Trajectory planning method, device and equipment for emergency lane keeping based on Bezier curve and storage medium

Abstract

The invention discloses a Bezier curve-based emergency lane keeping trajectory planning method, device and equipment and a storage medium, and relates to the technical field of vehicle intelligent driving, and the Bezier curve-based emergency lane keeping trajectory planning method comprises the steps of obtaining road edge scenes, classifying the road edge scenes, and determining the road edge scenes according to the classified road edge scenes; obtaining a classification result; determining a target lateral deviation between a starting point and an ending point of trajectory planning according to the classification result; a starting point parameter and an end point parameter of the trajectory planning are obtained, the starting point parameter at least comprises a starting point transverse acceleration, and the end point parameter at least comprises an end point transverse acceleration; and taking the target transverse deviation, the starting point parameter and the end point parameter as parameters of a Bezier curve to carry out track planning of emergency lane keeping to obtain a target planning track. According to the invention, the stability of the trajectory planning result of emergency lane keeping can be improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle intelligent driving technology, and in particular to a trajectory planning method, device, equipment and storage medium for emergency lane keeping based on Bezier curves. Background Art

[0002] The Emergency Lane Keeping (ELK) system is an auxiliary system that actively corrects the vehicle's posture when the driver unconsciously drives the vehicle toward the edge of the road or unconsciously drives into an adjacent lane and there are oncoming or overtaking vehicles in the adjacent lane. However, the ELK function is currently affected by the complexity and diversity of road edge scenes, and the stability of the trajectory planning results of emergency lane keeping is low. Therefore, how to improve the stability of the trajectory planning results of emergency lane keeping is a problem that still needs to be solved.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present application is to provide a trajectory planning method, device, equipment and storage medium for emergency lane keeping based on Bezier curves, aiming to solve the technical problem of how to improve the stability of trajectory planning results for emergency lane keeping.

[0005] To achieve the above objectives, the present application proposes a trajectory planning method for emergency lane keeping based on Bezier curves, the method comprising:

[0006] Acquire a road edge scene, and classify the road edge scene to obtain a classification result;

[0007] Determine the target lateral deviation between the starting point and the end point of the trajectory planning according to the classification result;

[0008] Acquire the starting point parameters and the end point parameters of the trajectory planning, wherein the starting point parameters at least include the starting point lateral acceleration, and the end point parameters at least include the end point lateral acceleration;

[0009] The target lateral deviation, the starting point parameter and the end point parameter are used as parameters of a Bezier curve to perform trajectory planning for emergency lane keeping, so as to obtain a target planning trajectory.

[0010] In one embodiment, the step of determining the target lateral deviation between the starting point and the end point of trajectory planning according to the classification result includes:

[0011] According to the classification result, determining target edges on the left side of the road and the right side of the road, and obtaining edge coefficients of the target edges;

[0012] Obtaining a lateral distance between the vehicle and the target edge;

[0013] Obtaining a preset lateral offset of an end point of trajectory planning from an edge of the target;

[0014] A target lateral deviation between a starting point and an end point of trajectory planning is determined according to the edge coefficient, the lateral distance, and the preset lateral offset.

[0015] In one embodiment, the step of determining the target edges on the left side of the road and the right side of the road according to the classification result includes:

[0016] When the classification result is that there is only a lane line on the left side of the vehicle and only a curb on the right side, the left lane line is determined as the left target edge, and the right lane line is determined as the right target edge;

[0017] When the classification result is that there is only a lane line on the left side of the vehicle and there are both a lane line and a curb on the right side, the left lane line is determined as the left target edge, and the right target edge is determined according to the distance between the right lane line and the right curb;

[0018] When the classification result is that there is only a curb on the right side of the vehicle and no lane line or curb on the left side, the right curb is determined as the right target edge, and there is no left target edge;

[0019] When the classification result is that there are both a lane line and a curb with a spacing less than a preset value on the right side of the vehicle and there is no lane line or curb on the left side, the right lane line is determined as the right target edge, and there is no left target edge;

[0020] When the classification result is that there are lane lines and curbs on the right side of the vehicle at a distance not less than a preset value and there are no lane lines or curbs on the left side, the right curb is determined as the right target edge, and there is no left target edge.

[0021] In one embodiment, the step of obtaining a preset lateral offset of the end point of trajectory planning from the target edge comprises:

[0022] Obtaining a left lateral speed of the vehicle relative to a target edge on the left side of the road, a right lateral speed of the vehicle relative to a target edge on the right side of the road, a maximum value of the left lateral speed of the vehicle relative to the target edge on the left side of the road, and a maximum value of the right lateral speed of the vehicle relative to the target edge on the right side of the road;

[0023] A preset lateral offset of the target edge is determined according to the left lateral velocity, the right lateral velocity, the left lateral velocity maximum value, and the right lateral velocity maximum value.

[0024] In one embodiment, the step of using the target lateral deviation, the starting point parameter, and the end point parameter as parameters of a Bezier curve to perform trajectory planning for emergency lane keeping to obtain a target planning trajectory includes:

[0025] Determine a lateral acceleration Bezier curve according to the target lateral deviation, the starting point parameter and the end point parameter;

[0026] The lateral acceleration Bezier curve is integrated twice to obtain a lateral displacement Bezier curve, and the target planning trajectory is obtained.

[0027] In one embodiment, the step of determining the lateral acceleration Bezier curve according to the target lateral deviation, the starting point parameter and the end point parameter comprises:

[0028] Determine a curve starting point and a curve end point of a lateral acceleration Bezier curve according to the starting point parameter and the end point parameter;

[0029] A lateral acceleration Bezier curve is determined according to the curve starting point, the curve end point and the target lateral deviation.

