A vehicle deviation correction method, device, equipment and medium in the case of an obstacle

Abstract

The present invention discloses a vehicle deviation correction method, device, equipment and medium in the case of obstacles, which relates to the field of autonomous driving. The method includes real-time detection of whether there is an obstacle target at the front edge of the current lane, and when there is an obstacle target, the identified lane line of the current lane is translated in the opposite direction of the obstacle target; based on the existence of the obstacle target on one side of the lane line translation direction, and the translated lane line, the LDW triggering condition and the LKA trajectory generation condition are reconstructed to achieve vehicle deviation correction. The application can improve the driving performance and experience of the overall assisted driving and ensure driving safety.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and specifically to a method, device, equipment and medium for correcting vehicle deviation in the event of an obstacle. Background Art

[0002] The LKA (Lane Keeping Assist) system and the LDW (Lane Departure Warning) system are common functions in ADAS (Advanced Driving Assistance System). The vehicle uses a camera to identify the driving lane line while driving to keep the vehicle in the lane and driving normally. If the vehicle approaches the lane line, the LDW system vibrates the steering wheel or reminds the driver with a sound. If necessary, the LKA system can intervene in the vehicle's steering wheel torque to make the vehicle drive in the center of the lane. The above lane keeping function can usually be activated and used on vehicles with front vision sensor systems and wire control. In fact, with the development of intelligent driving technology, vehicle sensors are gradually increasing. Unlike single vision sensor systems, the sensors equipped on vehicles can now cover the target and lane information within the 360° range of the vehicle, so the adaptability of the LKA system and LDW system can be enhanced through the current intelligent driving system.

[0003] The existing LDW system and LKA system only use lane lines as information input. When the vehicle approaches the edge of the lane line, the software identifies the TTL (Time To Lane) distance from the lane line to provide reminders and corrections. However, when driving on actual roads, there may be potholes on the edge of the road, pedestrians / cyclists driving on the side of the road (occupying a smaller lane), and other situations in the lane where the vehicle is driving. When the driver avoids obstacles by making small turns, the existing LDW system and LKA system will alarm and correct the vehicle, affecting the driving experience. It can be seen that the current system only relies on lane lines as information input and does not receive more information, resulting in a situation where the driver competes with the driver for control of the steering wheel, affecting driving safety. Summary of the invention

[0004] The present application provides a vehicle deviation correction method, device, equipment and medium in the event of an obstacle, which can improve the driving performance and experience of the overall assisted driving and ensure driving safety.

[0005] In a first aspect, an embodiment of the present application provides a vehicle deviation correction method in an obstacle situation, and the vehicle deviation correction method in an obstacle situation includes:

[0006] Detect in real time whether there is an obstacle target at the front edge of the current lane, and if there is an obstacle target, translate the identified lane line of the current lane in the opposite direction of the obstacle target;

[0007] Based on the existence of obstacle targets on one side of the lane line translation direction and the lane line after translation, the LDW triggering conditions and the LKA trajectory generation conditions are reconstructed to achieve vehicle deviation correction.

[0008] In combination with the first aspect, in one implementation, when there is an obstacle target, the identified lane line of the current lane is translated in the opposite direction of the obstacle target, specifically:

[0009] When it is detected that there is an obstacle target in front of the current lane and the obstacle target is located at the right edge of the road, the left lane line of the current lane is shifted to the left;

[0010] When it is detected that there is an obstacle target in front of the current lane and the obstacle target is located at the left edge of the road, the right lane line of the current lane is translated to the right.

[0011] In combination with the first aspect, in one implementation, for a situation where the left lane line moves to the left, before reconstructing the LDW triggering condition and the LKA trajectory generating condition, the method further includes:

[0012] The lane line related parameters are obtained by recognizing the front vision camera of the vehicle, and the lane line before translation and the lane line after translation are calculated;

[0013] Based on the calculated front lane line and rear lane line, the distance between the vehicle and the lane line on the left side of the front lane line and the distance between the vehicle and the lane line on the left side of the rear lane line are obtained;

[0014] The lateral speed of the vehicle is calculated, and based on the calculated lateral speed of the vehicle, the time required for the vehicle to translate to the lane line to the left of the lane line before translation and the time required for the vehicle to translate to the lane line to the left of the lane line after translation are obtained.

