A method, apparatus, and medium for lane departure assist

Abstract

The application relates to the technical field of automatic driving, and discloses a lane departure assistance method, device and medium, which comprises the following steps: acquiring lane departure related information of a vehicle in a current driving environment in real time, wherein the lane departure related information comprises basic information and lateral information; the basic information comprises a preview distance, a self-vehicle trajectory model, a lane center line trajectory model and a current vehicle speed; the lateral information comprises a wheel offset and a vehicle lateral speed; when it is determined that the vehicle triggers a lane departure assistance function according to the lane departure related information, a compensation torque is calculated, and the compensation torque is outputted so as to compensate the torque of the vehicle under different lateral deviation speeds. Therefore, whether the lane departure assistance function is triggered is determined according to the lane departure related information, so that intelligent control of emergency lane keeping of the vehicle is realized; on this basis, the compensation torque is outputted to compensate and correct the torque of the vehicle, so that the vehicle can successfully correct the deviation under different lateral deviation speeds, and the driving safety of the vehicle is improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method, device and medium for lane departure assistance. Background Technology

[0002] Lane Departure Assistant (LDP) is a vehicle driving safety assistance system, while Electric Power Steering (EPS) is a power steering system that directly relies on an electric motor to provide auxiliary torque. When the driver unintentionally crosses lane markings without activating the turn signal, LDP issues a warning signal to alert the driver. Simultaneously, the EPS system provides power steering control with auxiliary torque to prevent the vehicle from deviating from its lane and causing a collision or traffic accident.

[0003] However, the current methods for switching from manual to automatic control to maintain lane keeping when a vehicle deviates from its lane are often not very intelligent, and the performance of LDP control varies greatly at different lateral deviation speeds. It often fails to correct the vehicle at high lateral deviation speeds, meaning it cannot meet the requirement of successfully correcting the vehicle at different lateral deviation speeds.

[0004] Therefore, when a vehicle deviates from its lane, how to improve the intelligence of the automatic control system for emergency lane keeping, meet the requirements for successful correction at different lateral deviation speeds, reduce the probability of the vehicle deviating from its lane, and improve vehicle driving safety and comfort are problems that urgently need to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, and medium for lane departure assistance, which improves the intelligence of switching from manual control to automatic control for emergency lane keeping when a vehicle deviates from its lane, meets the requirements for successful correction at different lateral deviation speeds, reduces the probability of the vehicle deviating from its lane, and improves vehicle driving safety and comfort.

[0006] To address the aforementioned technical problems, this application provides a lane departure assistance method, comprising:

[0007] The system acquires lane departure information related to the vehicle's current driving environment. The lane departure information includes basic information and lateral information. The basic information includes the aiming distance, the vehicle's trajectory model, the lane centerline trajectory model, and the current vehicle speed. The lateral information includes the wheelbase distance and the vehicle's lateral speed.

[0008] When it is determined that the vehicle has triggered the lane departure assist function based on the lane departure information, the compensation torque is calculated based on the lane departure information.

[0009] The compensation torque is output to compensate for the torque of the vehicle at different lateral deviation speeds.

[0010] Preferably, the compensation torque includes a far-end compensation torque, a near-end compensation torque, and a feedforward compensation torque; wherein the far-end compensation torque is the torque output by the PID far-end control, and the near-end compensation torque is the torque output by the PID near-end control.

[0011] Preferably, calculating the compensation torque based on the lane departure information includes:

[0012] Obtain the feedforward correlation coefficient and vehicle lateral acceleration;

[0013] The lateral angle deviation rate and lateral displacement deviation rate of the vehicle are determined based on the vehicle trajectory model and the lane centerline trajectory model.

[0014] The feedforward compensation torque is calculated based on the feedforward correlation coefficient and the lateral acceleration;

[0015] The distal compensation torque and the proximal compensation torque are calculated based on the pre-aiming distance, the rate of change of the lateral angle deviation, and the rate of change of the lateral displacement deviation.

[0016] Preferably, the compensation torque further includes wheel edge distance compensation torque and lateral speed compensation torque.

[0017] Preferably, calculating the compensation torque based on the lane departure information includes:

[0018] The curvature influence factor and speed influence factor are determined based on the wheel edge distance;

[0019] The correspondence between the vehicle's lateral velocity and the basic torque of the lateral velocity is established in advance;

[0020] After determining the total influence factor based on the curvature influence factor and the speed influence factor, the wheel edge distance compensation torque is calculated based on the total influence factor, and the lateral speed compensation torque is determined based on the corresponding relationship.

[0021] Preferably, determining whether the vehicle triggers the lane departure assist function based on the lane departure related information includes:

[0022] Determine whether the wheel edge distance at the pre-aiming point is greater than the wheel edge distance threshold, and whether the current vehicle speed is greater than the vehicle speed threshold;

[0023] If so, then it is determined that the vehicle has triggered the lane departure assist function.

