Automatic driving vehicle trajectory planning method, device and equipment and storage medium

Abstract

The invention discloses an automatic driving vehicle track planning method and device, equipment and a storage medium, and relates to the technical field of path planning, and the method comprises the steps: determining a target lane; the target lane is converted into a target coordinate system according to the lane center line of the target lane, the ordinate of the target coordinate system is the arc length, and the abscissa of the target coordinate system is the transverse offset; sampling along the longitudinal coordinate direction of the target coordinate system at a preset resolution to obtain a plurality of track sampling points; and planning and analyzing the trajectory sampling points to obtain a target path under the target coordinate system, thereby avoiding the situation that the vehicle head rushes out of the road boundary due to the planned path.

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to a method, device, equipment and storage medium for trajectory planning of an autonomous driving vehicle. Background Art

[0002] The task of trajectory planning for autonomous vehicles is to calculate a collision-free, safe and drivable trajectory based on map data, perception data, positioning data, vehicle status, etc. Most solutions plan a large number of trajectories through sampling, and then perform collision detection, curvature detection, etc. on the large number of trajectories to select the optimal trajectory.

[0003] However, during the design process, under the preset lane constraint boundary, due to factors such as the length of the vehicle, a risky trajectory may be planned, and it is very easy for the front of the vehicle to go out of the lane boundary and hit the curb during the lane change process.

[0004] 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

[0005] The main purpose of this application is to provide a method, device, equipment and storage medium for autonomous driving vehicle trajectory planning, aiming to solve the technical problem that the length of the vehicle causes the front of the vehicle to run out of the road boundary due to the planned path.

[0006] To achieve the above objectives, the present application proposes a method for autonomous driving vehicle trajectory planning, the method comprising:

[0007] Determine the target lane;

[0008] The target lane is converted into a target coordinate system based on the lane centerline of the target lane, wherein the ordinate of the target coordinate system is the arc length and the abscissa is the lateral offset;

[0009] Sampling along the ordinate direction of the target coordinate system at a preset resolution to obtain a plurality of trajectory sampling points;

[0010] The trajectory sampling points are planned and analyzed to obtain the target path in the target coordinate system.

[0011] In one embodiment, the step of performing planning analysis on the trajectory sampling points to obtain the target path in the target coordinate system includes:

[0012] Based on the quadratic programming strategy, determine the target optimization function;

[0013] Acquire vehicle information, and determine target vehicle constraint conditions based on the vehicle information, wherein the target vehicle constraint conditions include lateral boundary constraints, upper and lower boundary constraints, heading angle constraints, and curvature constraints;

[0014] The trajectory sampling points are processed based on the target optimization function and the target vehicle constraint conditions to obtain a target path in the target coordinate system.

[0015] In one embodiment, the step of obtaining vehicle information and determining the target vehicle constraint condition based on the vehicle information includes:

[0016] Determine a lane change state of the vehicle based on the vehicle information, the lane change state of the vehicle including the vehicle changing lanes to the left and the vehicle changing lanes to the right;

[0017] determining a left lane restriction and a right lane restriction based on the vehicle lane change state;

[0018] Determine a lateral boundary constraint and an upper and lower boundary constraint of the target coordinate system based on the left lane constraint and the right lane constraint;

[0019] Determining a heading angle constraint based on a lateral boundary constraint and an upper and lower boundary constraint of the target coordinate system;

[0020] A curvature constraint is determined based on the heading angle constraint.

[0021] In one embodiment, the step of determining the left lane constraint and the right lane constraint based on the vehicle lane change state includes:

[0022] When determining that the lane change state of the vehicle is that the vehicle is changing lanes to the left, obtaining a set lateral offset of the left lane of the target coordinate system;

[0023] Determine the inclination angle of the vehicle along the longitudinal axis direction of the target coordinate system, the distance from the center of the rear axle of the vehicle to the front of the vehicle, and the width of the vehicle to determine the offset of the left front point of the vehicle relative to the center line of the left lane based on the vehicle information;

[0024] A left lane constraint of the target vehicle constraint condition is determined based on a set lateral offset of the left lane of the target coordinate system and an offset of the left front point of the vehicle relative to a center line of the left lane.

