution to the inner drive wheels (e.g., increase by 20%) to generate a yaw moment that assists vehicle steering. This enhances the active steering assist of the electronic system, allowing the vehicle to corner more flexibly and stably under low-traction conditions.

[0139] In summary, the vehicle control method provided in this application, through the combination of a vehicle trajectory prediction algorithm and a multi-source data fusion strategy, can cover sharp curves and continuous S-shaped curves with small radii, significantly improving safety under complex road conditions; it does not rely on high-cost sensors such as lidar, but only requires a forward-looking camera and wheel speed sensors to achieve high-precision control, adapting to the intelligent upgrade needs of mid-to-low-end vehicles; by dynamically adjusting the deceleration gradient and steering torque, it reduces sudden changes in lateral acceleration, increasing user trust in the assistance system; in severe weather conditions such as heavy rain and snow, it effectively maintains vehicle stability and reduces system failure rate by judging road conditions and torque vector distribution strategies through slip ratio.

[0140] Figure 3 This is a schematic diagram of the structure of the vehicle control device 30 provided in the embodiments of this application, as shown below. Figure 3 As shown, it includes:

[0141] The determination module 301 is used to determine the curve boundary parameters based on the data collected by the vehicle sensors; the vehicle sensors include at least an image acquisition device.

[0142] The prediction module 302 is used to predict the trajectory of the vehicle based on the vehicle's dynamics model and its historical trajectory, and obtain the predicted trajectory.

[0143] The processing module 303 is used to generate turning control parameters for the vehicle based on the curve boundary parameters, the vehicle's dynamic model, the predicted trajectory, and the vehicle's state information. The turning control parameters include the vehicle speed threshold and the steering angle, and the state information includes the vehicle's longitudinal speed and yaw rate.

[0144] The control module 304 is used to control the vehicle to turn based on the turning control parameters so that the vehicle's trajectory is close to the center line of the curve.

[0145] In some embodiments, the processing module 303 is used to determine the target trajectory of the vehicle when turning based on the curve boundary parameters, the vehicle's dynamic model and the vehicle's state information; determine the vehicle speed threshold based on the curvature of the target trajectory and the friction coefficient between the vehicle and the road surface; and determine the steering angle based on the predicted trajectory and the target trajectory.

[0146] In some embodiments, the processing module 303 is used to determine a reference trajectory for the vehicle when turning based on the curve boundary parameters; construct a trajectory optimization model based on the reference trajectory, dynamic model and state information; and solve the trajectory optimization model with the goal of minimizing the tracking error of the reference trajectory to obtain the target trajectory.

[0147] In some embodiments, the processing module 303 is configured to determine a first vehicle speed threshold based on the curvature of the target trajectory and the friction coefficient between the vehicle and the road surface; determine a second vehicle speed threshold based on the curve width and the friction coefficient; and determine a vehicle speed threshold based on the first vehicle speed threshold and the second vehicle speed threshold.

[0148] In some embodiments, the processing module 303 is used to determine the deviation between the predicted trajectory and the target trajectory; and to process the deviation based on a feedback control algorithm to obtain a steering angle so that the vehicle tracks the target trajectory.

[0149] In some embodiments, the determining module 301 is configured to, when driving at night, reduce the gain and exposure time of the image acquisition device when acquiring data, and turn on the infrared fill light if it is determined that the confidence level of the image acquired by the image acquisition device is lower than a preset threshold.

[0150] In some embodiments, the control module 304 is configured to determine the vehicle's slip ratio based on data collected by the wheel speed sensor; when the vehicle's slip ratio is greater than a preset value, reduce the upper limit of the vehicle's lateral acceleration to a target value; and increase the braking force distribution ratio of the vehicle's inner drive wheels to a target ratio.

[0151] In some embodiments, the processing module 303 is configured to determine the turning planning length of the vehicle based on the length of the current curve when the vehicle's driving path is determined to be a series of curves; and to plan the steering angle in advance based on the turning planning length.

[0152] In some embodiments, the control module 304 is used to generate deceleration control parameters for the vehicle based on a preset deceleration gradient when the vehicle speed is greater than a vehicle speed threshold; and to perform deceleration control on the vehicle based on the deceleration control parameters.

[0153] The vehicle control device provided in this application embodiment can execute the vehicle control method shown in any of the above embodiments. Its principle and technical effect are similar, and will not be described again here.

[0154] This application also provides an electronic device.

[0155] Figure 4 This is a schematic diagram of the structure of the electronic device 40 provided in the embodiments of this application, such as... Figure 4 As shown, the electronic device may include: transceiver 401, processor 402, and memory 403.

[0156] Processor 402 executes computer execution instructions stored in memory, causing processor 402 to perform the scheme in the above embodiments. Processor 402 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0157] The memory 403 is connected to the processor 402 via the system bus and completes communication between them. The memory 403 is used to store computer program instructions.

[0158] Transceiver 401 can perform the functions of receiving and sending data and instructions.

[0159] Optionally, the electronic device 40 may also include a communication interface 404, which allows communication and interaction with external or internal devices via the communication interface 403. External devices may be, for example, client devices (e.g., mobile phones, tablets). In specific implementations, if the communication interface 404, memory 403, and processor 402 are implemented independently, they can be interconnected via a bus to complete communication with each other.

[0160] The system bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. Transceivers are used to enable communication between database access devices and other computers (e.g., clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) and may also include non-volatile memory.

[0161] Optionally, in a specific implementation, if the communication interface 404, memory 403, and processor 402 are integrated on a single chip, then the communication interface 404, memory 403, and processor 402 can communicate through an internal interface.