[0015] In combination with the first aspect, in one implementation, for the case where the left lane line shifts to the left, the LDW triggering condition and the LKA trajectory generation condition are reconstructed, wherein the triggering of LDW is specifically:

[0016] When there is no obstacle target on the side of the lane line translation direction, if TTL2<TTL threshold , and DL2<0, trigger LDW, where TTL threshold Indicates the set time threshold, DL2 indicates the distance between the vehicle and the lane line on the left side of the lane line after translation;

[0017] When there is an obstacle target in the left front of the lane line translation direction, if LongDist>LongDist threshold , and LongDist / (V target -V_host)>TTC threshold , then the obstacle target is a non-dangerous target, and when TTL2<TTL threshold , and DL2<0, LDW is triggered, where LongDist represents the longitudinal distance between the vehicle and the obstacle target, LongDist threshold Indicates setting the vertical distance threshold, V target Indicates the longitudinal speed of the obstacle target, TTC threshold Indicates setting the collision time threshold, V_host indicates the vehicle speed;

[0018] When there is an obstacle target in the left front of the lane line translation direction, if LongDist≤LongDist threshold , and LongDist / (V target -V_host)≤TTC threshold , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold , and DL<0, LDW is triggered, where TTL1 represents the time required for the vehicle to move to the lane line on the left side of the lane line before translation, and DL represents the distance between the vehicle and the lane line on the left side of the lane line before translation;

[0019] When there is an obstacle on the left side of the lane line translation direction, if the obstacle is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold , and DL<0, LDW is triggered;

[0020] When there is an obstacle target on the left rear side of the lane line translation direction, if LongDist>LongDist threshold , or LongDist / (V_host-V target )>TTL threshold , then the obstacle target is a non-dangerous target, and when TTL2<TTL threshold , and DL2<0, LDW is triggered;

[0021] When there is an obstacle target on the left rear side of the lane line translation direction, if LongDist≤LongDist threshold , and LongDist / (V target -V_host)≤TTC threshold , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold , and DL<0, LDW is triggered.

[0022] In combination with the first aspect, in an implementation manner, the reconstructing the LDW triggering condition and the LKA generating track condition, before reconstructing the LKA generating track condition, further includes:

[0023] Determine the control points of the Bezier curve based on the total length of the vehicle's obstacle avoidance operation driving curve;

[0024] According to the determined control points of the Bezier curve, the obstacle avoidance operation curve of the vehicle is calculated when the lane line does not translate;

[0025] According to the determined control points of the Bezier curve, the obstacle avoidance operation curve of the vehicle after the lane line is shifted is calculated.

[0026] In combination with the first aspect, in one implementation, for a situation where the left lane line shifts to the left, the LDW triggering condition and the LKA trajectory generation condition are reconstructed, wherein for LKA, specifically:

[0027] When there is no obstacle target on the side of the lane line translation direction, if TTL2<TTL threshold , then LKA is triggered, and the vehicle deviation from the lane is corrected based on the obstacle avoidance operation curve of the vehicle after the lane line is translated. Among them, TTL threshold Indicates the set time threshold, TTL2 indicates the time required for the vehicle to move to the lane line on the left side of the lane line after the translation;

[0028] When there is an obstacle target in the left front of the lane line translation direction, if LongDist>LongDist threshold 、LongDist / (V target -V_host)>TTC threshold , and TTL2<TTL threshold When the obstacle target is a non-dangerous target, the vehicle deviation from the lane is corrected based on the vehicle obstacle avoidance operation curve after the lane line is translated. Among them, LongDist represents the longitudinal distance between the vehicle and the obstacle target, LongDist threshold Indicates setting the vertical distance threshold, V target Indicates the longitudinal speed of the obstacle target, TTC threshold Indicates setting the collision time threshold, V_host indicates the vehicle speed;

[0029] When there is an obstacle target in the left front of the lane line translation direction, if LongDist≤LongDist threshold , and LongDist / (V target -V_host)≤TTC threshold, then the obstacle target is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold When the vehicle is moving to the left lane of the lane line before the lane line is shifted, the vehicle is corrected for deviation from the lane based on the obstacle avoidance operation curve when the lane line is not shifted. TTL1 represents the time required for the vehicle to shift to the lane line on the left side of the lane line before the shift.

[0030] When there is an obstacle on the left side of the lane line translation direction, if the obstacle is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold When the lane line is not shifted, the vehicle is corrected for deviating from the lane based on the vehicle's obstacle avoidance operation curve.

[0031] In combination with the first aspect, in one implementation, for a situation where the left lane line shifts to the left, the LDW triggering condition and the LKA trajectory generation condition are reconstructed, wherein for LKA, specifically:

[0032] When there is an obstacle target on the left rear side of the lane line translation direction, if LongDist>LongDist threshold , or LongDist / (V_host-V target )>TTL threshold , then the obstacle target is a non-dangerous target, and when TTL2<TTL threshold When the lane line is shifted, the vehicle is corrected to deviate from the lane based on the obstacle avoidance operation curve of the vehicle after the lane line is shifted;

[0033] When there is an obstacle target on the left rear side of the lane line translation direction, if LongDist≤LongDist threshold , and LongDist / (V target -V_host)≤TTC threshold , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold When the lane line is not shifted, the vehicle is corrected for deviating from the lane based on the vehicle's obstacle avoidance operation curve.