[0030] In one embodiment, the step of determining the lateral acceleration Bezier curve according to the curve starting point, the curve end point and the target lateral deviation comprises:

[0031] Calculating the lateral acceleration of the end point of the first Bezier curve, the lateral speed difference of the first Bezier curve, and the lateral speed difference of the second Bezier curve through the starting point of the curve, the end point of the curve, and the target lateral deviation;

[0032] A lateral acceleration Bezier curve is determined according to the end point lateral acceleration, the lateral speed difference of the first Bezier curve, and the lateral speed difference of the second Bezier curve.

[0033] In addition, to achieve the above purpose, the present application also proposes a trajectory planning device for emergency lane keeping based on a Bezier curve, and the trajectory planning device for emergency lane keeping based on a Bezier curve includes:

[0034] A classification module, used to obtain a road edge scene, and classify the road edge scene to obtain a classification result;

[0035] A determination module, used to determine a target lateral deviation between a starting point and an end point of trajectory planning according to the classification result;

[0036] An acquisition module, used to acquire the starting point parameters and the end point parameters of the trajectory planning, wherein the starting point parameters at least include the starting point lateral acceleration, and the end point parameters at least include the end point lateral acceleration;

[0037] The planning module is used to use the target lateral deviation, the starting point parameter and the end point parameter as parameters of the Bezier curve to perform trajectory planning for emergency lane keeping, so as to obtain a target planning trajectory.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a trajectory planning device for emergency lane keeping based on Bezier curves, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the trajectory planning method for emergency lane keeping based on Bezier curves as described above.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the trajectory planning method for emergency lane keeping based on Bezier curves as described above are implemented.

[0040] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the trajectory planning method for emergency lane keeping based on Bezier curves as described above.

[0041] The present application provides a trajectory planning method for emergency lane keeping based on Bezier curves. The present application obtains a road edge scene, and classifies the road edge scene to obtain a classification result; determines a target lateral deviation between a start point and an end point of trajectory planning according to the classification result; obtains a start point parameter and an end point parameter of the trajectory planning, wherein the start point parameter at least includes a start point lateral acceleration, and the end point parameter at least includes an end point lateral acceleration; uses the target lateral deviation, the start point parameter, and the end point parameter as parameters of the Bezier curve to perform trajectory planning for emergency lane keeping, and obtains a target planning trajectory.

[0042] In summary, the present application combines various situations of road edge scenes and uses Bezier curves to perform targeted trajectory planning for emergency lane keeping, thereby improving the stability of the trajectory planning results for emergency lane keeping. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] Figure 1 A flowchart diagram of a first embodiment of a trajectory planning method for emergency lane keeping based on Bezier curves provided in this application;

[0046] Figure 2 A schematic diagram of trajectory planning for different road edge scenarios of the Bezier curve-based emergency lane keeping trajectory planning method provided in Example 1 of the present application;

[0047] Figure 3 A schematic diagram of a third-order Bezier curve for a Bezier curve-based trajectory planning method for emergency lane keeping provided in Example 1 of the present application;

[0048] Figure 4 A schematic diagram of trajectory planning for a road edge scenario of a Bezier curve-based emergency lane keeping trajectory planning method provided in Example 1 of the present application;

[0049] Figure 5 A flowchart diagram of Embodiment 2 of the trajectory planning method for emergency lane keeping based on Bezier curves provided in this application;

[0050] Figure 6 A schematic diagram of trajectory planning for a road edge scenario 1 of a trajectory planning method for emergency lane keeping based on Bezier curves provided in Example 2 of the present application;

[0051] Figure 7 A schematic diagram of trajectory planning for a second road edge scenario of a Bezier curve-based emergency lane keeping trajectory planning method provided in Embodiment 2 of the present application;

[0052] Figure 8 A schematic diagram of trajectory planning for a road edge scenario three of a trajectory planning method for emergency lane keeping based on Bezier curves provided in Example 2 of the present application;

[0053] Fig. 9 A schematic diagram of trajectory planning for a road edge scenario 4 of a trajectory planning method for emergency lane keeping based on Bezier curves provided in Example 2 of the present application;

[0054] Fig.10 A schematic diagram of trajectory planning for a road edge scenario 5 of a trajectory planning method for emergency lane keeping based on Bezier curves provided in Example 2 of the present application;

[0055] Fig.11This is a schematic diagram of the module structure of a trajectory planning device for emergency lane keeping based on Bezier curves according to an embodiment of the present application;

[0056] Fig.12 Schematic diagram of the device structure of the hardware operating environment involved in the trajectory planning method for emergency lane keeping based on Bezier curves in an embodiment of the present application.

[0057] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0059] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0060] The main solution of the present application is to obtain a road edge scene, classify the road edge scene, and obtain a classification result; determine the target lateral deviation of the starting point and the end point of trajectory planning according to the classification result; obtain the starting point parameter and the end point parameter of the trajectory planning, the starting point parameter at least includes the starting point lateral acceleration, and the end point parameter at least includes the end point lateral acceleration; use the target lateral deviation, the starting point parameter and the end point parameter as parameters of the Bezier curve to perform trajectory planning for emergency lane keeping, and obtain the target planning trajectory.

[0061] At present, the emergency lane keeping function is affected by the complexity and diversity of the road edge scene, and the stability of the trajectory planning results of the emergency lane keeping is low. Therefore, how to improve the stability of the trajectory planning results of the emergency lane keeping is a problem that still needs to be solved.

[0062] The present application combines various situations of road edge scenes and uses Bezier curves to perform targeted trajectory planning for emergency lane keeping, thereby improving the stability of the trajectory planning results for emergency lane keeping.

[0063] Based on this, the embodiment of the present application provides a trajectory planning method for emergency lane keeping based on Bezier curve, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the trajectory planning method for emergency lane keeping based on Bezier curves of the present application.

[0064] In this embodiment, the trajectory planning method for emergency lane keeping based on Bezier curve includes steps S10 to S40:

[0065] Step S10: Acquire a road edge scene, and classify the road edge scene to obtain a classification result;

[0066] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a trajectory planning device for emergency lane keeping based on Bezier curves, etc. The following takes the trajectory planning device for emergency lane keeping based on Bezier curves as an example to illustrate this embodiment and the following embodiments.