[0162] This application also provides a chip for executing instructions, which is used to execute the technical solutions of the methods described in the above embodiments.

[0163] This application also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0164] In one possible implementation, a computer-readable medium may include random access memory (RAM), read-only memory (ROM), compact discread-only memory (CD-ROM) or other optical disc storage, disk storage or other magnetic storage devices, or any other medium targeted to carry or to store the required program code in the form of instructions or data structures, and accessible by a computer. Furthermore, any connection is appropriately referred to as a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. As used herein, disks and optical discs include optical discs, laser discs, optical discs, Digital Versatile Discs (DVDs), floppy disks, and Blu-ray discs, where disks typically reproduce data magnetically, while optical discs optically reproduce data using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0165] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the technical solution of the above method embodiments. Its implementation principle and technical effects are similar, and will not be repeated here.

[0166] In the specific implementation of the aforementioned terminal device or server, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0167] Those skilled in the art will understand that all or part of the steps in any of the above method embodiments can be implemented by hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium, and when the program is executed, all or part of the steps in the above method embodiments are performed.

[0168] If the technical solution of this application is implemented in software form and sold or used as a product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of this application can be embodied in the form of a software product, which is stored in a storage medium and includes a computer program or several instructions. This computer software product enables a computer device (which may be a personal computer, server, network device, or similar electronic device) to execute all or part of the steps of the methods in the embodiments of this application.

[0169] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0170] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0171] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0172] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0173] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0174] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0175] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A vehicle control method characterized by, The method comprises: determining a curve boundary parameter based on data collected by a vehicle sensor; the vehicle sensor at least comprises an image collection device; performing trajectory prediction on the vehicle based on a vehicle dynamics model and a historical trajectory of the vehicle, to obtain a predicted trajectory; generating a turning control parameter of the vehicle based on the curve boundary parameter, the vehicle dynamics model, the predicted trajectory and state information of the vehicle; the turning control parameter comprises a vehicle speed threshold and a steering angle, and the state information comprises a longitudinal speed and a yaw rate of the vehicle; performing turning control on the vehicle based on the turning control parameter, so that the driving trajectory of the vehicle is close to a curve center line.

2. The method of claim 1, wherein, The generating of the turning control parameter of the vehicle based on the curve boundary parameter, the vehicle dynamics model, the predicted trajectory and the state information of the vehicle comprises: determining a target trajectory of the vehicle when turning based on the curve boundary parameter, the vehicle dynamics model and the state information of the vehicle; determining the vehicle speed threshold based on a curvature of the target trajectory and a friction coefficient between the vehicle and the road surface; determining the steering angle based on the predicted trajectory and the target trajectory.

3. The method of claim 2, wherein, The determining of the target trajectory of the vehicle when turning based on the curve boundary parameter, the vehicle dynamics model and the state information of the vehicle comprises: determining a reference trajectory of the vehicle when turning based on the curve boundary parameter; constructing a trajectory optimization model based on the reference trajectory, the vehicle dynamics model and the state information; solving the trajectory optimization model to obtain the target trajectory, with the goal of minimizing the tracking error of the reference trajectory.

4. The method of claim 2, wherein, The determining of the vehicle speed threshold based on the curvature of the target trajectory and the friction coefficient between the vehicle and the road surface comprises: determining a first vehicle speed threshold based on the curvature of the target trajectory and the friction coefficient between the vehicle and the road surface; determining a second vehicle speed threshold based on the curve width and the friction coefficient; determining the vehicle speed threshold based on the first vehicle speed threshold and the second vehicle speed threshold.

5. The method of claim 2, wherein, The determining of the steering angle based on the predicted trajectory and the target trajectory comprises: determining a deviation between the predicted trajectory and the target trajectory; processing the deviation based on a feedback control algorithm to obtain the steering angle, so that the vehicle tracks the target trajectory.

6. The method according to claim 4 or 5, characterized in that, The method further comprises: when driving at night, if it is determined that the confidence of the image collected by the image collection device is lower than a preset threshold, then reducing the gain and exposure time when the image collection device collects data, and turning on an infrared fill light.

7. The method of claim 6, wherein, The method further comprises: determining the slip rate of the vehicle based on data collected by a wheel speed sensor; when the slip rate of the vehicle is greater than a preset value, reducing the upper limit value of the lateral acceleration of the vehicle to a target value, and increasing the distribution ratio of the braking force of the inner drive wheel of the vehicle to a target ratio.

8. The method of claim 6, wherein, The method further comprises: when it is determined that the driving path of the vehicle is a continuous curve, determining a turning planning length of the vehicle based on the length of the current curve; anticipating the planning of the steering angle based on the turning planning length.

9. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: generating a deceleration control parameter of the vehicle based on a preset deceleration gradient when the speed of the vehicle is greater than the vehicle speed threshold; controlling the vehicle to decelerate based on the deceleration control parameter.

10. An electronic device, comprising: Comprise: a processor, a transceiver, and a memory; the processor is in communication connection with the transceiver and the memory respectively; the memory stores computer execution instructions; the transceiver communicates with external devices; the processor executes the computer execution instructions stored in the memory to realize the method as claimed in any one of claims 1-9.

11. A computer readable storage medium, characterized in that, A computer program is stored thereon, and the computer program is executed by a processor to realize the method as claimed in any one of claims 1-9.

12. A computer program product, characterised in that, A computer program is stored thereon, and the computer program is executed by a processor to realize the method as claimed in any one of claims 1-9. A computer program is stored thereon, and the computer program is executed by a processor to realize the method as claimed in any one of claims 1-9.

Images