[0024] To address the aforementioned technical problems, this application also provides a lane departure assist device, comprising:

[0025] The acquisition module is used to acquire lane departure information related to the current driving environment of the vehicle; wherein, the lane departure information related to the vehicle includes basic information and lateral information, the basic information includes the aiming distance, the vehicle trajectory model, the lane centerline trajectory model and the current vehicle speed, and the lateral information includes the wheel distance and the vehicle lateral speed;

[0026] The calculation module is used to calculate the compensation torque based on the lane departure information when it is determined that the vehicle has triggered the lane departure assist function.

[0027] The output module is used to output the compensation torque in order to compensate for the torque of the vehicle at different lateral deviation speeds.

[0028] To address the aforementioned technical problems, this application also provides a lane departure assist device, including a memory for storing a computer program;

[0029] A processor, used to implement the lane departure assistance method when executing the computer program.

[0030] To address the aforementioned technical problems, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the lane departure assistance method.

[0031] This invention provides a lane departure assist method, comprising: real-time acquisition of lane departure-related information in the current driving environment of the vehicle, wherein the lane departure-related information includes basic information and lateral information. The basic information includes the aiming distance, the vehicle's trajectory model, the lane centerline trajectory model, and the current vehicle speed; the lateral information includes the wheelbase and the vehicle's lateral speed. When it is determined that the vehicle will trigger the lane departure assist function based on the lane departure-related information, a compensation torque is calculated based on the lane departure-related information, and the compensation torque is output to compensate for the vehicle's torque at different lateral departure speeds. Therefore, the technical solution provided in this application determines whether to trigger the lane departure assist function based on the lane departure-related information, thereby achieving intelligent control of the vehicle's emergency lane keeping. Furthermore, by outputting compensation torque to compensate and correct the vehicle's torque, it ensures that the vehicle successfully corrects its course at different lateral departure speeds, reducing the probability of traffic accidents and thus improving vehicle driving safety while enhancing the user experience.

[0032] In addition, this application also provides a lane departure assist device and medium, which correspond to the lane departure assist method described above and have the same effect. Attached Figure Description

[0033] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 A flowchart illustrating a lane departure assistance method provided in an embodiment of this application;

[0035] Figure 2 This is a schematic diagram of a vehicle in motion provided as an embodiment of this application;

[0036] Figure 3(a) is a schematic diagram of a vehicle's lane departure assist function triggered on the outside of a curve, provided in an embodiment of this application.

[0037] Figure 3(b) is a schematic diagram of a vehicle's lane departure assist function triggered on the inside of a curve, provided in an embodiment of this application.

[0038] Figure 4 A structural diagram of a lane departure assist device provided in an embodiment of this application;

[0039] Figure 5 This is a structural diagram of a lane departure assist device provided in another embodiment of this application. Detailed Implementation

[0040] 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, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0041] The core of this application is to provide a method, device, and medium for lane departure assistance, which improves the intelligence of switching from manual control to automatic control for emergency lane keeping when a vehicle deviates from its lane, meets the requirements for successful correction at different lateral deviation speeds, reduces the probability of the vehicle deviating from its lane, and improves vehicle driving safety and comfort.

[0042] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] LDP (Lane Deployment Device) is a driver assistance system, while EPS (Electric Power Steering) is a power steering system that directly relies on an electric motor to provide auxiliary torque. When the driver does not activate the turn signal and unintentionally drives the vehicle across lane markings, LDP issues a warning signal to alert the driver. Simultaneously, the EPS system provides power steering control with auxiliary torque to prevent the vehicle from veering out of its lane and causing a collision or traffic accident.

[0044] However, the current methods for switching from manual to automatic control to maintain lane keeping when a vehicle deviates from its lane are often not very intelligent, and the performance of LDP control varies greatly at different lateral deviation speeds. It often fails to correct the vehicle at high lateral deviation speeds, meaning it cannot meet the requirement of successfully correcting the vehicle at different lateral deviation speeds.

[0045] To address the aforementioned technical issues and ensure the intelligent transition from manual to automatic control for emergency lane keeping when a vehicle deviates from its lane, thereby meeting the requirements for successful lane correction at different lateral deviation speeds, reducing the probability of lane departure, and improving vehicle driving safety and comfort, this application provides a lane departure assistance method. When determining the lane departure assistance function for the departing vehicle based on lane departure information, a compensation torque is calculated and output to compensate for the vehicle's torque, thus achieving successful lane correction at different lateral deviation speeds and improving vehicle driving safety.

[0046] Figure 1 A flowchart of a lane departure assistance method provided in an embodiment of this application is shown below. Figure 1 As shown, the method includes:

[0047] S10: Obtain lane departure information in the current driving environment of the vehicle; among which, lane departure information includes basic information and lateral information. The basic information includes the aiming distance, the vehicle trajectory model, the lane centerline trajectory model and the current vehicle speed. The lateral information includes the wheel distance and the vehicle lateral speed.

[0048] In a specific embodiment, when a vehicle tends to deviate from its lane, lane deviation-related information of the vehicle under the current driving environment is acquired in real time. The lane deviation-related information includes basic information and lateral information. The basic information includes the aiming distance, the vehicle trajectory model, the lane centerline trajectory model, and the current vehicle speed. The lateral information includes the wheel distance and the vehicle's lateral speed.