[0067] It should be noted that, since the roadside scenes are complex and changeable, when performing trajectory planning, it is necessary to consider the impact of the roadside scenes and perform targeted trajectory planning. Therefore, the roadside scenes can be classified first, and different trajectory planning schemes can be determined according to different classification results.

[0068] It is understandable that the classification process first obtains the road edge scene, and obtains the lane line and the curb according to the road edge scene; then the lane line and the curb are classified according to the obtained lane line and the curb, and the classification results include: there is only a lane line on the left side of the vehicle and only a curb on the right side, there is only a lane line on the left side of the vehicle and both lane lines and curbs exist on the right side, there is only a curb on the right side of the vehicle and no lane line or curb on the left side, there are both lane lines and curbs on the right side of the vehicle with an interval less than a preset value and no lane lines or curbs on the left side, and there are both lane lines and curbs on the right side of the vehicle with an interval not less than a preset value and no lane lines or curbs on the left side. For reference Figure 2 , Figure 2 The following is a schematic diagram of trajectory planning for different road edge scenarios. Different planning trajectories are determined according to different road edge scenarios.

[0069] It is understandable that there may be lane lines and road edges in the road edge scene. Since the quality of the road edge is not stable enough, while the quality of the lane lines is generally good, the lane lines are selected as reference lines in the scene where there are lane lines.

[0070] Step S20: determining the target lateral deviation between the starting point and the end point of the trajectory planning according to the classification result;

[0071] It should be noted that the Bezier curve is a smooth curve defined by a series of control points. These control points determine the shape and direction of the curve. In the Bezier curve, the starting point and the end point are fixed, and the control points can be at any position of the curve. By adjusting these control points, the shape of the curve can be changed. In the trajectory planning process of this embodiment, one of the important parameters of the Bezier curve is the target lateral deviation between the starting point and the end point of the trajectory planning, so it is necessary to determine the target lateral deviation according to the classification result of the road edge field for subsequent calculation.

[0072] Step S30: obtaining the starting point parameters and the end point parameters of the trajectory planning, wherein the starting point parameters at least include the starting point lateral acceleration, and the end point parameters at least include the end point lateral acceleration;

[0073] It should be noted that, in this embodiment, the starting point lateral velocity and the starting point lateral acceleration can be directly obtained, and the end point lateral velocity and the end point lateral acceleration can be set according to actual conditions, thereby obtaining the starting point parameters and the end point parameters.

[0074] Step S40: using the target lateral deviation, the starting point parameter and the end point parameter as parameters of a Bezier curve to perform trajectory planning for emergency lane keeping, and obtain a target planning trajectory.

[0075] It should be noted that, in this embodiment, the initially obtained Bezier curve is a lateral acceleration curve, and the target planning trajectory curve can be obtained by integration.

[0076] In a feasible manner, the step of using the target lateral deviation, the starting point parameter, and the end point parameter as parameters of a Bezier curve to perform trajectory planning for emergency lane keeping to obtain a target planning trajectory includes:

[0077] Determine a lateral acceleration Bezier curve according to the target lateral deviation, the starting point parameter and the end point parameter;

[0078] The lateral acceleration Bezier curve is integrated twice to obtain a lateral displacement Bezier curve, and the target planning trajectory is obtained.

[0079] It is understandable that the starting point and the end point of the lateral acceleration Bezier curve can be first determined according to the starting point parameter and the end point parameter; and then the lateral acceleration Bezier curve can be determined according to the starting point of the curve, the end point of the curve and the target lateral deviation. In a specific process, the lateral acceleration of the end point of the first Bezier curve, the lateral speed difference of the first Bezier curve and the lateral speed difference of the second Bezier curve can be calculated according to the starting point of the curve, the end point of the curve and the target lateral deviation; the lateral acceleration Bezier curve can be determined according to the lateral acceleration of the end point, the lateral speed difference of the first Bezier curve and the lateral speed difference of the second Bezier curve.

[0080] It is understandable that in order to ensure the continuity and smoothness of each curve segment, this embodiment selects a third-order Bezier curve. Figure 3As shown, there are two curves, each of which requires 4 control points. Since only the acceleration information of the starting point and the end point is known, the other two control points take the adjacent information, as shown in the control points (t0, a0), (t1, am) and (t2, ae) in the figure. (t1, am) can be used as the end point of the first Bezier curve and the starting point of the second Bezier curve at the same time, for a total of 4 control points. According to the kinematic relationship of the lateral velocity, the following equation can be calculated:

[0081]

[0082] Where a0 is the lateral acceleration at the starting point, a m is the lateral acceleration of the end point of the first Bezier curve, which is the lateral acceleration of the starting point of the second Bezier curve. e is the lateral acceleration of the end point. In ELK trajectory planning, the lateral acceleration of the end point is set to 0. Assuming that the planning time of the two Bezier curves is the same, d t Represents the planning time of each Bezier curve; Δv1 and Δv2 are the lateral speed difference of the first Bezier curve and the lateral speed difference of the second Bezier curve, respectively.

[0083] According to the kinematic relationship of lateral displacement, the following equation can be calculated:

[0084]

[0085] Among them, v0, v e They are the lateral velocity of the starting point and the lateral velocity of the ending point. The lateral velocity of the ending point is set to 0 in ELK trajectory planning; Δp1 and Δp2 represent the lateral displacement difference of the first Bezier curve and the lateral displacement difference of the second Bezier curve, respectively.

[0086] According to the relationship between the velocity and displacement of the two Bezier curves, the following equation can be listed:

[0087] Δv1+Δv2-dv=0

[0088] Δp1+Δp2-dp=0

[0089] Among them, d v d p They are the lateral velocity difference between the end point and the starting point of the planned trajectory, and the lateral displacement difference between the end point and the starting point of the planned trajectory.