[0034] In a second aspect, an embodiment of the present application provides a vehicle deviation correction device in the case of an obstacle, and the vehicle deviation correction device in the case of an obstacle includes:

[0035] A detection module is used to detect in real time whether there is an obstacle target at the front edge of the current lane, and when an obstacle target exists, the identified lane line of the current lane is translated in the opposite direction of the obstacle target;

[0036] The execution module is used to reconstruct the LDW triggering conditions and the LKA trajectory generation conditions based on the existence of obstacle targets on one side of the lane line translation direction and the translated lane line to achieve vehicle deviation correction.

[0037] In a third aspect, an embodiment of the present application provides a vehicle deviation correction device in the event of an obstacle, the vehicle deviation correction device in the event of an obstacle comprising a processor, a memory, and a vehicle deviation correction program in the event of an obstacle stored in the memory and executable by the processor, wherein when the vehicle deviation correction program in the event of an obstacle is executed by the processor, the steps of the vehicle deviation correction method in the event of an obstacle described above are implemented.

[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which is stored a vehicle correction program in the event of an obstacle. When the vehicle correction program in the event of an obstacle is executed by a processor, the steps of the vehicle correction method in the event of an obstacle described above are implemented.

[0039] The beneficial effects brought by the technical solution provided by the embodiments of the present application include:

[0040] When it is detected that there is an obstacle target at the edge of the current lane, the lane line is virtually translated, and the LDW triggering conditions and LKA trajectory generation conditions are reconstructed. At the same time, in order to meet safety requirements, a danger judgment is made for the target on the other side of the lane line, and the LDW triggering conditions and LKA trajectory are reprocessed to output reasonable and safe results to drive the LDW and LKA systems to operate, effectively solving the problem of poor driver operation experience that is prone to occur in the current LDW / LKA system that only uses a single camera, improving the overall assisted driving performance and experience, and ensuring driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a vehicle deviation correction method in an obstacle situation for this application;

[0042] Figure 2 This is a schematic diagram of lane line translation;

[0043] Figure 3 This is a schematic diagram when there is no obstacle on the left side of the translation lane line;

[0044] Figure 4 This is a schematic diagram when there is an obstacle in front of the left side of the translation lane line;

[0045] Figure 5 This is a schematic diagram when there is an obstacle on the left side of the translation lane line;

[0046] Figure 6 This is a schematic diagram when there is an obstacle behind the left side of the translation lane line;

[0047] Figure 7It is a schematic diagram of a vehicle obstacle avoidance operation driving curve when the lane line is not translated and a vehicle obstacle avoidance operation driving curve after the lane line is translated;

[0048] Figure 8 It is a schematic diagram of the driving curve of the vehicle's obstacle avoidance operation when there is no obstacle on the left side of the horizontal lane line;

[0049] Fig. 9 This is a schematic diagram of the structure of a vehicle deviation correction device in an obstacle situation of the present application;

[0050] Fig.10 This is a schematic diagram of the hardware structure of the vehicle correction equipment in the case of obstacles. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0053] On the first aspect, the embodiment of the present application provides a vehicle correction method in the event of an obstacle. For a vehicle equipped with a 360-degree smart sensor, the driver activates the LDW and LKA systems through the vehicle computer. When the vehicle speed is greater than the system activation speed, if there are obstacles or pedestrians at the edge of the vehicle lane, the sensor perceives the surrounding targets and road edge information, and reasonably designs the LDW trigger conditions and LKA correction trajectory to achieve safe avoidance, improve driving comfort, and effectively ensure vehicle safety and pedestrian safety.

[0054] In one embodiment, referring to Figure 1 , Figure 1 This is a vehicle deviation correction method in the case of obstacles in this application. Figure 1 As shown, the vehicle deviation correction method in the case of an obstacle includes:

[0055] S1: Detect in real time whether there is an obstacle target at the front edge of the current lane, and if there is an obstacle target, translate the identified lane line of the current lane in the opposite direction of the obstacle target;

[0056] Furthermore, in one embodiment, when there is an obstacle target, the identified lane line of the current lane is translated in the opposite direction of the obstacle target, specifically:

[0057] When it is detected that there is an obstacle target in front of the current lane and the obstacle target is located at the right edge of the road, the left lane line of the current lane is shifted to the left;

[0058] When it is detected that there is an obstacle target in front of the current lane and the obstacle target is located at the left edge of the road, the right lane line of the current lane is translated to the right.

[0059] That is, the vehicle monitors the obstacle situation in front of the current lane in real time during driving. When there is an obstacle at the lane edge in front of the current lane, the lane line on the other side is virtually translated.