[0025] In one embodiment, the step of determining the left lane constraint and the right lane constraint based on the vehicle lane change state includes:

[0026] When determining that the lane change state of the vehicle is that the vehicle is changing lanes to the right, obtaining a set lateral offset of the right lane of the target coordinate system;

[0027] Based on the vehicle information, determine the inclination angle of the vehicle along the longitudinal axis direction of the target coordinate system, the distance from the center of the rear axle of the vehicle to the front of the vehicle, and the vehicle width to determine the offset of the right front point of the vehicle relative to the center line of the right lane;

[0028] A right lane constraint of the target vehicle constraint condition is determined based on a set lateral offset of the right lane of the target coordinate system and an offset of the right front point of the vehicle relative to a center line of the right lane.

[0029] In one embodiment, the step of processing the trajectory sampling points based on the target optimization function and the target vehicle constraint condition to obtain the target path in the target coordinate system includes:

[0030] Establishing a quadratic programming formula based on the target optimization function and the target vehicle constraint condition;

[0031] The trajectory sampling points are processed by the quadratic programming formula to obtain the target path in the target coordinate system.

[0032] In one embodiment, the step of processing the trajectory sampling points by using the quadratic programming formula to obtain the target path in the target coordinate system includes:

[0033] The trajectory sampling points are processed by the quadratic programming formula to obtain a lateral offset constraint, a lateral offset first-order derivative constraint, and a lateral offset second-order derivative constraint corresponding to each trajectory sampling point;

[0034] Determining the arc length of each trajectory sampling point according to the preset resolution;

[0035] The target path in the target coordinate system is obtained according to the lateral offset constraint, the lateral offset first-order derivative constraint, the lateral offset second-order derivative constraint and the arc length corresponding to each trajectory sampling point.

[0036] In addition, to achieve the above objectives, the present application also proposes a trajectory planning device for an autonomous driving vehicle, the device comprising:

[0037] A lane determination module, used to determine a target lane;

[0038] A coordinate system conversion module, used to convert the target lane into a target coordinate system based on the lane centerline of the target lane, wherein the ordinate of the target coordinate system is the arc length and the abscissa is the lateral offset;

[0039] A sampling module, used for sampling along the ordinate direction of the target coordinate system at a preset resolution to obtain a plurality of trajectory sampling points;

[0040] The trajectory planning module is used to plan and analyze the trajectory sampling points to obtain the target path in the target coordinate system.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes an autonomous driving vehicle trajectory planning device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the autonomous driving vehicle trajectory planning method as described above.

[0042] 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 the processor, the steps of the autonomous driving vehicle trajectory planning method as described above are implemented.

[0043] 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 autonomous driving vehicle trajectory planning method as described above.

[0044] One or more technical solutions proposed in this application have at least the following technical effects:

[0045] Determine the target lane; transform the target lane into the target coordinate system based on the lane centerline of the target lane, wherein the ordinate of the target coordinate system is the arc length and the abscissa is the lateral offset; perform sampling along the ordinate direction of the target coordinate system at a preset resolution to obtain a number of trajectory sampling points; perform planning and analysis on the trajectory sampling points to obtain a target path in the target coordinate system, and establish a quadratic programming formula through the target optimization function and the target vehicle constraint conditions during the analysis process; process the trajectory sampling points through the quadratic programming formula, consider the impact of the vehicle's contour, and obtain the target path in the target coordinate system to avoid the situation where the planned path causes the vehicle head to run out of the road boundary. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] 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.

[0047] 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.