[0090] From the above equation we can get:

[0091]

[0092] From this, the lateral acceleration a of the end point of the first Bezier curve can be calculated mand the planning time d of each Bezier curve t When completing a m and d t By calculating , we can get two Bezier curves, that is, we can get a smooth lateral acceleration curve. The lateral acceleration curve can be integrated to get the lateral velocity curve. Finally, the lateral velocity curve can be integrated to get the lateral displacement curve, that is, we can get the planned trajectory of the Bezier curve. Figure 4 , Figure 4 The schematic diagram of the trajectory planning for the road edge scene, where Ego is the vehicle, (t0, a0) is the starting point, (t2, a e ) is the end point, delta_lat_posn is the lateral deviation between the starting point and the end point of the planned trajectory, and extra_margin_end_offset is the lateral offset of the end point of the planned trajectory from the edge of the road.

[0093] This embodiment obtains a road edge scene, and classifies the road edge scene to obtain a classification result; determines a target lateral deviation between a starting point and an end point of trajectory planning according to the classification result; obtains a starting point parameter and an end point parameter of the trajectory planning, wherein the starting point parameter at least includes a starting point lateral acceleration, and the end point parameter at least includes an end point lateral acceleration; uses the target lateral deviation, the starting point parameter, and the end point parameter as parameters of a Bezier curve to perform trajectory planning for emergency lane keeping, and obtains a target planned trajectory.

[0094] In summary, this embodiment combines various situations of road edge scenes and uses Bezier curves to perform trajectory planning for emergency lane keeping in a targeted manner, thereby improving the stability of the trajectory planning results for emergency lane keeping.

[0095] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 5 , step S20 also includes steps S201 to S204:

[0096] Step S201: determining target edges on the left side of the road and the right side of the road according to the classification result, and obtaining edge coefficients of the target edges;

[0097] It should be noted that there are lane lines and curbs in the road edge scene, and one of them needs to be determined as the target edge according to different situations.

[0098] In a feasible manner, the step of determining the target edges on the left side of the road and the right side of the road according to the classification result includes:

[0099] When the classification result is that there is only a lane line on the left side of the vehicle and only a curb on the right side, the left lane line is determined as the left target edge, and the right lane line is determined as the right target edge;

[0100] When the classification result is that there is only a lane line on the left side of the vehicle and there are both a lane line and a curb on the right side, the left lane line is determined as the left target edge, and the right target edge is determined according to the distance between the right lane line and the right curb;

[0101] When the classification result is that there is only a curb on the right side of the vehicle and no lane line or curb on the left side, the right curb is determined as the right target edge, and there is no left target edge;

[0102] When the classification result is that there are both a lane line and a curb with a spacing less than a preset value on the right side of the vehicle and there is no lane line or curb on the left side, the right lane line is determined as the right target edge, and there is no left target edge;

[0103] When the classification result is that there are lane lines and curbs on the right side of the vehicle at a distance not less than a preset value and there are no lane lines or curbs on the left side, the right curb is determined as the right target edge, and there is no left target edge.

[0104] It is understandable that the road edge scenario 1 is that only the lane line on the left side of the vehicle and only the curb on the right side is used as reference. Figure 6 , Figure 6 This is a schematic diagram of trajectory planning for the road edge scenario 1. Ego represents the vehicle, the dotted line represents the lane line, and the solid line represents the road edge. When the left lane line quality LaneLeft_Quality is greater than 0 and the right road edge quality EdgeRight_Quality is greater than 0, the left lane line is used as the reference line to obtain the lateral distance lane_offset_left of the vehicle relative to the left lane line and the lateral distance edge_offset_right of the vehicle relative to the right road edge:

[0105] lane_offset_left=c0_lane_left*cos(-actan(c1_lane_left))

[0106] edge_offset_right=c0_roadedge_right*cos(-actan(c1_roadedge_right))

[0107] Among them, c0_lane_left is the coefficient c0 of the left lane line curve, which indicates the lateral distance from the center of the vehicle to the lane line, c1_lane_left is the coefficient c1 of the left lane line curve, which indicates the vehicle heading angle at the starting point, c0_roadedge_right is the coefficient c0 of the right road edge curve, and c1_roadedge_right is the coefficient c1 of the right road edge curve. Then the distance lat_dist_lane_edge between the lane line and the road edge can be obtained as:

[0108] lat_dist_lane_edge=edge_offset_right-lane_offset_left

[0109] Then the lateral deviation delta_lat_posn between the starting point and the end point of the planned trajectory can be calculated:

[0110] delta_lat_posn=-(lat_dist_lane_edge+lane_offset_left+extra_margin_end_offset)

[0111] Roadside scene 1: The lateral velocity v0 of the starting point and the lateral velocity v of the ending point are known. e , the lateral acceleration at the starting point is a0, and the lateral acceleration at the end point is a e , the lateral velocity difference d between the end point and the start point v =v e -v0, the lateral deviation d between the starting point and the end point of the planned trajectory p =delta_lat_posn, the planned trajectory of the road edge scene 1 can be obtained.

