Transverse control method and device of vehicle, electronic equipment and vehicle

Abstract

The invention provides a transverse control method and device of a vehicle, electronic equipment and the vehicle. The method comprises the steps that front road surface state information of the vehicle is obtained; under the condition that the target bumping area is recognized based on the front road surface state information, a target smooth driving track is generated according to the target bumping area and the lane line where the vehicle is located; and based on the current vehicle speed, the current driving track and the target smooth driving track of the vehicle, target torque and a target steering angle are determined, a transverse control instruction is generated according to the target torque and the target steering angle, and transverse control is conducted on the vehicle according to the transverse control instruction. After a front bumping area is recognized, a lane line and a bumping geometric boundary are fused to generate a target smooth driving track, and a target steering angle and compensation torque are dynamically determined in combination with the current vehicle speed and the track to generate a transverse control instruction, so that the vehicle can be controlled to pass through the bumping area stably and smoothly based on the transverse control instruction; and the comfort and the safety of automatic driving transverse control are improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, device, electronic equipment, and vehicle for lateral control of a vehicle. Background Technology

[0002] With the rapid development of autonomous driving technology, the smoothness and comfort of vehicle lateral control have become one of the key indicators for measuring the performance of autonomous driving systems. On structured roads, when vehicles drive on uneven road surfaces, they often face problems such as trajectory tracking disturbances, trajectory planning blind spots, and insufficient actuator response.

[0003] In related technologies, the level of road bumpiness is determined by monitoring changes in vehicle speed, and a counter-torque opposite to the steering wheel angle is applied after a bump is detected to suppress deviation.

[0004] However, the above method can easily cause unexpected shaking of the steering wheel when driving on bumpy roads, thus affecting the smoothness of lateral control, which urgently needs to be addressed. Summary of the Invention

[0005] This application provides a lateral control method, device, electronic device, and vehicle for a vehicle, in order to solve the technical problem that in the case of autonomous driving systems of the related technology, the steering wheel cannot be effectively suppressed due to road impacts when passing through bumpy roads, thus affecting the smoothness of lateral control.

[0006] The first aspect of this application provides a method for lateral control of a vehicle, comprising the following steps: Obtain information about the road conditions ahead of the vehicle; If a target bumpy area is identified based on the road surface condition information ahead, a target smooth driving trajectory is generated according to the target bumpy area and the lane line where the vehicle is located. Based on the vehicle's current speed, current driving trajectory, and target smooth driving trajectory, a target torque and a target steering angle are determined, and a lateral control command is generated according to the target torque and the target steering angle to perform lateral control on the vehicle.

[0007] The above technical solution identifies bumpy areas ahead, integrates lane lines and bumpy geometric boundaries to generate a smooth target driving trajectory, and dynamically determines the target steering angle and compensation torque based on the current vehicle speed and trajectory to generate lateral control commands. This allows the vehicle to smoothly and effortlessly traverse bumpy areas based on lateral control commands, improving the comfort and safety of lateral control in autonomous driving. It solves the technical problems of steering wheel vibration, trajectory deviation, and lateral control instability caused by the lack of coordinated control of trajectory correction and torque compensation in related autonomous driving systems on bumpy roads.

[0008] A second aspect of this application provides a lateral control device for a vehicle, comprising: The acquisition module is used to acquire information about the road surface ahead of the vehicle. The generation module is used to generate a target smooth driving trajectory based on the target bumpy area and the lane line where the vehicle is located, when the target bumpy area is identified based on the road surface condition information ahead. The control module is used to determine the target torque and target steering angle based on the vehicle's current speed, current driving trajectory, and target smooth driving trajectory, and to generate lateral control commands based on the target torque and target steering angle, so as to perform lateral control on the vehicle according to the lateral control commands.

[0009] A third aspect of this application provides an electronic device, including a processor and a memory, wherein, Memory, used to store computer programs; A processor is used to execute programs stored in memory to implement any of the methods described in the above embodiments.

[0010] A fourth aspect of this application provides a vehicle that includes the electronic equipment described above.

[0011] A fifth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements any of the methods described in the above embodiments.