[0049] It should be noted that the aiming distance is the distance between the aiming point and the vehicle's center of gravity. The aiming point refers to the distance between the aiming point and the vehicle's center of gravity. Automatic vehicle control is divided into longitudinal and lateral control based on direction. Lateral control mainly controls the vehicle's direction of travel, ensuring the vehicle automatically stays near the center of the lane. In lateral control research, the vehicle is considered equivalent to a point mass at its center of gravity. While ensuring the point mass is near the lane center, controlling the moving vehicle based solely on the current vehicle-road position results in a delay in the vehicle's performance and poor control effectiveness. Therefore, it is necessary to anticipate the vehicle's movement. Thus, a point is selected ahead of the vehicle to replace the vehicle's point mass, and this point is controlled to stay in the lane center to improve control effectiveness. This selected point ahead of the vehicle is the aiming point.

[0050] In addition, the wheel-side distance is the distance between the edge of the vehicle's front wheel and the inside of the left / right lane line.

[0051] S11: When it is determined that the vehicle has triggered the lane departure assist function based on lane departure information, the compensation torque is calculated based on the lane departure information.

[0052] After obtaining the wheel track distance and current vehicle speed, if the wheel track distance is greater than the wheel track distance threshold and the current vehicle speed is greater than the vehicle speed threshold, then the vehicle is activated to initiate lane departure warning. At this point, compensation torque is calculated to compensate for the vehicle's torque.

[0053] The compensation torque includes far-end compensation torque, near-end compensation torque, feedforward compensation torque, wheel-side distance compensation torque, and lateral speed compensation torque. In fact, the far-end compensation torque, near-end compensation torque, and feedforward compensation torque are the vehicle's basic compensation torques. Compensation with the basic compensation torque can correct lane departures. However, at high lateral departure speeds, the basic compensation torque may fail to correct lane departures. Therefore, in addition to the basic compensation torque, wheel-side distance compensation torque and lateral speed compensation torque are added to ensure successful lane departure correction at different lateral speeds.

[0054] It should be noted that vehicle PID control includes both remote control and local control. Remote control refers to control at the aiming point, while local control refers to control at the front position of the vehicle. Therefore, remote compensation torque refers to the torque output by the PID remote control, and local compensation torque refers to the torque output by the PID local control.

[0055] When calculating the far-end compensation torque and the near-end compensation torque, the lateral angle deviation change rate and the lateral displacement deviation change rate of the vehicle are determined based on the aiming distance, the vehicle trajectory model, and the lane centerline trajectory model. Then, the far-end compensation torque is calculated based on the lateral angle deviation change rate, and the near-end compensation torque is calculated based on the lateral displacement deviation change rate.

[0056] Furthermore, the feedforward correlation coefficient and vehicle lateral acceleration in the automatic vehicle control are obtained, and the feedforward compensation torque is calculated based on the feedforward correlation coefficient and vehicle lateral acceleration.

[0057] To ensure successful lane correction for vehicles deviating from their lanes under different wheel-side distances and lateral speeds, wheel-side distance compensation torque and lateral speed compensation torque are introduced. Wheel-side distance compensation torque refers to torque compensation based on different wheel-side distances, while lateral speed compensation torque refers to torque compensation under different lateral deviation speeds.

[0058] During implementation, the vehicle's speed influence factor and curvature influence factor are acquired, and a pre-established correspondence between the vehicle's lateral speed and the basic lateral speed torque is established. Then, the total influence factor is determined based on the speed influence factor and curvature influence factor, and the wheel-side distance compensation torque is calculated based on the total influence factor. Simultaneously, after determining the vehicle's current lateral speed, the lateral speed compensation torque is determined according to the pre-established correspondence.

[0059] S12: Outputs compensation torque to compensate for torque loss at different lateral deviation speeds of the vehicle.

[0060] After obtaining the compensation torque in step S11, the compensation torque is output to compensate the vehicle's torque. Thus, based on the torque control of the far-end compensation torque, near-end compensation torque, and feedforward compensation torque, the wheel-side distance compensation torque and lateral speed compensation torque are introduced for torque control, so as to successfully correct the vehicle's deviation at different lateral deviation speeds.

[0061] The lane departure assist method provided in this application includes: real-time acquisition of lane departure-related information in the current driving environment of the vehicle. This information includes basic information and lateral information. The basic information includes the aiming distance, the vehicle's trajectory model, the lane centerline trajectory model, and the current vehicle speed. The lateral information includes the wheelbase and the vehicle's lateral speed. When it is determined that the vehicle is triggering the lane departure assist function based on this information, a compensation torque is calculated and output to compensate for torque at different lateral departure speeds. Therefore, the technical solution provided in this application determines whether to trigger the lane departure assist function based on lane departure-related information, thereby achieving intelligent control of emergency lane keeping. Furthermore, by outputting compensation torque to compensate and correct the vehicle's torque, it ensures successful lane correction at different lateral departure speeds, reducing the probability of traffic accidents and improving both vehicle driving safety and user experience.

[0062] In a specific embodiment, the vehicle is equipped with devices such as cameras and radar sensors, which can collect lane line information in the vehicle's driving environment. When obtaining the preview distance, the preview time and the vehicle's longitudinal speed are first determined, and then the preview distance is calculated using the formula d_predit = v * t_predit, where d_predit is the preview distance, v is the longitudinal speed, and t_predit is the preview time.