[0060] S2: Based on the existence of obstacles on one side of the lane line translation direction and the translated lane line, the LDW triggering conditions and the LKA trajectory generation conditions are reconstructed to achieve vehicle deviation correction. After the lane line is virtually translated, based on the translated lane line and the obstacles on the side of the lane line, the LDW triggering conditions and the LKA trajectory generation conditions are reconstructed to achieve the triggering of the LDW and LKA systems.

[0061] Furthermore, in one embodiment, for the case where the left lane line moves to the left, before reconstructing the LDW triggering condition and the LKA trajectory generating condition, the method further includes:

[0062] S201: Obtain lane line related parameters through the front visual camera of the vehicle, and calculate the front lane line and the rear lane line representation, specifically:

[0063] f(x)=C0+C1*x+C2*x 2 +C3*x 3

[0064] f1(x)=C0+D+C1*x+C2*x 2 +C3*x 3

[0065] Among them, f(x) represents the lane line equation before translation, C0 represents the lateral distance between the camera and the lane line at the starting point, C1 represents the lateral angle between the camera and the lane line at the starting point, C2 represents the curvature of the lane line, C3 represents the curvature change rate of the lane line, f1(x) represents the lane line equation after translation, D represents the lane line translation distance, that is, the width of the obstacle target in front of the current lane, and x represents the longitudinal distance between the camera and the starting point; it should be noted that LaneWidth indicates the lane width of the current lane. Lane line related parameters include C0, C1, C2, and C3.

[0066] See also Figure 2As shown, for the LDW system, an example is given in which an obstacle exists at the edge of the right lane line in front of the current lane. Figure 2 In the figure, the rectangular block represents the vehicle, the cube represents the obstacle target, the two bold dashed lines represent the lane line of the current lane, the dashed line to the left of the left bold dashed line represents the lane line obtained by translating the left lane line of the current lane to the left, and the dashed line between the two bold dashed lines represents the center line of the lane line of the current lane.

[0067] S202: Based on the calculated front lane line and rear lane line, the distance between the vehicle and the lane line on the left side of the front lane line and the distance between the vehicle and the lane line on the left side of the rear lane line are obtained. Specifically:

[0068] DL=C0*cos(-arctan(C1))

[0069] DL2=(C0+D)*cos(-arctan(C1))

[0070] Among them, DL represents the distance between the vehicle and the lane line on the left side of the lane line before translation, and DL2 represents the distance between the vehicle and the lane line on the left side of the lane line after translation;

[0071] According to the scenario described in step S201, when there is an obstacle target in the current lane and the obstacle target is located at the right edge of the road, the identified left lane line of the current lane is translated to the left by a distance D, and the lateral deviation (distance) of the vehicle from the left lane line changes from DL to DL2.

[0072] S203: Calculate the lateral speed of the vehicle, and obtain the time required for the vehicle to move to the left lane line of the front lane line and the time required for the vehicle to move to the left lane line of the rear lane line according to the calculated lateral speed of the vehicle. Specifically:

[0073] V Lat =V_host*sin(-arctan(C1))

[0074]

[0075]

[0076] Among them, V Lat represents the lateral speed of the vehicle, V_host represents the vehicle speed, TTL1 represents the time required for the vehicle to move to the lane line on the left side of the lane line before translation, and TTL2 represents the time required for the vehicle to move to the lane line on the left side of the lane line after translation.

[0077] Furthermore, in one embodiment, for the case where the left lane line shifts to the left, the LDW triggering condition and the LKA trajectory generation condition are reconstructed, wherein the triggering of LDW is specifically:

[0078] When there is no obstacle target on the side of the lane line translation direction, if TTL2<TTL threshold , and DL2<0, trigger LDW, where TTL threshold Indicates setting a time threshold; Figure 3 As shown, there is no obstacle target on the side of the lane line translation direction. Similarly, the two bold dashed lines represent the lane line of the current lane, and the dashed line to the left of the left bold dashed line represents the lane line obtained by translating the left lane line of the current lane to the left.

[0079] When there is an obstacle target in the left front of the lane line translation direction, if LongDist>LongDist threshold , and LongDist / (V target -V_host)>TTC threshold , then the obstacle target is a non-dangerous target, and when TTL2<TTL threshold , and DL2<0, LDW is triggered, where LongDist represents the longitudinal distance between the vehicle and the obstacle target, LongDist threshold Indicates setting the vertical distance threshold, V target Indicates the longitudinal speed of the obstacle target, TTC threshold Indicates setting the collision time threshold;

[0080] When there is an obstacle target in the left front of the lane line translation direction, if LongDist≤LongDist threshold , and LongDist / (V target -V_host)≤TTC threshold , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold , and DL<0, LDW is triggered, that is, Figure 4 As shown, Figure 4 In, V HOST Indicates the vehicle speed, LongDist indicates the longitudinal distance between the vehicle and the obstacle target, case1 indicates the obstacle target on the left front side of the lane line translation direction, and Vtarget indicates the longitudinal speed of the obstacle target;

[0081] When there is an obstacle on the left side of the lane line translation direction, if the obstacle is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold , and DL<0, LDW is triggered; Figure 5As shown in FIG. 1 , there is an obstacle target on the left side of the lane line translation direction, and case 2 represents an obstacle target on the left side of the lane line translation direction.