[0012] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0013] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a lateral control method for a vehicle according to an embodiment of this application; Figure 2 This is a schematic diagram of a smooth driving trajectory control architecture according to an embodiment of this application; Figure 3 This is a schematic diagram illustrating the relationship between the input and output quantities for smooth driving trajectory control according to an embodiment of this application; Figure 4 This is a schematic diagram of a convex hull trajectory smoothing method according to an embodiment of this application; Figure 5 This is a schematic diagram of a method for smoothing the trajectory of a speed bump according to an embodiment of this application; Figure 6 This is a schematic diagram of a method for stabilizing EPS (Electric Power Steering) on ​​bumpy roads according to an embodiment of this application; Figure 7 This is a schematic diagram of a scheme for mitigating reverse impact on the road surface according to an embodiment of this application; Figure 8 This is a flowchart illustrating the overall solution according to one embodiment of this application; Figure 9 This is an example diagram of a lateral control device for a vehicle according to an embodiment of this application; Figure 10 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0014] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the following detailed description is provided in conjunction with embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0015] Specifically, before introducing the embodiments of this application, we will first introduce the relevant background technology and existing technical problems. Current autonomous driving systems generally adopt lane-line-based lateral control strategies, acquiring lane information through cameras or fused perception to plan the vehicle's trajectory, and executing steering control through an electric power steering system. Some steering systems apply corrective torque when they detect the vehicle deviating from the lane to maintain lane centering. Furthermore, related technologies attempt to determine road impact based on wheel speed fluctuations or steering wheel disturbances after the vehicle has entered a bumpy area, and apply a counter-torque to suppress deviation; this belongs to passive response control.

[0016] Therefore, the above technical solutions mainly have the following technical problems: (1) lack of bump prediction capability: most existing systems rely on feedback signals after the vehicle has been impacted for compensation, which cannot intervene in advance, resulting in control lag; (2) failure to integrate road geometry information: relying only on lane lines for trajectory planning, when bumpy areas (such as bumps, speed bumps) block or destroy lane lines, it is easy to cause trajectory loss or sudden change; (3) passive steering control: even if compensation torque is applied, it is mostly simple reverse damping, without combining vehicle speed and trajectory curvature for refined feedforward compensation, making it difficult to suppress unexpected steering wheel shaking.

[0017] Therefore, based on the technical problems existing in the above-mentioned solutions, there is an urgent need for a lateral control method with bump prediction, trajectory reconstruction and active steering compensation capabilities to achieve smooth and seamless passage on bumpy roads. The following will provide a detailed explanation through specific implementation schemes.

[0018] This application applies to electric vehicles and internal combustion engine vehicles equipped with an autonomous driving system. This autonomous driving system includes an autonomous driving domain controller, road surface detection and sensing devices, and braking, steering, and drive systems. The autonomous driving domain controller receives input signals from the sensing sensors, fuses and calculates road surface information and the vehicle's trajectory. Surrounding lane lines and road surface detection devices can use sensors such as smart cameras and LiDAR to detect road surface information in the vehicle's driving lane. The drive, steering, and braking control devices control the vehicle's acceleration, deceleration, and lateral control, generating corresponding control commands to control the steering and braking systems, thereby enabling comfortable control of the autonomous vehicle.

[0019] Specifically, Figure 1 This is a flowchart illustrating a lateral control method for a vehicle provided in an embodiment of this application.

[0020] like Figure 1 As shown, the lateral control method for this vehicle includes the following steps: In step S101, the road surface condition information ahead of the vehicle is obtained.

[0021] In step S102, if the target bumpy area is identified based on the road surface condition information ahead, a target smooth driving trajectory is generated according to the target bumpy area and the lane line where the vehicle is located.

[0022] In step S103, based on the vehicle's current speed, current driving trajectory, and target smooth driving trajectory, the target torque and target steering angle are determined, and a lateral control command is generated according to the target torque and target steering angle to perform lateral control on the vehicle.

[0023] Therefore, by identifying bumpy areas ahead, the system integrates lane lines and bumpy geometric boundaries to generate a smooth target driving trajectory. It also dynamically determines the target steering angle and compensation torque based on the current vehicle speed and trajectory to generate lateral control commands. This allows the vehicle to smoothly and effortlessly traverse bumpy areas based on lateral control commands, improving the comfort and safety of lateral control in autonomous driving. This solves the technical problems of steering wheel vibration, trajectory deviation, and lateral control instability caused by the lack of coordinated control of trajectory correction and torque compensation in autonomous driving systems on bumpy roads.