[0048] Figure 1 A flowchart of the first embodiment of the method for trajectory planning of an autonomous driving vehicle of the present application;

[0049] Figure 2 A schematic diagram of converting a lane into a Frenet coordinate system based on the lane centerline provided in Example 1 of the autonomous driving vehicle trajectory planning method of the present application;

[0050] Figure 3 A schematic diagram of sampling of the Frenet coordinate system provided for the first embodiment of the autonomous driving vehicle trajectory planning method of the present application;

[0051] Figure 4 A flowchart diagram of the second embodiment of the method for trajectory planning of an autonomous driving vehicle of the present application;

[0052] Figure 5 A schematic diagram of the Frenet coordinate system for a vehicle left lane change scenario provided in Example 2 of the autonomous driving vehicle trajectory planning method of this application;

[0053] Figure 6 A flowchart diagram of the third embodiment of the autonomous driving vehicle trajectory planning method of the present application;

[0054] Figure 7 This is a schematic diagram of the module structure of the autonomous driving vehicle trajectory planning device according to an embodiment of the present application;

[0055] Figure 8 Schematic diagram of the device structure of the hardware operating environment involved in the autonomous driving vehicle trajectory planning method in the embodiment of the present application.

[0056] 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

[0057] 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.

[0058] 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.

[0059] 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, an autonomous driving vehicle trajectory planning device, etc. The following takes the autonomous driving vehicle trajectory planning device as an example to illustrate this embodiment and the following embodiments.

[0060] Based on this, the present application embodiment provides a method for autonomous driving vehicle trajectory planning, referring to Figure 1 , Figure 1This is a flow chart of the first embodiment of the autonomous driving vehicle trajectory planning device method of the present application.

[0061] In this embodiment, the autonomous driving vehicle trajectory planning device method includes steps S10 to S40:

[0062] Step S10, determining the target lane;

[0063] It should be noted that the target lane is the lane area where the vehicle is traveling.

[0064] Step S20, converting the target lane into a target coordinate system based on the lane centerline of the target lane, wherein the ordinate of the target coordinate system is the arc length and the abscissa is the lateral offset;

[0065] It should be noted that in order to adapt to different road shapes, the Frenet coordinate system is introduced, such as Figure 2 As shown, Figure 2 In order to convert the lane into a Frenet coordinate system diagram based on the lane centerline (the tangent direction along the lane centerline is the longitudinal s direction, and the perpendicular tangent direction is the lateral l direction, also known as the sl coordinate system), the vehicle path planning problem is converted into the longitudinal position (arc length s) and lateral offset (offset l) along the curve, which makes the planning process more intuitive and simplified.

[0066] It should be understood that the target coordinate system, namely the Frenet coordinate system, is a coordinate system commonly used in autonomous driving and trajectory planning, which can more intuitively represent the position and motion state of the vehicle on a curved road.

[0067] Step S30, sampling along the ordinate direction of the target coordinate system at a preset resolution to obtain a plurality of trajectory sampling points;

[0068] It should be noted that the preset resolution is Δs. Taking Δs as the resolution refers to the interval or step size used when discretizing the path in the longitudinal direction (s direction) along the centerline of the lane. Δs is a fixed unit of length, which is used to represent the distance between adjacent sampling points on the s axis (longitudinal direction) in the Frenet coordinate system.

[0069] It should be understood that the smaller the value of Δs is, the closer the distance between the sampling points is, and the denser the sampling of the path is, so that a more precise path planning result can be obtained. On the contrary, the larger the value of Δs is, the farther the distance between the sampling points is, and the accuracy of path planning will decrease.

[0070] In the specific implementation, sampling is performed along the s direction of the sl coordinate system in the vehicle driving lane area with a resolution of Δs. In the conventional obstacle-free situation, the target trajectory reference point is along the lane centerline, and in some scenarios affected by obstacles, the reference point will be laterally offset.

[0071] like Figure 3 As shown in FIG. 1 , when there is no obstacle, the trajectory sampling point is on the center line of the lane. When there is an obstacle, the trajectory sampling point will be offset to the positions on both sides of the center line of the lane.

[0072] Step S40, planning and analyzing the trajectory sampling points to obtain the target path in the target coordinate system.

[0073] It should be noted that planning analysis is quadratic programming analysis, which explicitly defines the objective function and constraints of the optimization problem and ensures that they conform to the standard form of quadratic programming. Quadratic programming is used to minimize the acceleration change (smoothness) of the vehicle path while satisfying vehicle dynamics and safety constraints.