[0082] When there is an obstacle target on the left rear side of the lane line translation direction, if LongDist>LongDist threshold , or LongDist / (V_host-V target )>TTL threshold , then the obstacle target is a non-dangerous target, and when TTL2<TTL threshold , and DL2<0, LDW is triggered;

[0083] When there is an obstacle target on the left rear side of the lane line translation direction, if LongDist≤LongDist threshold , and LongDist / (V target -V_host)≤TTC threshold , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold , and DL<0, LDW is triggered. Figure 6 As shown, there is an obstacle target on the left rear side of the lane line translation direction, and case 3 represents an obstacle target on the left rear side of the lane line translation direction.

[0084] Furthermore, in one embodiment, the LDW triggering condition and the LKA generation track condition are reconstructed, wherein before reconstructing the LKA generation track condition, the method further includes:

[0085] S211: Determine the control points of the Bezier curve based on the total length of the vehicle's obstacle avoidance operation driving curve, specifically:

[0086] L_Total=V_host*Tcal

[0087]

[0088] Among them, L_Total represents the total length of the vehicle's obstacle avoidance operation curve when the lane line does not translate, Tcal represents the preview time of the vehicle's driving trajectory, L represents the distance between P0 and P1, and also represents the distance between P2 and P3, and P0, P1, P2, and P3 represent the control points in the Bezier curve distributed from the front of the vehicle to the front in sequence;

[0089] That is, in the embodiment of the present application, the LKA system is described by taking the case where there is an obstacle at the edge of the right lane line of the current lane as an example. Figure 7As shown in the figure, when there is an obstacle target in the current lane and the obstacle target is located at the right edge of the road, the identified left lane line of the current lane is translated to the left by a distance D, and the lateral deviation (distance) of the vehicle from the left lane line changes from DL to DL2. The target trajectory is solved for different degrees of deviation of the left lane line, and the solution curve is solved using the third-order Bezier curve method. Figure 7 In the left image, the dashed curve represents the vehicle's obstacle avoidance operation curve when the lane line is not shifted, and in the right image, the dashed curve represents the vehicle's obstacle avoidance operation curve after the lane line is shifted. The positions of P0, P1, P2, and P3 before and after the lane line is shifted are shown in Figure 1. Figure 7 As indicated in the markings.

[0090] S212: Based on the determined control points of the Bezier curve, a driving curve for the vehicle to avoid obstacles when the lane line does not translate is calculated:

[0091] f_A(t)=P0_A(1-t) 3 +3P1_A*t(1-t) 2 +3P2_A*t 2 (1-t)+P3_A*t 3

[0092] Among them, f_A(t) represents the vehicle obstacle avoidance operation curve when the lane line is not translated, P0_A represents the starting point, corresponding to P0, with coordinates (0,0), P1_A represents the point in the vehicle heading angle direction, corresponding to P1, with coordinates (tan(-arctan(C1)),L), and P2_A represents the point in the end point direction, corresponding to P2, with coordinates VehicleWidth represents the width of the vehicle, P3_A represents the end point, corresponding to P3, the coordinates are t represents the normalization coefficient of the Bezier curve, and its value range is 0 to 1;

[0093] It should be noted that points P0_A, P1_A, P2_A, and P3_A are points on the driving curve of the vehicle's obstacle avoidance operation when the lane line does not translate, that is, control points of the Bezier curve.

[0094] S213: According to the determined control points of the Bezier curve, the obstacle avoidance operation curve of the vehicle after the lane line is shifted is calculated:

[0095] f_B(t)=P0_B(1-t) 3 +3P1_B*t(1-t) 2 +3P2_B*t 2 (1-t)+P3_B*t 3

[0096] Among them, f_B(t) represents the obstacle avoidance operation curve of the vehicle after the lane line is translated, P0_B represents the starting point, corresponding to P0, with coordinates (0,0), P1_B represents the point in the vehicle heading angle direction, corresponding to P1, with coordinates (tan(-arctan(C1)),L), and P2_B represents the point in the end point direction, corresponding to P2, with coordinates P3_B represents the end point, corresponding to P3, and its coordinates are

[0097]

[0098] It should be noted that points P0_B, P1_B, P2_B, and P3_B are points on the driving curve of the vehicle's obstacle avoidance operation after the lane line is translated, that is, control points of the Bezier curve.