[0024] Step S101 includes the following aspects: Specifically, such as Figure 2As shown, in addition to considering the safety, efficiency, and rationality of the vehicle's driving trajectory, this application also comprehensively considers the comfort of the driving trajectory. This application mainly adds road surface status signals on the basis of the existing trajectory, so that the vehicle can control the vehicle to drive more smoothly when passing through bumpy roads. At the same time, the steering system (such as EPS) receives road surface signals, triggers a forced follow intelligent driving angle request, increases control torque, and filters the steering wheel shaking caused by the reverse impact of bumpy roads, so as to improve the sense of security of autonomous driving vehicles.

[0025] The system in this application includes an autonomous driving domain controller that calculates the vehicle's driving trajectory and requests EPS lateral control; a braking system that provides vehicle speed signals, and the steering torque will vary at different vehicle speeds; an in-vehicle infotainment system that provides the vehicle's driving navigation path, and intelligent driving requires the output of the driving trajectory in conjunction with the navigation signals; and a perception system that provides lane line information, serves as a reference boundary for the trajectory, and can also provide information on road bumps, including the size, height, or depth of speed bumps, road protrusions, and potholes.

[0026] Specifically, such as Figure 3 As shown, this application first needs to collect road surface condition information in front of the vehicle through an onboard forward perception sensor. For example, image semantic segmentation can be performed through a forward-facing camera to identify abnormal road surface areas such as speed bumps, manhole covers, bumps, or potholes in front of the vehicle. Secondly, this application can combine the height change of the perception system on the Z-axis (vertical direction) of the area to calculate the Z-direction height difference of each abnormal area relative to the surrounding road surface. When the absolute value of the Z-direction height difference of an abnormal area is greater than a preset threshold (e.g., 2 cm), that is, when the absolute value of the Z-direction height difference between the road bump or pothole and the ground is > 2 cm, the intelligent driving system determines that there is a possibility of bumps on the driving trajectory, indicating that there are abnormal areas in the road surface condition information where bumps occur. Then, the abnormal area is the target bump area, which is used for subsequent bump effectiveness judgment and trajectory planning.

[0027] Thus, by identifying the target bumpy area, the system can accurately determine the bumpy event and actively mark the system state, providing a reliable trigger basis for subsequent trajectory reconstruction and steering torque feedforward compensation, effectively avoiding false or missed responses, and improving control robustness and comfort.

[0028] Step S102 includes the following aspects: Optionally, in one embodiment of this application, generating a target smooth driving trajectory based on the target bumpy area and the lane line where the vehicle is located includes: identifying the geometric boundary of the target bumpy area, and generating a virtual lane line based on the intersection of the geometric boundary of the target bumpy area and the lane line where the vehicle is located; and optimizing the virtual lane line with the same curvature based on the curvature and confidence of adjacent lane lines to obtain the target smooth driving trajectory.

[0029] Specifically, such as Figure 3 As shown, the purpose of this application embodiment is to optimize the driving trajectory and lateral control smoothness of autonomous vehicles. During trajectory planning, road condition information is incorporated for filtering. Compared with traditional trajectory optimization, it has two main advantages. First, the autonomous driving trajectory output takes into account road condition information. When there is a target bumpy area, it is necessary to filter the interference of road unevenness on the trajectory. Second, the road condition information is sent to the steering system. When the steering system receives the road unevenness information and angle request, it will increase the torque output and forcefully respond to the intelligent driving angle request in a short time, filtering the steering wheel shaking caused by the reverse impact of the road.

[0030] Therefore, when the sensing sensor detects unevenness on the road surface, it re-plans a new driving trajectory by fusing lane line and road surface unevenness information to obtain the target smooth driving trajectory, thereby ensuring that the smooth driving trajectory is not affected by road surface unevenness and smoothly passes through the target bumpy area.

[0031] Specifically, this application uses two types of bumpy road surfaces, such as road bumps and speed bumps, as examples. First, a perception sensor identifies the geometric boundary of the target bumpy area, and then generates a virtual lane line based on the intersection of the geometric boundary of the target bumpy area and the lane line where the vehicle is located. Figure 4 For lane lines on a road surface convex hull, their geometric boundaries are defined by the entry point B and the exit point A. Points A and B are the front and rear endpoints of the convex hull in the lane line direction, and also the intersections with the lane line where the vehicle is located. Points A and B are smoothly stitched together based on the vehicle's adjacent lane lines (e.g., the right lane line) to obtain a virtual lane line, which is used to replace the original lane line as a trajectory planning reference. The virtual lane line is optimized for the same curvature based on the curvature and confidence of the adjacent lane lines. That is, while maintaining the consistency of the overall path direction, the curvature change of the virtual lane line when entering and leaving the target bumpy area matches the surrounding lane lines, avoiding drastic fluctuations in lateral acceleration due to abrupt changes in curvature. Finally, the optimized virtual lane line is used as the target smooth driving trajectory, making the curvature of the left and right lane lines as close as possible to each other.