[0112] The second road edge scenario is that there is only a lane line on the left side of the vehicle and both a lane line and a curb on the right side. Figure 7 , Figure 7 This is a schematic diagram of trajectory planning for the road edge scenario 2. Ego represents the vehicle, the dotted line represents the lane line, and the solid line represents the road edge. There are two cases: when the left lane line quality LaneLeft_Quality is greater than 0, the right lane line quality LaneRight_Quality is greater than 0, the right road edge quality EdgeRight_Quality is greater than 0, and:

[0113] |c0_lane_right-c0_roadedge_right|<=Cal_k_ELK_LaneEdgeLateralError

[0114] Among them, c0_lane_right is the right lane line coefficient c0, c0_roadedge_right is the right road edge coefficient c0, Cal_k_ELK_LaneEdgeLateralError is the distance threshold between the right lane line coefficient c0_lane_right and the right road edge coefficient c0_roadedge_right. At this time, the right lane line is actually regarded as the real road edge and offset by a certain lateral displacement

[0115] Cal_k_ELK_LaneOffset, that is, the road edge related parameters are as follows:

[0116] c0_roadedge_right=c0_lane_right-Cal_k_ELK_LaneOffset

[0117] c1_roadedge_right=c1_lane_right

[0118] c2_roadedge_right=c2_lane_right

[0119] c3_roadedge_right=c3_lane_right

[0120] Among them, c0_lane_right is the right lane line coefficient c0, c1_lane_right is the right lane line coefficient c1, c2_lane_right is the right lane line coefficient c2, c3_lane_right is the right lane line coefficient c3; c0_roadedge_right is the right road edge coefficient c0, c1_roadedge_right is the right road edge coefficient c1, c2_roadedge_right is the right road edge coefficient c2, c3_roadedge_right is the right road edge coefficient c3.

[0121] Then we can obtain the lateral distance lane_offset_right of the vehicle relative to the left lane line and the lateral distance edge_offset_right of the vehicle relative to the right road edge:

[0122] lane_offset_left=c0_lane_left*cos(-actan(c1_lane_left))

[0123] edge_offset_right=c0_roadedge_right*cos(-actan(c1_roadedge_right))

[0124] Since the lane line has high quality and good stability, the left lane line is used as the reference line, and the distance lat_dist_lane_edge between the lane line and the road edge can be obtained as:

[0125] lat_dist_lane_edge=edge_offset_right-lane_offset_left

[0126] Then the lateral deviation delta_lat_posn between the starting point and the end point of the planned trajectory can be calculated:

[0127] delta_lat_posn=-(lat_dist_lane_edge+lane_offset_left+extra_margin_end_offset)

[0128] When the left lane quality LaneLeft_Quality is greater than 0, the right lane quality LaneRight_Quality is greater than 0, the right road edge quality EdgeRight_Quality is greater than 0, and:

[0129] |c0_lane_right-c0_roadedge_right|>Cal_k_ELK_LaneEdgeLateralError

[0130] At this time, the right side of the road is regarded as the actual road edge, and the right lane line is regarded as non-existent, that is, the relevant parameters of the road edge are as follows:

[0131] c0_lane_right=0

[0132] c1_lane_right=0

[0133] c2_lane_right=0

[0134] c3_lane_right=0

[0135] At this time, since the lane line has high quality and good stability, the left lane line is used as the reference line, and the lateral deviation delta_lat_posn between the starting point and the end point of the planned trajectory can be calculated:

[0136] delta_lat_posn=-(lat_dist_lane_edge+lane_offset_left+extra_margin_end_offset)

[0137] Roadside scenario 2: The lateral velocity v0 of the starting point and the lateral velocity v of the ending point are known.e , the lateral acceleration at the starting point is a0, and the lateral acceleration at the end point is a e , the lateral velocity difference d between the end point and the start point v =v e -v0, the lateral deviation d between the starting point and the end point of the planned trajectory p =delta_lat_posn, the planned trajectory of the road edge scenario 2 can be obtained.

[0138] The road edge scenario 3 is that there is only a curb on the right side of the vehicle and no lane line or curb on the left side. Figure 8 , Figure 8 The figure is a schematic diagram of trajectory planning for the road edge scenario three. Ego represents the vehicle, the dotted line represents the lane line, and the solid line represents the road edge.

[0139] At this time, when only the right road edge quality EdgeRight_Quality is greater than 0, the lateral deviation delta_lat_posn between the starting point and the end point of the planned trajectory can be calculated:

[0140] delta_lat_posn=-(edge_offset_right+extra_margin_end_offset)

[0141] Among them, edge_offset_right is the distance from the vehicle to the right edge of the road.

[0142] Road edge scene 3: The starting point lateral velocity is 0, and the ending point lateral velocity is v e , the lateral acceleration at the starting point is a0, and the lateral acceleration at the end point is a e , the lateral velocity difference d between the end point and the start point v =v e -v0, the lateral deviation d between the starting point and the end point of the planned trajectory p =delta_lat_posn, the planned trajectory of the road edge scenario three can be obtained.

[0143] The fourth scenario is that there is only a lane line on the left side of the vehicle and there is both a lane line and a curb on the right side. Fig. 9 , Fig. 9 The figure is a schematic diagram of trajectory planning for the road edge scenario 4. Ego represents the vehicle, the dotted line represents the lane line, and the solid line represents the road edge.

[0144] At this time, when the right lane line quality LaneLeft_Quality is greater than 0, the right road edge quality EdgeRight_Quality is greater than 0, and:

[0145] |c0_lane_right-c0_roadedge_right|<=Cal_k_ELK_LaneEdgeLateralError

[0146] The right lane line is actually regarded as the real road edge, and a certain lateral displacement Cal_k_ELK_LaneOffset is offset, that is, the road edge related parameters are as follows:

[0147] c0_roadedge_right=c0_lane_right-Cal_k_ELK_LaneOffset

[0148] c1_roadedge_right=c1_lane_right

[0149] c2_roadedge_right=c2_lane_right

[0150] c3_roadedge_right=c3_lane_right

[0151] Since the lane line has high quality and good stability, the left lane line is used as the reference line to obtain the lateral distance edge_offset_right of the vehicle relative to the right edge of the road:

[0152] edge_offset_right=c0_roadedge_right*cos(-actan(c1_roadedge_right))

[0153] Then the lateral deviation delta_lat_posn between the starting point and the end point of the planned trajectory can be calculated:

[0154] delta_lat_posn=-(edge_offset_right+extra_margin_end_offset)

[0155] Roadside scenario 4: The lateral velocity v0 of the starting point and the lateral velocity v of the ending point are known. e , the lateral acceleration at the starting point is a0, and the lateral acceleration at the end point is a e , the lateral velocity difference d between the end point and the start point v =v e -v0, the lateral deviation d between the starting point and the end point of the planned trajectory p =delta_lat_posn, the planned trajectory of the road edge scenario 4 can be obtained.