[0099] Furthermore, in one embodiment, for the case where the left lane line shifts to the left, the LDW triggering condition and the LKA trajectory generation condition are reconstructed, wherein for LKA, specifically:

[0100] When there is no obstacle target on the side of the lane line translation direction, if TTL2<TTL threshold , then LKA is triggered, and the vehicle deviation from the lane is corrected based on the obstacle avoidance operation curve of the vehicle after the lane line is translated. Among them, TTL threshold Indicates setting a time threshold; Figure 8 As shown, there is no obstacle target on the side of the lane line translation direction. Similarly, the two bold dashed lines represent the lane line of the current lane. The dashed line on the left side of the bold dashed line on the left represents the lane line obtained by translating the left lane line of the current lane to the left. The dashed curve represents the obstacle avoidance operation curve of the vehicle after the lane line is translated.

[0101] When there is an obstacle target in the left front of the lane line translation direction, if LongDist>LongDist threshold 、LongDist / (V target -V_host)>TTC threshold , and TTL2<TTL threshold When the obstacle target is a non-dangerous target, the vehicle deviation from the lane is corrected based on the vehicle obstacle avoidance operation curve after the lane line is translated. Among them, LongDist represents the longitudinal distance between the vehicle and the obstacle target, LongDist threshold Indicates setting the vertical distance threshold, V target Indicates the longitudinal speed of the obstacle target, TTC threshold Indicates setting the collision time threshold;

[0102] When there is an obstacle target in the left front of the lane line translation direction, if LongDist≤LongDist threshold, and LongDist / (V target -V_host)≤TTC threshold , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold When the lane line is not shifted, the vehicle is corrected for deviation from the lane based on the vehicle's obstacle avoidance operation curve;

[0103] When there is an obstacle on the left side of the lane line translation direction, if the obstacle is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold When the lane line is not shifted, the vehicle is corrected for deviation from the lane based on the vehicle's obstacle avoidance operation curve;

[0104] When there is an obstacle target on the left rear side of the lane line translation direction, if LongDist>LongDist threshold , or LongDist / (V_host-V target )>TTL threshold , then the obstacle target is a non-dangerous target, and when TTL2<TTL threshold When the lane line is shifted, the vehicle is corrected to deviate from the lane based on the obstacle avoidance operation curve of the vehicle after the lane line is shifted;

[0105] When there is an obstacle target on the left rear side of the lane line translation direction, if LongDist≤LongDist threshold , and LongDist / (V target -V_host)≤TTC threshold , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when TTL1<TTL threshold When the lane line is not shifted, the vehicle is corrected for deviating from the lane based on the vehicle's obstacle avoidance operation curve.

[0106] The vehicle deviation correction method in the obstacle situation of the embodiment of the present application, when detecting that there is an obstacle target at the edge of the current lane road, performs a virtual translation operation on the lane line, reconstructs the LDW triggering condition and the LKA trajectory generation condition, and at the same time, in order to meet the safety requirements, performs a danger judgment on the target on the other side of the lane line, and reprocesses the LDW triggering condition and the LKA trajectory, outputs a reasonable and safe result to drive the LDW and LKA system to operate, effectively solves the problem of affecting the driver's poor operating experience that is prone to occur in the current LDW / LKA system using only a single camera, improves the driving performance and experience of the overall assisted driving, and ensures driving safety.

[0107] In a second aspect, an embodiment of the present application also provides a vehicle deviation correction device in the event of an obstacle.

[0108] In one embodiment, referring to Fig. 9 , Fig. 9 This is a functional module diagram of the vehicle deviation correction device in the case of an obstacle in this application. Fig. 9 As shown, the vehicle deviation correction device in the case of an obstacle includes a detection module and an execution module.

[0109] The detection module is used to detect in real time whether there is an obstacle target at the front edge of the current lane, and when an obstacle target exists, the identified lane line of the current lane will be translated in the opposite direction of the obstacle target; the execution module is used to reconstruct the LDW triggering conditions and the LKA trajectory generation conditions based on the existence of the obstacle target on one side of the lane line translation direction and the translated lane line to achieve vehicle correction.

[0110] On the third aspect, an embodiment of the present application provides a vehicle deviation correction device in the event of an obstacle. The vehicle deviation correction device in the event of an obstacle may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0111] Reference Fig.10 , Fig.10 The hardware structure diagram of the vehicle deviation correction device under the obstacle situation involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the vehicle deviation correction device under the obstacle situation may include a processor, a memory, a communication interface and a communication bus.

[0112] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0113] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces for interconnecting the components of the vehicle deviation correction device in the case of an obstacle, and for interconnecting the vehicle deviation correction device in the case of an obstacle with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0114] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0115] The processor may be a general-purpose processor, and the general-purpose processor may call the vehicle deviation correction program under the obstacle situation stored in the memory, and execute the vehicle deviation correction method under the obstacle situation provided by the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). Among them, the method executed when the vehicle deviation correction program under the obstacle situation is called can refer to the various embodiments of the vehicle deviation correction method under the obstacle situation of the present application, which will not be repeated here.