[0074] It should be understood that the target path is a safe trajectory that satisfies the lane change while ensuring that the lane boundary is not crossed.

[0075] In a feasible implementation, step S40 may include steps A11 to A13:

[0076] Step A11: Determine the target optimization function based on the quadratic programming strategy;

[0077] In the specific implementation, refer to the quadratic programming idea and set the target optimization function:

[0078]

[0079] where x i is the lateral offset, r i is the reference offset, x i ″、x i ″、x i ″′ respectively represent the first-order derivative, second-order derivative, and third-order derivative of the lateral offset corresponding to the sample s. In order to optimize the objective function to obtain a smaller value, it is required that 1)x i ″、x i ″、x i A smaller value of ″′ means a smaller lateral change, thus making the trajectory smoother; 2) x i Closer to the reference offset point.

[0080] Step A12: Acquire vehicle information, and determine target vehicle constraint conditions based on the vehicle information, where the target vehicle constraint conditions include lateral boundary constraints, upper and lower boundary constraints, heading angle constraints, curvature constraints, and continuity constraints;

[0081] It should be noted that, based on the above sampling modeling, the risk of the vehicle outline going out of the lane boundary is solved, thus introducing the influence of the vehicle outline in the process of designing the constraint conditions. It is easier to describe this problem with a lane change scenario.

[0082] It should be understood that the lateral boundary constraint is used to limit the lateral position of the vehicle within the lane, ensuring that the vehicle does not deviate from the lane;

[0083] The upper and lower boundary constraints are used to limit the position of the vehicle in the direction perpendicular to the lane to prevent the vehicle from running off the road or colliding with the vehicle in front;

[0084] The heading angle constraint is used to limit the vehicle's heading angle change to maintain the vehicle's stability and avoid sharp turns;

[0085] Curvature constraints are used to limit the curvature of the vehicle path to ensure the safety and comfort of the vehicle when turning;

[0086] Continuity constraints are used to ensure the continuity of vehicle trajectory in time and space, including the continuity of position, velocity, acceleration, etc.

[0087] These constraints need to be adjusted according to the specific parameters of the vehicle and the driving environment. By accurately determining these constraints, it can be ensured that the autonomous vehicle can drive safely and efficiently in various situations.

[0088] It should be understood that the vehicle information includes at least the vehicle's inclination angle along the s-axis, the distance from the center of the vehicle's rear axle to the front of the vehicle, the vehicle width, the lateral distance value of the vehicle's left front corner relative to the center of the vehicle's rear axle, and other data.

[0089] Step A13: Process the trajectory sampling points based on the target optimization function and the target vehicle constraint conditions to obtain the target path in the target coordinate system.

[0090] In the specific implementation, a quadratic programming solver is used to solve the optimization problem according to the constructed mathematical model and constraints, and the lateral state value of each sampling point is obtained. After processing the sampling points, a smooth trajectory is fitted, that is, the target path.

[0091] This embodiment provides a method for trajectory planning of an autonomous driving vehicle, which determines a target lane; converts the target lane into a target coordinate system based on the lane centerline of the target lane, wherein the ordinate of the target coordinate system is the arc length and the abscissa is the lateral offset; samples are performed along the ordinate direction of the target coordinate system at a preset resolution to obtain a number of trajectory sampling points; and plans and analyzes the trajectory sampling points to obtain a target path in the target coordinate system to avoid a situation in which the planned path causes the front of the vehicle to run out of the road boundary.

[0092] 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 4 , step A12, including steps S401 to S406:

[0093] Step S401, determining a lane change state of the vehicle based on vehicle information, where the lane change state of the vehicle includes the vehicle changing lanes to the left and the vehicle changing lanes to the right;

[0094] It should be noted that, based on the above sampling modeling, the risk of the vehicle outline going out of the lane boundary is solved, thus introducing the influence of the vehicle outline in the process of designing the constraint conditions. It is easier to describe this problem with a lane change scenario, such as Figure 5 As shown, assuming that the vehicle changes lanes to the left, the sl coordinate system is established based on the center line of the left lane, and the dotted box represents a certain state of the vehicle during the lane change process.