[0156] The road edge scenario 5 is a scenario where only lane lines exist on the left side of the vehicle and both lane lines and curb exist on the right side. Fig.10 , Fig.10 This is a schematic diagram of trajectory planning for road edge scenario five. Ego represents the vehicle, the dotted line represents the lane line, and the solid line represents the road edge.

[0157] When the right lane line quality LaneLeft_Quality is greater than 0, the right road edge quality EdgeRight_Quality is greater than 0, and:

[0158] |c0_lane_right-c0_roadedge_right|>Cal_k_ELK_LaneEdgeLateralError

[0159] The right road edge is regarded as the actual road edge, and the right lane line is regarded as non-existent to avoid premature activation of the road edge scene. Then, the lateral deviation delta_lat_posn between the starting point and the end point of the planned trajectory can be calculated:

[0160] delta_lat_posn=-(edge_offset_right+extra_margin_end_offset)

[0161] Roadside scene 5: The lateral velocity v0 of the starting point and the lateral velocity v of the ending point are known. e , the lateral acceleration at the starting point is a0, and the lateral acceleration at the end point is a e , the lateral velocity difference d between the end point and the start point v =v e -v0, the lateral deviation d between the starting point and the end point of the planned trajectory p =delta_lat_posn, the planned trajectory of road edge scene 5 can be obtained.

[0162] Step S202: obtaining the lateral distance between the vehicle and the target edge;

[0163] It should be noted that after determining the target edge of the road edge scene, the lateral distance between the vehicle and the target edge can be directly obtained for subsequent calculations. The lateral distance here can include the lateral distance between the vehicle and the left target edge and the lateral distance between the vehicle and the right target edge.

[0164] Step S203: obtaining a preset lateral offset between the end point of trajectory planning and the target edge;

[0165] It is understandable that the preset lateral offset of the end point of trajectory planning from the target edge is an important parameter for calculating trajectory planning. In order to cope with the lateral deviation correction capability of the ELK function at different lateral speeds, this embodiment uses the lateral offset of the end point of the planned trajectory from the road edge as extra_margin_end_offset as a calibration value, which is related to the lateral speed of the vehicle relative to the road edge. The lateral offset of the end point of the planned trajectory from the road edge is obtained by one-dimensional table interpolation. The specific relationship is as follows:

[0166] vlat_elka_edge=max(abs(vlat_left_edge),abs(vlat_right_edge))

[0167] extra_margin_end_offset=Interp(vlat_elka_edge,InterpX,InterpY,size_of_table)

[0168] Among them, vlat_left_edge and vlat_right_edge are the lateral speed of the vehicle relative to the left edge of the road and the lateral speed of the vehicle relative to the right edge of the road respectively, vlat_elka_edge is the maximum value of the lateral speed of the vehicle relative to the left and right edges of the road, and is also the input of the one-dimensional interpolation table lookup. The one-dimensional interpolation table lookup value dimension size_of_table is 3, the input query value lateral speed is [vlat_value1, vlat_value2, vlat_value3], and the corresponding output query value is: [extra_margin_value1, extra_margin_value2, extra_margin_value3].

[0169] Step S204: determining a target lateral deviation between a starting point and an end point of trajectory planning according to the edge coefficient, the lateral distance and the preset lateral offset.

[0170] After the lateral distance is obtained, the target lateral deviation between the starting point and the end point of the trajectory planning can be determined according to the edge coefficient, the lateral distance and the preset lateral offset.

[0171] This embodiment determines the target edges on the left side and the right side of the road based on the classification result, and obtains the edge coefficient of the target edge; obtains the lateral distance between the vehicle and the target edge; obtains the preset lateral offset of the end point of trajectory planning from the target edge; and determines the target lateral deviation between the starting point and the end point of trajectory planning based on the edge coefficient, the lateral distance and the preset lateral offset.

[0172] In summary, this embodiment determines the lateral distance between the vehicle and the road edge in different situations through the classification results of the road edge scene, so as to facilitate subsequent trajectory planning, thereby improving the stability of the trajectory planning results of emergency lane keeping.

[0173] This application also provides a trajectory planning device for emergency lane keeping based on Bezier curves, please refer to Fig.11 , the trajectory planning device for emergency lane keeping based on Bezier curve includes:

[0174] The classification module 10 is used to obtain a road edge scene and classify the road edge scene to obtain a classification result;

[0175] A determination module 20, for determining a target lateral deviation between a starting point and an end point of trajectory planning according to the classification result;

[0176] An acquisition module 30, used to acquire the starting point parameters and the end point parameters of the trajectory planning, wherein the starting point parameters at least include the starting point lateral acceleration, and the end point parameters at least include the end point lateral acceleration;

[0177] The planning module 40 is used to perform trajectory planning for emergency lane keeping by using the target lateral deviation, the starting point parameter and the end point parameter as parameters of a Bezier curve to obtain a target planned trajectory.

[0178] This embodiment obtains a road edge scene, and classifies the road edge scene to obtain a classification result; determines a target lateral deviation between a starting point and an end point of trajectory planning according to the classification result; obtains a starting point parameter and an end point parameter of the trajectory planning, wherein the starting point parameter at least includes a starting point lateral acceleration, and the end point parameter at least includes an end point lateral acceleration; uses the target lateral deviation, the starting point parameter, and the end point parameter as parameters of a Bezier curve to perform trajectory planning for emergency lane keeping, and obtains a target planned trajectory.

[0179] In summary, this embodiment combines various situations of road edge scenes and performs targeted trajectory planning for emergency lane keeping through Bezier curves, thereby improving the stability of the trajectory planning results for emergency lane keeping.