[0116] Those skilled in the art will understand that Fig.10 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0117] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0118] The computer-readable storage medium of the present application stores a vehicle deviation correction program in the event of an obstacle, wherein when the vehicle deviation correction program in the event of an obstacle is executed by a processor, the steps of the vehicle deviation correction method in the event of an obstacle as described above are implemented.

[0119] Among them, the method implemented when the vehicle correction program in the obstacle situation is executed can refer to the various embodiments of the vehicle correction method in the obstacle situation of the present application, and will not be repeated here.

[0120] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0121] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0122] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0123] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0124] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0125] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle deviation correction method in an obstacle situation, characterized in that: The vehicle deviation correction method under the obstacle situation includes: Detect in real time whether there is an obstacle target at the front edge of the current lane, and if there is an obstacle target, translate the identified lane line of the current lane in the opposite direction of the obstacle target; Based on the existence of obstacles on the side of the lane line translation direction and the lane line after translation, the LDW triggering conditions and the LKA trajectory generation conditions are reconstructed to achieve vehicle deviation correction; In the case where the left lane line shifts to the left, the LDW triggering condition and the LKA trajectory generation condition are reconstructed to achieve vehicle deviation correction. For LKA, specifically: When there is an obstacle on the left rear side of the lane line translation direction, if ,or , then the obstacle target is a non-dangerous target, and when When the lane line is shifted, the vehicle is corrected to deviate from the lane based on the obstacle avoidance operation curve of the vehicle after the lane line is shifted; When there is an obstacle on the left rear side of the lane line translation direction, if ,and , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when When the lane line is not shifted, the vehicle is corrected for deviation from the lane based on the vehicle's obstacle avoidance operation curve; in, Indicates the longitudinal distance between the vehicle and the obstacle target, Indicates setting the vertical distance threshold. represents the vehicle speed, represents the longitudinal velocity of the obstacle target, Indicates setting the time threshold. Indicates the time required for the vehicle to move to the lane line on the left side of the lane line after translation. Indicates setting the collision time threshold. Indicates the time required for the vehicle to move to the lane line to the left of the lane line before translation.

2. The vehicle deviation correction method in an obstacle situation as claimed in claim 1, characterized in that: When there is an obstacle target, the lane line of the identified current lane is translated in the opposite direction of the obstacle target, specifically: When it is detected that there is an obstacle target in front of the current lane and the obstacle target is located at the right edge of the road, the left lane line of the current lane is shifted to the left; When it is detected that there is an obstacle target in front of the current lane and the obstacle target is located at the left edge of the road, the right lane line of the current lane is translated to the right.

3. The vehicle deviation correction method in the case of an obstacle as claimed in claim 2, characterized in that: For the case where the left lane line moves to the left, before reconstructing the LDW triggering conditions and the LKA trajectory generation conditions, the following are also included: The lane line related parameters are obtained by recognizing the front vision camera of the vehicle, and the lane line before translation and the lane line after translation are calculated; Based on the calculated front lane line and rear lane line, the distance between the vehicle and the lane line on the left side of the front lane line and the distance between the vehicle and the lane line on the left side of the rear lane line are obtained; The lateral speed of the vehicle is calculated, and based on the calculated lateral speed of the vehicle, the time required for the vehicle to translate to the lane line to the left of the lane line before translation and the time required for the vehicle to translate to the lane line to the left of the lane line after translation are obtained.

4. The vehicle deviation correction method in the case of an obstacle as claimed in claim 3, characterized in that: In the case where the left lane line shifts to the left, the LDW triggering condition and the LKA trajectory generation condition are reconstructed to achieve vehicle deviation correction, wherein the LDW triggering is specifically as follows: When there is no obstacle target on the side of the lane line translation direction, if ,and , triggering LDW; When there is an obstacle in the left front of the lane line in the direction of translation, ,and , then the obstacle target is a non-dangerous target, and when ,and When , LDW is triggered; When there is an obstacle in the left front of the lane line in the direction of translation, ,and , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when ,and When , LDW is triggered; When there is an obstacle on the left side of the lane line translation direction, if the obstacle is a dangerous target, cancel the lane line translation operation and ,and When , LDW is triggered; When there is an obstacle on the left rear side of the lane line translation direction, if ,or , then the obstacle target is a non-dangerous target, and when ,and When , LDW is triggered; When there is an obstacle on the left rear side of the lane line translation direction, if ,and , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when ,and When , LDW is triggered; in, Indicates setting the time threshold. Indicates the distance between the vehicle and the lane line on the left of the translated lane line. Indicates the longitudinal distance between the vehicle and the obstacle target, Indicates setting the vertical distance threshold. represents the longitudinal velocity of the obstacle target, Indicates setting the collision time threshold. represents the vehicle speed, Indicates the time required for the vehicle to move to the lane line to the left of the lane line before translation. Indicates the distance between the vehicle and the lane line to the left of the lane line before translation.