[0032] Optionally, such as Figure 5As shown, the lane lines of the speed bump are defined by four key points: left entry point A, left exit point B, right entry point C, and right exit point D. Points A and B are smoothly connected based on the front and rear lane lines, as are points C and D, to form smooth virtual lane lines. Then, based on the curvature and confidence of the lane line connecting points C and D, the lane line connecting the new virtual points A and B is optimized for the same curvature. This also ensures that the curvature change of the virtual lane line when entering and leaving the target bumpy area matches the surrounding lane lines while maintaining the consistency of the overall path direction, avoiding drastic fluctuations in lateral acceleration caused by sudden changes in curvature. Finally, the optimized virtual lane line is used as the target smooth driving trajectory, making the curvature of the left and right lane lines as close as possible to each other.

[0033] Therefore, by integrating the geometric boundaries of the target bumpy area with the lane lines to generate and optimize the virtual lane lines, the problem of trajectory abrupt changes caused by lane line occlusion or distortion in the bumpy area is effectively solved. This ensures that the vehicle can still track a smooth and stable driving path with continuous curvature when passing through bumps, significantly improving the robustness of lateral control and ride comfort.

[0034] Step S103 includes the following aspects: Specifically, such as Figure 6 and Figure 7 As shown, after the intelligent driving system smooths the road surface, it still needs to perform wheel-end stabilization control on the steering system. When briefly passing through the target bumpy area, in addition to sending an angle control request, the intelligent driving system also sends a bump status flag and a torque request to the steering system based on the target bumpy area. After receiving the bump status flag, the steering system switches to bump control mode and applies additional compensation torque according to the torque request while responding to the angle request normally. The angle response is to achieve the driving trajectory of the intelligent driving system, and the torque response is to ensure the angle response while the steering system needs to simultaneously superimpose angle and torque control. Through torque compensation, the steering wheel control is stabilized, the adverse impact caused by road bumps is offset, and the expected steering wheel wobbling is reduced. Therefore, in addition to meeting the angle request of the intelligent driving system, this application also requires the steering system to apply an additional torque to overcome the fluctuations of mechanical transmission such as wheel ends, thereby reducing or avoiding unexpected wobbling of the steering wheel end. This ensures that when passing through the target bumpy area, the steering wheel only responds to the angle request of the intelligent driving system, thereby effectively solving the risk of the steering wheel wobbling causing the trajectory to be irregular in the target bumpy area.

[0035] Optionally, in one embodiment of this application, determining the target torque and target steering angle based on the vehicle's current speed, current driving trajectory, and target smooth driving trajectory includes: determining the vehicle's compensation torque based on the current speed, and determining the target torque based on the compensation torque and the vehicle's current torque; and determining the target steering angle based on the current driving trajectory and the target smooth driving trajectory.

[0036] Optionally, in one embodiment of this application, determining the vehicle's compensation torque based on the current vehicle speed includes: constructing a mapping relationship between the vehicle's driving speed and the compensation torque; and matching the compensation torque corresponding to the current vehicle speed based on the current vehicle speed and the mapping relationship.

[0037] Specifically, during the system development phase, a segmented mapping relationship table between vehicle speed and required compensation torque can first be established through real-vehicle road testing and simulation calibration. This mapping relationship is designed based on ergonomics and vehicle dynamics characteristics to ensure that steering wheel vibration can be effectively suppressed at different vehicle speeds without sacrificing steering lightness. The mapping relationship between vehicle speed and compensation torque is shown in Table 1. Table 1

[0038] In other words, when the autonomous driving system detects bumps on the road ahead, it changes the bump status flag from 0 to 1 when the vehicle is 10m away from the target bump area. At the same time, it sends a steering angle request and a compensation torque request to the steering system. Thus, while tracking the target steering angle request, it requests the application of compensation torque to suppress steering wheel disturbances caused by road impacts.