[0063] Lane departure information also includes the vehicle trajectory model and the lane centerline trajectory model. In practice, the steering wheel angle is calculated using the Ackermann angle formula to obtain the vehicle trajectory model, and the vehicle trajectory model is dyactual=1 / 2*C0*(d_predit)2, where C0 is the lane line curvature at the current position of the vehicle.

[0064] The lane centerline trajectory model is dytarget=C1+C2*d_predit+1 / 2C0*(d_predit)2+1 / 6C3*(d_predit)3, where C1 is the distance between the lane line and the rear axle center of the vehicle at the current position, C2 is the heading angle of the lane line at the current position of the vehicle, and C3 is the rate of change of curvature of the lane line at the current position of the vehicle.

[0065] Figure 2 This application provides a schematic diagram of a vehicle driving, as shown in the embodiment of the present application. Figure 2 As shown, D1 is the left wheelbase distance, D2 is the general width of the vehicle, D3 is the lateral offset at the aiming point, D4 is the distance from the center of the rear axle to the left lane line, and D5 is the aiming distance. In practice, wheelbase distance includes the left wheelbase distance and the right wheelbase distance, and the calculation formulas for the left wheelbase distance and the right wheelbase distance are as follows:

[0066] dlc_left=y_leftLine(d_predit)-y_egotrajectory(d_predit)-vehWidth / 2;

[0067] dlc_right=y_rightLine(d_predit)-y_egotrajectory(d_predit)-vehWidth / 2.

[0068] Wherein, dlc_left is the left wheelbase distance, which is the distance from the two front wheels of the vehicle at the aiming point to the left lane line. dlc_right is the right wheelbase distance, which is the distance from the two front wheels of the vehicle at the aiming point to the right lane line. y_leftLine(d_predit) is the distance of the left lane line from the aiming point relative to the center of the vehicle's rear axle, y_rightLine(d_predit) is the distance of the right lane line from the aiming point relative to the center of the vehicle's rear axle, y_egotrajectory(d_predit) is the distance of the vehicle's trajectory from the aiming point relative to the center of the vehicle's rear axle, and vehWidth is the vehicle width.

[0069] The lane departure assist method provided in this application obtains lane departure related information such as the aiming distance, the vehicle trajectory model, the lane centerline trajectory model, the wheel distance, and the current vehicle speed. Based on the lane departure related information, it determines whether the vehicle should trigger the lane departure assist function and activates the lane departure assist function at the triggering time to assist the vehicle in correcting its course, avoid the vehicle deviating from the lane and causing traffic accidents and other dangers, thereby improving vehicle driving safety.

[0070] It is understandable that although triggering the lane departure assist function can help correct the vehicle's deviation from the lane to a certain extent, when the measured deviation speed of the vehicle is large, the torque provided by triggering the lane departure assist function is difficult to successfully correct the deviation. Therefore, the technical solution provided in this application outputs different compensation torques to compensate when the vehicle deviates from the lane, so as to achieve correction at different lateral deviation speeds.

[0071] The compensation torque includes far-end compensation torque, near-end compensation torque, and feedforward compensation torque. Far-end and near-end compensation torques constitute the feedback compensation torque. PID control is divided into far-end control and near-end control; therefore, the far-end compensation torque is the torque output by the PID far-end control, and the near-end compensation torque is the torque output by the PID near-end control. Based on the above embodiments, the calculation of far-end compensation torque, near-end compensation torque, and feedforward compensation torque will be explained in detail below.

[0072] (1) When calculating the far-end compensation torque, first calculate the difference in lateral displacement between the lane centerline trajectory model and the vehicle trajectory model at the target point, namely: dynear=dytarget-dyactual.

[0073] The lateral angle deviation at the far-end aiming point is:

[0074] headingAngleDifffar=arctan[(dytarget-dyactual) / d_predit];

[0075] Where headingAngleDifffar is the lateral angle deviation and d_predit is the aiming distance.

[0076] The rate of change of lateral angle deviation is:

[0077] headingAngleDiffrate = (headingAngleDifffar_k1 - headingAngleDifffar_k0) / t, where headingAngleDiffrate is the rate of change of the lateral angle deviation, headingAngleDifffar_k1 is the lateral angle deviation value at the current moment, headingAngleDifffar_k0 is the lateral angle deviation value at the previous moment, and t is the sampling period.

[0078] Therefore, we can obtain the different output components in PID remote control:

[0079] LDPtorqueFarp=Kp*Gainfactorfarp*headingAngleDifffar;

[0080] LDPtorqueFari=Ki*Gainfactorfari*headingAngleDifffar*dt;

[0081] LDPtorqueFard=Kd*Gainfactorfard*headingAngleDiffrate;

[0082] Wherein, LDPtorqueFarp is the remote proportional control output component, LDPtorqueFari is the remote integral control output component, LDPtorqueFard is the remote derivative control output component, Kp is the basic proportional gain coefficient, Ki is the basic integral gain coefficient, and Kd is the basic derivative gain coefficient.