[0095] In the figure, l is the lateral offset of the center of the vehicle's rear axle relative to the center line of the left lane, and the left side of the center line is defined as positive, and the right side of the center line is defined as negative. θ is the vehicle's inclination along the s-axis, f is the distance from the center of the vehicle's rear axle to the front of the vehicle, and w is the vehicle width. loffset is the lateral distance value of the vehicle's left front corner relative to the center of the vehicle's rear axle, which can be obtained through geometric relationships:

[0096] l offset =f*sinθ+0.5w*cosθ

[0097] In a specific implementation, it is identified whether the vehicle is currently performing a lane change operation and the direction of the lane change (left or right).

[0098] Step S402, determining a left lane constraint and a right lane constraint based on a vehicle lane change state;

[0099] In a specific implementation, the lane constraints that the vehicle needs to comply with during the lane change process are determined according to the lane change status of the vehicle.

[0100] In a feasible implementation, step S402 may include steps A21 to A23:

[0101] Step A21: When it is determined that the lane change state of the vehicle is that the vehicle is changing lanes to the left, a set lateral offset of the left lane of the target coordinate system is obtained;

[0102] It should be noted that the lateral offset is set so as not to exceed the maximum offset of the left and right lanes.

[0103] Step A22: Determine the inclination angle of the vehicle along the longitudinal axis of the target coordinate system, the distance from the center of the rear axle of the vehicle to the front of the vehicle, and the width of the vehicle to determine the offset of the left front point of the vehicle relative to the center line of the left lane based on the vehicle information;

[0104] Step A23: Determine the left lane constraint of the target vehicle constraint condition based on the set lateral offset of the left lane of the target coordinate system and the offset of the left front point of the vehicle relative to the center line of the left lane.

[0105] In the specific implementation, left =l+l offset =l+f*sinθ+0.5w*cosθ

[0106] Through transformation, we get the following formula:

[0107] l left =l+(f*tanθ+0.5w)*cosθ<=l+f*tanθ+0.5w

[0108] Among them, tanθ is the first derivative of l with respect to the s direction, that is, tanθ = l′;

[0109] Let l+f*l′+0.5w <l max , then l left <l max It is definitely true.

[0110] Therefore, we only need to set the constraint l+f*l′+0.5w <l max , the planning trajectory finally solved by the optimization function can ensure that the left front corner of the vehicle will not cross the left boundary of the road.

[0111] In another feasible implementation, step S402 may include steps A31 to A33:

[0112] Step A31: When it is determined that the lane change state of the vehicle is that the vehicle is changing lanes to the right, a set lateral offset of the right lane of the target coordinate system is obtained;

[0113] Step A32: Determine the inclination angle of the vehicle along the longitudinal axis direction of the target coordinate system, the distance from the center of the rear axle of the vehicle to the front of the vehicle, and the width of the vehicle to determine the offset of the right front point of the vehicle relative to the center line of the right lane based on the vehicle information;

[0114] Step A33: Determine the right lane constraint of the target vehicle constraint condition based on the set lateral offset of the right lane of the target coordinate system and the offset of the right front point of the vehicle relative to the center line of the right lane.

[0115] In the specific implementation, similar to the left lane constraint, the constraint condition lf*l′-0.5w>l is set during the right lane change process. min , the right front corner of the vehicle will not cross the right boundary of the road. min and l max Respectively represent the lateral offset of the left and right boundaries of the road relative to the baseline.