[0039] The compensation torque request is set according to the torque required by the current angle control closed loop and varies with vehicle speed. For example, when the vehicle speed is 0-20km / h, a compensation torque of 2Nm is requested; when the vehicle speed is 20-60km / h, a compensation torque of 1.5Nm is requested; and when the vehicle speed is 60-120km / h, a compensation torque of 1Nm is requested. The parameters can be calibrated on a real vehicle in combination with the steering wheel performance.

[0040] Therefore, during vehicle operation, the current vehicle speed is acquired in real time, and the compensation torque corresponding to the current vehicle speed is obtained based on the current vehicle speed and the above mapping relationship. Then, the current torque fed back by the steering system is acquired, and the compensation torque is superimposed or weighted and fused with the current torque to generate the final target torque.

[0041] Furthermore, this application calculates the deviations in lateral position, heading angle, and curvature between the current driving trajectory (i.e., the original planned trajectory before optimization) and the target smooth driving trajectory (the trajectory reconstructed by the virtual lane lines in the bumpy area), and inputs the deviations into the lateral tracking controller. Combining the vehicle's current pose, speed, and wheelbase parameters, it calculates in real time the target front wheel angle required to achieve a smooth transition from the current driving trajectory to the target smooth driving trajectory, and converts the target front wheel angle into the corresponding target steering wheel angle.

[0042] Furthermore, the target steering angle, target torque, and bump status flag obtained above are packaged into a complete lateral control command and sent to the steering system via the vehicle CAN bus. After receiving the lateral control command, the steering system performs lateral control on the vehicle according to the lateral control command. For example, during the period when the bump status flag is valid, the target steering angle is forced to be the main control command, and its priority is increased to suppress steering interference of the steering wheel. In addition, the target torque is superimposed on the motor torque output to form active damping, offset the reverse impact of the road surface, and continuously feed back the actual torque value for intelligent driving to perform closed-loop verification.

[0043] Therefore, by constructing a mapping relationship between vehicle speed and compensation torque, and dynamically determining the target steering angle and fusion torque by combining the current driving trajectory and the target smooth trajectory, adaptive feedforward compensation and precise steering control are achieved, effectively suppressing steering wheel vibration caused by bumps and improving lateral tracking stability and driving comfort.

[0044] Optionally, in one embodiment of this application, after lateral control of the vehicle according to the lateral control command, the method further includes: obtaining the driving distance of the vehicle after passing the target bumpy area; if the driving distance is greater than a preset distance, controlling the vehicle to maintain the original driving trajectory.

[0045] The preset distance can be based on the buffer length determined by actual vehicle calibration, and is used to ensure that the vehicle suspension system has completed the vibration attenuation after bumps and impacts.

[0046] Specifically, firstly, the system continuously monitors the distance the vehicle travels after passing the target bumpy area. Once both the front and rear wheels of the vehicle have passed the exit boundary of the target bumpy area (i.e., the rear wheels leave the target bumpy area), the system activates the exit timing module. Starting from the moment the rear wheels of the vehicle pass the exit, the system accumulates the longitudinal distance the vehicle continues to travel forward in real time. This distance can be obtained through wheel speed sensor integration, IMU (Inertial Measurement Unit) displacement estimation, or high-precision positioning data calculation.

[0047] Secondly, to determine whether the exit condition is met, the accumulated driving distance is compared with the preset distance (e.g., 5m). If the driving distance is greater than the preset distance, that is, the intelligent driving system sends the target smooth driving trajectory and road condition information to the steering system at a longitudinal distance (the closest point of the front bumper and the starting point of the bumpy road) of 10m. After the front and rear wheels have passed the target bumpy area for 5m, it is determined that the vehicle has stably driven away from the bumpy condition and the exit condition is met. At this time, the bumpy status flag is cleared and sent to the steering system via the CAN (Controller Area Network) bus. After receiving the bumpy status flag clearing signal, the steering system exits the forced tracking and torque compensation mode, restores the normal power steering logic, and controls the vehicle to maintain the original driving trajectory.

[0048] Therefore, by clearing the bump status flag after the vehicle has completely left the bumpy area and traveled a preset distance, the compensation control is ensured to exit only after the disturbance has been completely eliminated, avoiding secondary shaking caused by premature resumption of normal control, and achieving smooth and reliable mode switching and trajectory return.