[0083] Gainfactorfarp=farRadiusfactorkp*farSpeedfactorkp*farHandTqfactorkp*farh readingangleDifffactorkp;

[0084] Gainfactorfari=farRadiusfactorki*farSpeedfactorki*farHandTqfactorkp*farhe adingangleDifffactorki;

[0085] Gainfactorfard=farRadiusfactorki*farSpeedfactorkd*farHandTqfactorkd*farh readingangleDiffRatefactorkd;

[0086] Where farRadiusfactorkp is the radius component corresponding to the far-end proportional gain coefficient, farSpeedfactorkp is the speed component corresponding to the far-end proportional gain coefficient, farHandTqfactorkp is the driver's hand torque component corresponding to the far-end proportional gain coefficient, and farheadingangleDifffactorkp is the deviation component corresponding to the far-end proportional gain coefficient.

[0087] farRadiusfactorki is the radius component corresponding to the far-end integral gain coefficient, farSpeedfactorki is the velocity component corresponding to the far-end integral gain coefficient, and farheadingangleDifffactorki is the deviation component corresponding to the far-end proportional gain coefficient.

[0088] farSpeedfactorkd represents the velocity component corresponding to the far-end differential gain coefficient, and farHandTqfactorkd represents the driver's hand torque component corresponding to the far-end differential gain coefficient.

[0089] farheadingangleDiffRatefactorkd is the deviation component corresponding to the far-heading differential gain coefficient.

[0090] Gainfactorfarp is the product of the proportional gain coefficients at the far end, Gainfactorfari is the product of the integral gain coefficients at the far end, and Gainfactorfard is the product of the differential gain coefficients at the far end.

[0091] This allows us to obtain the far-end compensation torque:

[0092] trqFarCtrl = LDPtorqueFarp + LDPtorqueFari + LDPtorqueFard, where trqFarCtrl is the far-end compensation torque.

[0093] (2) When calculating the near-end compensation torque, the difference in lateral displacement of the vehicle is first determined based on the lane centerline trajectory model and the vehicle trajectory model, i.e., dynear=dytarget-dyactual. Then, the rate of change of lateral displacement deviation is determined: dyneardt=(dynear_k1-dynear_k0) / t, where dynear_k1 is the lateral displacement deviation value at the current moment, dynear_k0 is the lateral displacement deviation value at the previous moment, and t is the sampling period.

[0094] Therefore, we can obtain the different output components in PID proximal control:

[0095] LDPtorquenearp=Kp*Gainfactornearp*dynear;

[0096] LDPtorqueneard=Kd*Gainfactorneari*dyneardt;

[0097] LDPtorqueneari=Ki*Gainfactornear*dynear*dt;

[0098] Wherein, LDPtorquenearp is the proximal proportional control output component, LDPtorqueneard is the proximal derivative control output component, and LDPtorqueneari is the proximal integral control output component.

[0099] Gainfactornearp=nearRadiusfactorkp*nearSpeedfactorkp*nearHandTqfactork p*dynearfactorkp;

[0100] Gainfactorneari=nearRadiusfactorki*nearSpeedfactorki*nearHandTqfactorkp*dynearfactorki;

[0101] Gainfactorneard=nearRadiusfactorki*nearSpeedfactorkd*nearHandTqfactork d*dynearfactorkd;

[0102] Where nearRadiusfactorkp is the radius component corresponding to the near-end proportional gain coefficient, nearSpeedfactorkp is the speed component corresponding to the near-end proportional gain coefficient, nearHandTqfactorkp is the driver's hand torque component corresponding to the near-end proportional gain coefficient, and dynearfactorkp is the deviation component corresponding to the near-end proportional gain coefficient.

[0103] nearRadiusfactorki is the radius component corresponding to the near-end integral gain coefficient, nearSpeedfactorki is the velocity component corresponding to the near-end integral gain coefficient, and dynearfactorki is the deviation component corresponding to the near-end integral gain coefficient.

[0104] nearSpeedfactorkd is the velocity component corresponding to the near-end differential gain coefficient, nearHandTqfactorkd is the driver's hand torque component corresponding to the near-end differential gain coefficient, and dynearfactorkd is the deviation component corresponding to the near-end differential gain coefficient.

[0105] Gainfactornearp is the product of the proportional gain coefficients at the near end, Gainfactorneari is the product of the integral gain coefficients at the near end, and Gainfactorneard is the product of the differential gain coefficients at the near end.

[0106] Therefore, the proximal compensation torque can be obtained as follows:

[0107] trqNearCtrl = LDPtorquenearp + LDPtorqueneard + LDPtorqueneari, where trqNearCtrl is the near-end compensation torque.

[0108] (3) The basic principle for calculating the feedforward compensation torque is to multiply the feedforward correlation coefficient by the vehicle's lateral acceleration, i.e., K*a. Where K is the feedforward correlation coefficient, a is the lateral acceleration, and a = v² * m_curvaturePred_F, v is the longitudinal vehicle speed, and m_curvaturePred_F is the curvature at the aiming point. K = kFeedFwdCtrl * (1 ± dynear * kDYFeedFwdCtrl_F)

[0109] *KfwdSpeedFactorK_F*KfwdRadiusFactorK_F*KfwdCurvatureDer_F, where trqFeedFwdCtrl_f is the feedforward compensation torque, kFeedFwdCtrl is the basic feedforward coefficient, dynear is the proximal lateral displacement, kDYFeedFwdCtrl_F is the feedforward adjustment coefficient, KfwdSpeedFactorK_F is the speed relationship factor corresponding to the feedforward, KfwdRadiusFactorK_F is the radius correlation factor corresponding to the feedforward, and KfwdCurvatureDer_F is the factor of the rate of change of lane curvature corresponding to the feedforward.