[0180] In one embodiment, the determination module 20 is also used to determine the target edges on the left side and the right side of the road based on the classification results, and obtain the edge coefficient of the target edge; obtain the lateral distance between the vehicle and the target edge; obtain the preset lateral offset of the end point of trajectory planning from the target edge; determine the target lateral deviation between the starting point and the end point of trajectory planning based on the edge coefficient, the lateral distance and the preset lateral offset.

[0181] In one embodiment, the determination module 20 is further configured to, when the classification result is that there is only a lane line on the left side of the vehicle and only a curb on the right side, determine the left lane line as the left target edge and the right lane line as the right target edge; when the classification result is that there is only a lane line on the left side of the vehicle and there are both a lane line and a curb on the right side, determine the left lane line as the left target edge, and determine the right target edge according to the distance between the right lane line and the right curb; when the classification result is that there is only a curb on the right side of the vehicle and there is no lane line or curb on the left side, determine the right curb as the right target edge and there is no left target edge; when the classification result is that there are both a lane line and a curb with an interval less than a preset value on the right side of the vehicle and there is no lane line or curb on the left side, determine the right lane line as the right target edge and there is no left target edge; when the classification result is that there are both a lane line and a curb with an interval not less than a preset value on the right side of the vehicle and there is no lane line or curb on the left side, determine the right curb as the right target edge and there is no left target edge.

[0182] In one embodiment, the determination module 20 is further used to obtain the left lateral speed of the vehicle relative to the target edge on the left side of the road, the right lateral speed of the vehicle relative to the target edge on the right side of the road, the maximum left lateral speed of the vehicle relative to the target edge on the left side of the road, and the maximum right lateral speed of the vehicle relative to the target edge on the right side of the road; determine the preset lateral offset of the target edge based on the left lateral speed, the right lateral speed, the maximum left lateral speed, and the maximum right lateral speed.

[0183] In one embodiment, the planning module 40 is further used to determine a lateral acceleration Bezier curve through the target lateral deviation, the starting point parameter and the end point parameter; integrate the lateral acceleration Bezier curve twice to obtain a lateral displacement Bezier curve, and obtain a target planning trajectory.

[0184] In one embodiment, the planning module 40 is further used to determine the starting point and end point of the lateral acceleration Bezier curve according to the starting point parameter and the end point parameter; and determine the lateral acceleration Bezier curve according to the curve starting point, the curve end point and the target lateral deviation.

[0185] In one embodiment, the planning module 40 is further used to calculate the lateral acceleration of the end point of the first Bezier curve, the lateral speed difference of the first Bezier curve, and the lateral speed difference of the second Bezier curve through the starting point of the curve, the end point of the curve, and the target lateral deviation; and determine the lateral acceleration Bezier curve according to the lateral acceleration of the end point, the lateral speed difference of the first Bezier curve, and the lateral speed difference of the second Bezier curve.

[0186] The trajectory planning device for emergency lane keeping based on Bezier curves provided in the present application adopts the trajectory planning method for emergency lane keeping based on Bezier curves in the above-mentioned embodiments, which can solve the technical problem of how to improve the stability of the trajectory planning results of emergency lane keeping. Compared with the prior art, the beneficial effects of the trajectory planning device for emergency lane keeping based on Bezier curves provided in the present application are the same as the beneficial effects of the trajectory planning method for emergency lane keeping based on Bezier curves provided in the above-mentioned embodiments, and the other technical features of the trajectory planning device for emergency lane keeping based on Bezier curves are the same as the features disclosed in the above-mentioned embodiment methods, which will not be repeated here.

[0187] The present application provides a trajectory planning device for emergency lane keeping based on Bezier curves, and the trajectory planning device for emergency lane keeping based on Bezier curves includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the trajectory planning method for emergency lane keeping based on Bezier curves in the above-mentioned embodiment one.

[0188] Reference below Fig.12 , which shows a schematic diagram of the structure of a trajectory planning device for emergency lane keeping based on Bezier curves suitable for implementing the embodiment of the present application. The trajectory planning device for emergency lane keeping based on Bezier curves in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.12 The trajectory planning device for emergency lane keeping based on Bezier curves shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0189] like Fig.12As shown, the trajectory planning device for emergency lane keeping based on Bezier curves may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the trajectory planning device for emergency lane keeping based on Bezier curves are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the trajectory planning device for emergency lane keeping based on Bezier curves to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a trajectory planning device for emergency lane keeping based on Bezier curves with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0190] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0191] The trajectory planning device for emergency lane keeping based on Bezier curves provided in the present application adopts the trajectory planning method for emergency lane keeping based on Bezier curves in the above-mentioned embodiments, which can solve the technical problem of how to improve the stability of the trajectory planning results for emergency lane keeping. Compared with the prior art, the beneficial effects of the trajectory planning device for emergency lane keeping based on Bezier curves provided in the present application are the same as the beneficial effects of the trajectory planning method for emergency lane keeping based on Bezier curves provided in the above-mentioned embodiments, and the other technical features in the trajectory planning device for emergency lane keeping based on Bezier curves are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0192] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0193] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0194] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the trajectory planning method for emergency lane keeping based on Bezier curves in the above-mentioned embodiment.

[0195] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0196] The computer-readable storage medium may be included in the trajectory planning device for emergency lane keeping based on Bezier curves; or may exist independently without being assembled into the trajectory planning device for emergency lane keeping based on Bezier curves.

[0197] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a trajectory planning device for emergency lane keeping based on a Bezier curve, the trajectory planning device for emergency lane keeping based on a Bezier curve: obtains a road edge scene, and classifies the road edge scene to obtain a classification result; determines a target lateral deviation between a starting point and an end point of trajectory planning according to the classification result; obtains a starting point parameter and an end point parameter of the trajectory planning, wherein the starting point parameter at least includes a starting point lateral acceleration, and the end point parameter at least includes an end point lateral acceleration; uses the target lateral deviation, the starting point parameter and the end point parameter as parameters of the Bezier curve to perform trajectory planning for emergency lane keeping to obtain a target planning trajectory.