[0049] The following is combined with Figure 8 Further explanation of the overall process of this application: Step S801: Output the vehicle's current driving trajectory based on sensor input, such as from cameras, lidar, etc. Step S802: Based on the sensory input, analyze the road surface condition ahead in advance, judge the road bump information in advance, identify the target bump area, and determine its geometric boundary. Step S803: Send the road bump status and compensation torque request to the steering system to trigger the steering system to enter a special control mode; In step S804, the road bump information and target torque are sent to the steering system, and the forced follow logic is fully responsive to the intelligent driving angle request to reduce road interference.

[0050] Therefore, in addition to considering the safety boundary of the driving trajectory, the autonomous vehicle of this application also improves the lateral control of the driving trajectory through road condition information, thereby achieving better lateral control. Under the intelligent driving activation function, the vehicle anticipates road perception in advance and applies motor torque in advance before passing through bumpy roads to stabilize the steering wheel. This makes the steering wheel performance smoother when the vehicle passes through bumpy roads, ultimately achieving smooth trajectory control and improving the vehicle's lateral control performance.

[0051] The lateral control method for vehicles proposed in this application obtains the road surface state information ahead of the vehicle; when a target bumpy area is identified based on the road surface state information ahead, a target smooth driving trajectory is generated based on the target bumpy area and the lane line where the vehicle is located; based on the vehicle's current speed, current driving trajectory, and target smooth driving trajectory, a target torque and a target steering angle are determined, and a lateral control command is generated based on the target torque and target steering angle to perform lateral control on the vehicle. By identifying the bumpy area ahead, the target smooth driving trajectory is generated by fusing the lane line and the geometric boundary of the bump, and the target steering angle and compensation torque are dynamically determined by combining the current speed and trajectory to generate the lateral control command. Thus, the vehicle can be controlled smoothly and seamlessly through the bumpy area based on the lateral control command, improving the comfort and safety of lateral control in autonomous driving. This solves the technical problems of steering wheel vibration, trajectory deviation, and lateral control instability caused by the lack of coordinated control of trajectory correction and torque compensation in autonomous driving systems on bumpy roads.

[0052] Next, with reference to the accompanying drawings, a lateral control device for a vehicle according to an embodiment of this application is described.

[0053] Figure 9 This is a block diagram of a vehicle lateral control device according to an embodiment of this application.

[0054] like Figure 9 As shown, the lateral control device 10 of the vehicle includes: an acquisition module 100, a generation module 200, and a control module 300.

[0055] The acquisition module 100 is used to acquire road surface condition information ahead of the vehicle. The generation module 200 is used to generate a smooth driving trajectory of the target based on the target bumpy area and the lane line where the vehicle is located, when the target bumpy area is identified based on the road surface condition information ahead. The control module 300 is used to determine the target torque and target steering angle based on the vehicle's current speed, current driving trajectory and target smooth driving trajectory, and to generate lateral control commands based on the target torque and target steering angle, so as to perform lateral control on the vehicle according to the lateral control commands.

[0056] Optionally, in one embodiment of this application, the generation module 200 includes: The generation unit is used to identify the geometric boundaries of the target bumpy area and generate virtual lane lines based on the intersection of the geometric boundaries of the target bumpy area and the lane lines where the vehicle is located. The optimization unit is used to optimize the virtual lane lines with the same curvature based on the curvature and confidence of adjacent lane lines to obtain the target smooth driving trajectory.

[0057] Optionally, in one embodiment of this application, the control module 300 includes: The first determining unit is used to determine the vehicle's compensation torque based on the current vehicle speed, and to determine the target torque based on the compensation torque and the vehicle's current torque. The second determining unit is used to determine the target steering angle based on the current driving trajectory and the target smooth driving trajectory.

[0058] Optionally, in one embodiment of this application, the first determining unit includes: Construct sub-units to establish the mapping relationship between vehicle speed and compensation torque; The matching subunit is used to match the compensation torque corresponding to the current vehicle speed based on the current vehicle speed and the mapping relationship.

[0059] Optionally, in one embodiment of this application, after lateral control of the vehicle is performed according to the lateral control command, the control module 300 further includes: The acquisition unit is used to acquire the distance traveled by the vehicle after it has passed through the target bumpy area; The control unit is used to control the vehicle to maintain its original driving trajectory if the travel distance exceeds a preset distance.