[0110] In summary, the formula for calculating the feedforward compensation torque is as follows:

[0111] trqFeedFwdCtrl_F=kFeedFwdCtrl*(1±dynear*kDYFeedFwdCtrl_F)

[0112] *KfwdSpeedFactorK_F*KfwdRadiusFactorK_F*KfwdCurvatureDer_F*v2

[0113] *m_curvaturePred_F, where trqFeedFwdCtrl_F is the feedforward compensation torque.

[0114] The lane departure assist method provided in this application calculates a basic compensation torque, namely, a far-end compensation torque, a near-end compensation torque, and a feedforward compensation torque. When the vehicle deviates from the lane, the basic compensation torque is output to compensate, so as to provide an appropriate torque to correct the vehicle's deviation from the lane, so that the vehicle can drive smoothly in the lane, improve the driving comfort of the vehicle, and improve the overall safety.

[0115] As a preferred embodiment, considering that the torque required by the vehicle varies at different lateral deviation speeds, when the lateral deviation speed is high, relying solely on the basic compensation torque may fail to successfully correct the vehicle's deviation from the lane. Therefore, the technical solution provided in this application also introduces wheel-side distance compensation torque and lateral speed compensation torque.

[0116] It is understandable that the required torque varies depending on the wheelbase and lateral speed. Therefore, based on these two influencing factors, the compensation torque is further modified and optimized. The calculation methods for wheelbase compensation torque and lateral speed compensation torque will be explained in detail below.

[0117] (1) Calculation of wheel edge distance compensation torque

[0118] Considering the difference in EPS assist at high and low vehicle speeds, a relationship table can be pre-established based on past experience, relating vehicle speed (PidSpeedAdapt) to the speed influence factor (DLCSpeedFactor) at different vehicle speeds. Here, DLCSpeedFactor represents the wheelbase coefficient at different vehicle speeds. Furthermore, this relationship table can be used to determine the corresponding DLCSpeedFactor for different speed influence factors. Specifically, the current vehicle speed (PidSpeedAdapt) is obtained, and the corresponding DLCSpeedFactor is found in the relationship table.

[0119] Figure 3(a) is a schematic diagram of a vehicle triggering lane departure assist function on the outside of a curve according to an embodiment of this application, and Figure 3(b) is a schematic diagram of a vehicle triggering lane departure assist function on the inside of a curve according to an embodiment of this application. As shown in Figures 3(a) and 3(b), the vehicle triggers the lane departure assist function on the outside and inside of the curve, respectively. In implementation, the curvature influence factor is one of the factors affecting the calculation of wheelbase compensation torque. It is preset that the curvature direction is positive when it is to the left and negative when it is to the right. When the vehicle is to the left of the lane centerline, the lateral displacement of the vehicle is positive, and when it is to the right of the lane centerline, the lateral displacement of the vehicle is negative. Therefore, when the product of curvature and lateral displacement is greater than 0, the vehicle is located on the outside of the curve, and when the product of curvature and lateral displacement is less than 0, the vehicle is located on the inside of the curve.

[0120] Furthermore, after determining whether the vehicle is located on the inside or outside of the curve, based on the curvature influence factor, a pre-established correspondence is created between the lane line radius PidRadiusAdapt, the inner adjustment factor DLCRadiusInnerFactor corresponding to the wheelbase, and the outer adjustment factor DLCRadiusoutterFactor corresponding to the wheelbase. Then, the lane line radius PidRadiusAdapt under the vehicle's current driving environment is obtained, and the corresponding inner adjustment factor DLCRadiusInnerFactor or outer adjustment factor DLCRadiusoutterFactor corresponding to the wheelbase is found in the pre-established correspondence.

[0121] Therefore, by multiplying the speed influence factor DLCSpeedFactor by the inner adjustment factor DLCRadiusInnerFactor corresponding to the wheel edge distance, or by multiplying the speed influence factor DLCSpeedFactor by the outer adjustment factor DLCRadiusoutterFactor corresponding to the wheel edge distance, the total influence factor DLCTorqueGainfactor for wheel edge distance compensation torque can be obtained. The calculation formula is as follows:

[0122] DLCTorqueGainfactor=DLCSpeedFactor*DLCRadiusInnerFactor;

[0123] Or DLCTorqueGainfactor=DLCSpeedFactor*DLCRradiusoutterFactor;

[0124] Furthermore, a correspondence is pre-established between the wheel edge distance DLCLdpAdapt and the wheel edge distance base torque TrqDLCLdp. When the current wheel edge distance DLCLdpAdapt is obtained, the corresponding wheel edge distance base torque TrqDLCLdp is found based on this correspondence.