5. The vehicle deviation correction method in an obstacle situation as claimed in claim 3, characterized in that: The reconstructing of the LDW triggering condition and the LKA generating trajectory condition realizes vehicle deviation correction, wherein, before reconstructing the LKA generating trajectory condition, it also includes: Determine the control points of the Bezier curve based on the total length of the vehicle's obstacle avoidance operation driving curve; According to the determined control points of the Bezier curve, the obstacle avoidance operation curve of the vehicle is calculated when the lane line does not translate; According to the determined control points of the Bezier curve, the obstacle avoidance operation curve of the vehicle after the lane line is shifted is calculated.

6. The vehicle deviation correction method in the case of an obstacle as claimed in claim 5, characterized in that: In the case where the left lane line shifts to the left, the LDW triggering condition and the LKA trajectory generation condition are reconstructed to achieve vehicle deviation correction, wherein for LKA, specifically: When there is no obstacle target on the side of the lane line translation direction, if , then LKA is triggered, and the vehicle is corrected for lane deviation based on the vehicle's obstacle avoidance operation curve after the lane line is translated; When there is an obstacle in the left front of the lane line in the direction of translation, , ,and When the obstacle target is a non-dangerous target, the vehicle will be corrected for deviating from the lane based on the vehicle's obstacle avoidance operation curve after the lane line is translated; When there is an obstacle in the left front of the lane line in the direction of translation, ,and , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when When the lane line is not shifted, the vehicle is corrected for deviation from the lane based on the vehicle's obstacle avoidance operation curve; When there is an obstacle on the left side of the lane line translation direction, if the obstacle is a dangerous target, cancel the lane line translation operation and When the lane line is not shifted, the vehicle is corrected for deviation from the lane based on the vehicle's obstacle avoidance operation curve; in, Indicates setting the time threshold. Indicates the time required for the vehicle to move to the lane line on the left side of the lane line after translation. Indicates the longitudinal distance between the vehicle and the obstacle target, Indicates setting the vertical distance threshold. represents the longitudinal velocity of the obstacle target, Indicates setting the collision time threshold. represents the vehicle speed, Indicates the time required for the vehicle to move to the lane line to the left of the lane line before translation.

7. A vehicle deviation correction device in the case of an obstacle, characterized in that: The vehicle deviation correction device in the obstacle situation includes: A detection module is used to detect in real time whether there is an obstacle target at the front edge of the current lane, and when an obstacle target exists, the identified lane line of the current lane is translated in the opposite direction of the obstacle target; The execution module is used to reconstruct the LDW triggering conditions and the LKA trajectory generation conditions based on the existence of obstacles on the side of the lane line translation direction and the lane line after translation, so as to realize vehicle deviation correction; In the case where the left lane line shifts to the left, the LDW triggering condition and the LKA trajectory generation condition are reconstructed to achieve vehicle deviation correction. For LKA, specifically: When there is an obstacle on the left rear side of the lane line translation direction, if ,or , then the obstacle target is a non-dangerous target, and when When the lane line is shifted, the vehicle is corrected to deviate from the lane based on the obstacle avoidance operation curve of the vehicle after the lane line is shifted; When there is an obstacle on the left rear side of the lane line translation direction, if ,and , then the obstacle target is a dangerous target, cancel the lane line translation operation, and when When the lane line is not shifted, the vehicle is corrected for deviation from the lane based on the vehicle's obstacle avoidance operation curve; in, Indicates the longitudinal distance between the vehicle and the obstacle target, Indicates setting the vertical distance threshold. represents the vehicle speed, represents the longitudinal velocity of the obstacle target, Indicates setting the time threshold. Indicates the time required for the vehicle to move to the lane line on the left side of the lane line after translation. Indicates setting the collision time threshold. Indicates the time required for the vehicle to move to the lane line to the left of the lane line before translation.

8. A vehicle deviation correction device in the case of an obstacle, characterized in that: The vehicle correction device in the case of an obstacle includes a processor, a memory, and a vehicle correction program in the case of an obstacle stored in the memory and executable by the processor, wherein when the vehicle correction program in the case of an obstacle is executed by the processor, the steps of the vehicle correction method in the case of an obstacle as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a vehicle deviation correction program in an obstacle situation, wherein when the vehicle deviation correction program in an obstacle situation is executed by a processor, the steps of the vehicle deviation correction method in an obstacle situation as described in any one of claims 1 to 6 are implemented.

Images