[0060] According to the vehicle lateral control device proposed in this application embodiment, the device acquires the road surface state information ahead of the vehicle; when a target bumpy area is identified based on the road surface state information ahead, a target smooth driving trajectory is generated based on the target bumpy area and the lane line where the vehicle is located; based on the vehicle's current speed, current driving trajectory, and target smooth driving trajectory, a target torque and a target steering angle are determined, and a lateral control command is generated based on the target torque and target steering angle to perform lateral control on the vehicle. By identifying the bumpy area ahead, the target smooth driving trajectory is generated by fusing the lane line and the geometric boundary of the bump, and the target steering angle and compensation torque are dynamically determined by combining the current speed and trajectory to generate the lateral control command. Thus, the vehicle can be controlled smoothly and smoothly through the bumpy area based on the lateral control command, improving the comfort and safety of autonomous driving lateral control. This solves the technical problems of steering wheel vibration, trajectory deviation, and lateral control instability caused by the lack of coordinated control of trajectory correction and torque compensation in related autonomous driving systems on bumpy roads.

[0061] This application also provides an electronic device 20, please refer to... Figure 10 It includes a processor 210 and a memory 220, wherein the memory 210 is used to store computer programs; the processor 220 is used to execute the programs stored in the memory 210 to implement the lateral control method of the vehicle described in any embodiment of this application.

[0062] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the lateral control method for a vehicle described in any embodiment of this application.

[0063] In this application, "multiple" refers to two or more.

[0064] In this application, unless otherwise expressly defined, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0065] The terms “first,” “second,” “third,” “fourth,” etc., in this application (if present) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0066] In this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, in this application, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0067] Unless otherwise specified, all steps in this application may be performed sequentially or randomly. For example, if a method includes steps A and B, it means that the method may include steps A and B performed sequentially, or it may include steps B and A performed sequentially. For example, if a method may also include step C, it means that step C may be added to the method in any order. For example, the method may include steps A, B, and C, or it may include steps A, C, and B, or it may include steps C, A, and B, etc.

[0068] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for lateral control of a vehicle, characterized in that, Includes the following steps: Obtain information about the road conditions ahead of the vehicle; If a target bumpy area is identified based on the road surface condition information ahead, a target smooth driving trajectory is generated according to the target bumpy area and the lane line where the vehicle is located. Based on the vehicle's current speed, current driving trajectory, and target smooth driving trajectory, a target torque and a target steering angle are determined, and a lateral control command is generated according to the target torque and the target steering angle to perform lateral control on the vehicle.

2. The method according to claim 1, characterized in that, The step of generating a target smooth driving trajectory based on the target bumpy area and the lane line where the vehicle is located includes: Identify the geometric boundaries of the target bumpy area, and generate a virtual lane line based on the intersection of the geometric boundaries of the target bumpy area and the lane line where the vehicle is located; Based on the curvature and confidence of adjacent lane lines, the virtual lane lines are optimized for the same curvature to obtain the target smooth driving trajectory.

3. The method according to claim 1, characterized in that, The determination of the target torque and target steering angle based on the vehicle's current speed, current driving trajectory, and the target smooth driving trajectory includes: Based on the current vehicle speed, the compensation torque of the vehicle is determined, and the target torque is determined based on the compensation torque and the current torque of the vehicle. The target steering angle is determined based on the current driving trajectory and the target smooth driving trajectory.

4. The method according to claim 3, characterized in that, Determining the compensation torque of the vehicle based on the current vehicle speed includes: Construct a mapping relationship between the vehicle's speed and the compensation torque; Based on the current vehicle speed and the mapping relationship, a compensation torque corresponding to the current vehicle speed is matched.

5. The method according to claim 1, characterized in that, After performing lateral control on the vehicle according to the lateral control command, the method further includes: Obtain the distance traveled by the vehicle after it has passed the target bumpy area; If the travel distance is greater than the preset distance, the vehicle is controlled to maintain its original travel trajectory.

6. A lateral control device for a vehicle, characterized in that, include: The acquisition module is used to acquire information about the road surface ahead of the vehicle. The generation module is used to generate a target smooth driving trajectory based on the target bumpy area and the lane line where the vehicle is located, when the target bumpy area is identified based on the road surface condition information ahead. The control module is used to determine the target torque and target steering angle based on the vehicle's current speed, current driving trajectory, and target smooth driving trajectory, and to generate lateral control commands based on the target torque and target steering angle, so as to perform lateral control on the vehicle according to the lateral control commands.

7. An electronic device, characterized in that, Including processor and memory, among which, Memory, used to store computer programs; A processor for executing a program stored in memory to implement the method described in any one of claims 1-5.

8. A vehicle, characterized in that, It includes the electronic device as described in claim 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-5.

Images