[0125] Finally, the wheel edge compensation torque is calculated based on the total influence factor DLCTortueGainfactor and the wheel edge distance base torque TrqDLCLdp. The calculation formula is as follows:

[0126] TrqDLCLdp_output=DLCTorqueGainfactor*TrqDLCLdp;

[0127] Where TrqDLCLdp_output is the wheel edge distance compensation torque.

[0128] (2) Calculation of lateral velocity compensation torque

[0129] Based on experience, a correspondence is pre-established between the vehicle's lateral speed DLCdtAdapt and the lateral speed base torque DLCdtLdpTorque. When the vehicle's lateral speed DLCdtAdapt is obtained, the corresponding lateral speed base torque DLCdtLdpTorque is directly retrieved from this correspondence as the lateral speed compensation torque DLCdtTorque.

[0130] The formula for calculating the lateral velocity is: DLCdt=(DLC_k1-DLC_k0) / T, where DLCdt is the lateral velocity of the vehicle, DLC_k1 is the wheel edge distance at the current moment, DLC_k0 is the wheel edge distance at the previous moment, and T is the duration between the previous moment and the current moment.

[0131] Therefore, based on the above embodiments, the compensation torque includes far-end compensation torque, near-end compensation torque, feedforward compensation torque, wheel-side distance compensation torque, and lateral speed compensation torque, thus yielding the total compensation torque, namely:

[0132] trqControl = trqFarCtrl + trqNearCtrl + trqFeedFwdCtrl_F + TrqDLCLdp_output + DLCdtTorque, where trqControl is the compensation torque, trqFarCtrl is the far-end compensation torque, trqNearCtrl is the near-end compensation torque, trqFeedFwdCtrl_F is the feedforward compensation torque, TrqDLCLdp_output is the wheel-side distance compensation torque, and DLCdtTorque is the lateral speed compensation torque.

[0133] The lane departure assist method provided in this application, based on the basic compensation torque, adds wheel edge distance compensation torque and lateral speed compensation torque. This technical solution can adapt to successful correction at different lateral departure speeds, avoiding large differences in the correction performance of the lane departure assist function at different lateral departure speeds, which would lead to failure to correct at high lateral departure speeds. This further improves the probability of successful vehicle correction, enhances vehicle driving safety and reliability, and ultimately improves the user experience.

[0134] In a specific embodiment, after obtaining lane departure information related to the current driving environment of the vehicle, if it is determined that the vehicle has triggered the lane departure assist function based on the lane departure information, and if it is determined that the wheel distance at the pre-aiming point is greater than the wheel distance threshold and the current vehicle speed is greater than the vehicle speed threshold, then it is determined that the vehicle has triggered the lane departure assist function.

[0135] In fact, when determining whether a vehicle has triggered the lane departure assist function based on lane departure information, the judgment can also be made based on information such as the pre-collision time, pre-collision distance, and whether the edge of the current lane is the side of the road. This application does not make specific limitations on this.

[0136] The lane departure assist method provided in this application determines when the vehicle triggers the lane departure assist function based on lane departure-related information, and then activates the lane departure assist function to improve the intelligence of switching from manual control to automatic control for emergency lane keeping, thereby reducing the probability of the vehicle deviating from the lane and improving vehicle driving safety and comfort.

[0137] In the above embodiments, the method for lane departure assistance has been described in detail. This application also provides an embodiment corresponding to a lane departure assistance device. It should be noted that this application describes the embodiment of the device from two perspectives: one is based on the functional modules, and the other is based on the hardware structure.

[0138] Figure 4 A structural diagram of a lane departure assist device provided in an embodiment of this application is shown below. Figure 4 As shown, the device includes:

[0139] The acquisition module 10 is used to acquire lane departure information related to the current driving environment of the vehicle; wherein, the lane departure information includes basic information and lateral information, the basic information includes the aiming distance, the vehicle trajectory model, the lane centerline trajectory model and the current vehicle speed, and the lateral information includes the wheel edge distance and the vehicle lateral speed.

[0140] The calculation module 11 is used to calculate the compensation torque based on the lane departure information when it is determined that the vehicle has triggered the lane departure assist function.

[0141] Output module 12 is used to output compensation torque in order to compensate for torque at different lateral deviation speeds of the vehicle.

[0142] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.

[0143] The lane departure assist device provided in this application includes: real-time acquisition of lane departure-related information in the current driving environment of the vehicle. The lane departure-related information includes basic information and lateral information. The basic information includes the aiming distance, the vehicle's trajectory model, the lane centerline trajectory model, and the current vehicle speed. The lateral information includes the wheelbase and the vehicle's lateral speed. When it is determined that the vehicle will trigger the lane departure assist function based on the lane departure-related information, a compensation torque is calculated based on the lane departure-related information, and the compensation torque is output to compensate for the vehicle's torque at different lateral departure speeds. Therefore, the technical solution provided in this application determines whether to trigger the lane departure assist function based on the lane departure-related information, thereby achieving intelligent control of the vehicle's emergency lane keeping. Furthermore, by outputting compensation torque to compensate and correct the vehicle's torque, it ensures that the vehicle successfully corrects its course at different lateral departure speeds, reducing the probability of traffic accidents and improving both vehicle driving safety and user experience.