[0198] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0199] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0200] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0201] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned trajectory planning method for emergency lane keeping based on Bezier curves, and can solve the technical problem of how to improve the stability of the trajectory planning results of emergency lane keeping. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the trajectory planning method for emergency lane keeping based on Bezier curves provided by the above-mentioned embodiments, and will not be repeated here.

[0202] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned Bezier curve-based emergency lane keeping trajectory planning method.

[0203] The computer program product provided by the present application can solve the technical problem of how to improve the stability of the trajectory planning results of emergency lane keeping. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the trajectory planning method for emergency lane keeping based on Bezier curves provided in the above-mentioned embodiment, which will not be repeated here.

[0204] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A trajectory planning method for emergency lane keeping based on Bezier curve, characterized in that: The method includes: Acquire a road edge scene, and classify the road edge scene to obtain a classification result; Determine the target lateral deviation between the starting point and the end point of the trajectory planning according to the classification result; Acquire the starting point parameters and the end point parameters of the trajectory planning, wherein the starting point parameters at least include the starting point lateral acceleration, and the end point parameters at least include the end point lateral acceleration; The target lateral deviation, the starting point parameter and the end point parameter are used as parameters of a Bezier curve to perform trajectory planning for emergency lane keeping, so as to obtain a target planning trajectory.

2. The method according to claim 1, characterized in that The step of determining the target lateral deviation between the starting point and the end point of the trajectory planning according to the classification result comprises: According to the classification result, determining target edges on the left side of the road and the right side of the road, and obtaining edge coefficients of the target edges; Obtaining a lateral distance between the vehicle and the target edge; Obtaining a preset lateral offset of an end point of trajectory planning from an edge of the target; A target lateral deviation between a starting point and an end point of trajectory planning is determined according to the edge coefficient, the lateral distance, and the preset lateral offset.

3. The method according to claim 2, characterized in that The step of determining the target edges on the left side of the road and the right side of the road according to the classification result comprises: When the classification result is that there is only a lane line on the left side of the vehicle and only a curb on the right side, the left lane line is determined as the left target edge, and the right lane line is determined as the right target edge; When the classification result is that there is only a lane line on the left side of the vehicle and there are both a lane line and a curb on the right side, the left lane line is determined as the left target edge, and the right target edge is determined according to the distance between the right lane line and the right curb; When the classification result is that there is only a curb on the right side of the vehicle and no lane line or curb on the left side, the right curb is determined as the right target edge, and there is no left target edge; When the classification result is that there are both a lane line and a curb with a spacing less than a preset value on the right side of the vehicle and there is no lane line or curb on the left side, the right lane line is determined as the right target edge, and there is no left target edge; When the classification result is that there are lane lines and curbs on the right side of the vehicle at a distance not less than a preset value and there are no lane lines or curbs on the left side, the right curb is determined as the right target edge, and there is no left target edge.

4. The method according to claim 2, characterized in that The step of obtaining a preset lateral offset of the end point of trajectory planning from the target edge comprises: Obtaining a left lateral speed of the vehicle relative to a target edge on the left side of the road, a right lateral speed of the vehicle relative to a target edge on the right side of the road, a maximum value of the left lateral speed of the vehicle relative to the target edge on the left side of the road, and a maximum value of the right lateral speed of the vehicle relative to the target edge on the right side of the road; A preset lateral offset of the target edge is determined according to the left lateral velocity, the right lateral velocity, the left lateral velocity maximum value, and the right lateral velocity maximum value.

5. The method according to claim 1, characterized in that The step of using the target lateral deviation, the starting point parameter and the end point parameter as parameters of the Bezier curve to perform trajectory planning for emergency lane keeping to obtain the target planning trajectory comprises: Determine a lateral acceleration Bezier curve according to the target lateral deviation, the starting point parameter and the end point parameter; The lateral acceleration Bezier curve is integrated twice to obtain a lateral displacement Bezier curve, and the target planning trajectory is obtained.

6. The method according to claim 5, characterized in that The step of determining the lateral acceleration Bezier curve by using the target lateral deviation, the starting point parameter and the end point parameter comprises: Determine a curve starting point and a curve end point of a lateral acceleration Bezier curve according to the starting point parameter and the end point parameter; A lateral acceleration Bezier curve is determined according to the curve starting point, the curve end point and the target lateral deviation.

7. The method according to claim 6, characterized in that The step of determining the lateral acceleration Bezier curve according to the curve starting point, the curve end point and the target lateral deviation comprises: Calculating the lateral acceleration of the end point of the first Bezier curve, the lateral speed difference of the first Bezier curve, and the lateral speed difference of the second Bezier curve through the starting point of the curve, the end point of the curve, and the target lateral deviation; A lateral acceleration Bezier curve is determined according to the end point lateral acceleration, the lateral speed difference of the first Bezier curve, and the lateral speed difference of the second Bezier curve.

8. A trajectory planning device for emergency lane keeping based on Bezier curve, characterized in that: The device comprises: A classification module, used to obtain a road edge scene, and classify the road edge scene to obtain a classification result; A determination module, used to determine a target lateral deviation between a starting point and an end point of trajectory planning according to the classification result; An acquisition module, used to acquire the starting point parameters and the end point parameters of the trajectory planning, wherein the starting point parameters at least include the starting point lateral acceleration, and the end point parameters at least include the end point lateral acceleration; The planning module is used to perform trajectory planning for emergency lane keeping by using the target lateral deviation, the starting point parameter and the end point parameter as parameters of a Bezier curve to obtain a target planning trajectory.

9. A trajectory planning device for emergency lane keeping based on Bezier curve, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the Bezier curve-based emergency lane keeping trajectory planning method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the trajectory planning method for emergency lane keeping based on Bezier curves according to any one of claims 1 to 7 is implemented.

Images