[0144] Figure 5 A structural diagram of a lane departure assist device provided in another embodiment of this application is shown below. Figure 5 As shown, the lane departure assist device includes: a memory 20 for storing a computer program;

[0145] The processor 21 is configured to execute a computer program to implement the steps of the lane departure assistance method as described in the above embodiments.

[0146] The lane departure assist device provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, or desktop computers.

[0147] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an Artificial Intelligence (AI) processor, which is used to handle computational operations related to machine learning.

[0148] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, after being loaded and executed by the processor 21, is capable of implementing the relevant steps of the lane departure assistance method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, and the storage method may be temporary or permanent storage. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, relevant data involved in the lane departure assistance method.

[0149] In some embodiments, the lane departure assist device may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0150] Those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the lane departure assist device and may include more or fewer components than shown.

[0151] The lane departure assist device provided in this application includes a memory and a processor. When the processor executes the program stored in the memory, it can implement the following method: a lane departure assist method.

[0152] The lane departure assist device provided in this application determines whether to trigger the lane departure assist function based on lane departure related information, thereby realizing intelligent control of emergency lane keeping of the vehicle. On this basis, it ensures that the vehicle can successfully correct its course at different lateral deviation speeds by outputting compensation torque, reducing the probability of traffic accidents and thus improving vehicle driving safety and user experience.

[0153] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above method embodiments.

[0154] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, 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 storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0155] The foregoing has provided a detailed description of a lane departure assistance method, apparatus, and medium provided in this application. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0156] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method of lane departure assist, characterized by, include: The system acquires lane departure information related to the vehicle's current driving environment. The lane departure information includes basic information and lateral information. The basic information includes the aiming distance, the vehicle's trajectory model, the lane centerline trajectory model, and the current vehicle speed. The lateral information includes the wheelbase distance and the vehicle's lateral speed. When it is determined that the vehicle has triggered the lane departure assist function based on the lane departure information, the compensation torque is calculated based on the lane departure information. The compensation torque is output to compensate for the torque of the vehicle at different lateral deviation speeds; The compensation torque includes lateral velocity compensation torque; The calculation of compensation torque based on the lane departure information includes: The correspondence between the vehicle's lateral velocity and the basic torque of the lateral velocity is established in advance; The lateral velocity compensation torque is determined based on the aforementioned correspondence.

2. The method of lane departure assist according to claim 1, characterized in that The compensation torque includes remote compensation torque, near-end compensation torque, and feedforward compensation torque; wherein, the remote compensation torque is the torque output by the PID remote control, and the near-end compensation torque is the torque output by the PID near-end control.

3. The method of lane departure assist according to claim 2, characterized in that The calculation of compensation torque based on the lane departure information includes: Obtain the feedforward correlation coefficient and vehicle lateral acceleration; The lateral angle deviation rate and lateral displacement deviation rate of the vehicle are determined based on the vehicle trajectory model and the lane centerline trajectory model. The feedforward compensation torque is calculated based on the feedforward correlation coefficient and the lateral acceleration; The distal compensation torque and the proximal compensation torque are calculated based on the pre-aiming distance, the rate of change of the lateral angle deviation, and the rate of change of the lateral displacement deviation.

4. The method of lane departure assist according to claim 2, characterized in that The compensation torque also includes wheel edge distance compensation torque.

5. The lane departure assistance method according to claim 4, characterized in that, The calculation of compensation torque based on the lane departure information includes: The curvature influence factor and speed influence factor are determined based on the wheel edge distance; After determining the total influence factor based on the curvature influence factor and the speed influence factor, the wheel edge distance compensation torque is calculated based on the total influence factor.

6. The lane departure assistance method according to claim 2, characterized in that, Determining whether the vehicle triggers the lane departure assist function based on the lane departure information includes: Determine whether the wheel edge distance at the pre-aiming point is greater than the wheel edge distance threshold, and whether the current vehicle speed is greater than the vehicle speed threshold; If so, then it is determined that the vehicle has triggered the lane departure assist function.

7. A lane departure assist device, characterized in that, include: The acquisition module is used to acquire lane departure information related to the current driving environment of the vehicle; wherein, the lane departure information related to the vehicle includes basic information and lateral information, the basic information includes the aiming distance, the vehicle trajectory model, the lane centerline trajectory model and the current vehicle speed, and the lateral information includes the wheel distance and the vehicle lateral speed; The calculation module is used to calculate the compensation torque based on the lane departure information when it is determined that the vehicle has triggered the lane departure assist function. The output module is used to output the compensation torque in order to perform torque compensation for the vehicle at different lateral deviation speeds. The compensation torque includes lateral velocity compensation torque; The calculation of compensation torque based on the lane departure information includes: The correspondence between the vehicle's lateral velocity and the basic torque of the lateral velocity is established in advance; The lateral velocity compensation torque is determined based on the aforementioned correspondence.

8. A lane departure assist device, characterized in that, Includes memory used to store computer programs; A processor, configured to implement the steps of the lane departure assistance method as described in any one of claims 1 to 6 when executing the computer program.

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 steps of the lane departure assistance method as described in any one of claims 1 to 6.

Images