[0116] Step S403, determining a lateral boundary constraint and an upper and lower boundary constraints of the target coordinate system based on the left lane constraint and the right lane constraint;

[0117] In the specific implementation, the above constraint analysis is sorted out to obtain the horizontal l boundary constraint and the upper and lower boundary constraints:

[0118] l min +0.5w <l-f*l′&&l+f*l′<l max -0.5w

[0119] Step S404, determining a heading angle constraint based on the lateral boundary constraint and the upper and lower boundary constraints of the target coordinate system;

[0120] In the specific implementation, the lateral boundary constraint and the upper and lower boundary constraints are derived to obtain the first-order derivative constraint, that is, the constraint on the heading angle:

[0121] l′ min <l′<l′ max

[0122] Step S405, determining a curvature constraint based on the heading angle constraint;

[0123] In the specific implementation, the heading angle constraint is derived to obtain the second-order derivative constraint, that is, the curvature constraint, the range of which is the maximum curvature allowed by the road curvature for the vehicle:

[0124] l″ min <l″<l″ max

[0125] Furthermore, the constraints also include continuity constraints and starting point constraints.

[0126] It should be noted that the continuity constraint ensures that the vehicle trajectory is continuous in parameters such as position, velocity, acceleration, etc. to achieve a smooth driving experience and avoid sudden dynamic changes.

[0127] In the specific implementation, the continuity constraint needs to satisfy the constraints of the mathematical relationship because the Jerk of each segment is set to a constant:

[0128] ″″″′

[0129] l i+1 = l i +l i *Δs

[0130]

[0131]

[0132] ″″″

[0133] Starting point constraint, x init is the current vehicle position, x0 = x init , x0=x init , x0=xinit .

[0134] It should be noted that Jerk is the rate of change of acceleration.

[0135] This embodiment provides a method for trajectory planning of an autonomous driving vehicle. By setting constraints, the influence of the vehicle contour is considered in the algorithm constraint design process, and the function is optimized, thereby ensuring that the planned trajectory allows the vehicle to always drive safely within the lane and eliminates the risk of the vehicle hitting the curb.

[0136] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 6 , step A13, including steps S410 to S420:

[0137] Step S410, establishing a quadratic programming formula based on the target optimization function and the target vehicle constraint conditions;

[0138] In the specific implementation, the objective function and constraints can be converted into the standard form of quadratic programming;

[0139] minJ=1 / 2x T Px+Qx

[0140] st:l<=Ax<=u

[0141] Where x is in matrix form and is the set of lateral state values ​​of all sampling points

[0142] ″″″″′

[0143] x T =[l0,l0,l0,l1,l1,l1,…l n-1 ,l n-1 ,l n-1 ]

[0144] l and u are also in matrix form, which are the lateral, lateral first-order derivative, and lateral second-order derivative constraints corresponding to each sampling point. P, Q, and A are coefficient matrices.

[0145] Step S420, processing the trajectory sampling points by a quadratic programming formula to obtain a target path in a target coordinate system;

[0146] In the specific implementation, the quadratic programming solver is used to perform iterative optimization to obtain the l,l corresponding to each sampling point. ′ ,l″, and knowing s of each sampling point, we can fit the path of the sampling space in the sl coordinate system.

[0147] In a feasible implementation, step S402 may include steps A41 to A43:

[0148] Step A41: Processing the trajectory sampling points by using a quadratic programming formula to obtain a lateral offset constraint, a lateral offset first-order derivative constraint, and a lateral offset second-order derivative constraint corresponding to each trajectory sampling point;

[0149] In the specific implementation, the trajectory sampling points are processed by the quadratic programming formula to obtain the lateral offset constraint, the first-order derivative constraint of the lateral offset and the second-order derivative constraint of the lateral offset corresponding to each trajectory sampling point, ensuring that the lateral offset and its derivative of each sampling point meet the optimization objectives and constraints.

[0150] Step A42: determining the arc length of each trajectory sampling point according to a preset resolution;

[0151] It should be noted that the preset resolution is Δs. Taking Δs as the resolution refers to the interval or step size used when discretizing the path in the longitudinal direction (s direction) along the centerline of the lane. Δs is a fixed unit of length, which is used to represent the distance between adjacent sampling points on the s axis (longitudinal direction) in the Frenet coordinate system.

[0152] In the specific implementation, starting from the starting point of the lane, sampling is performed along the center line of the lane with a step size of Δs, and the arc length s of each sampling point is calculated. The arc length s is the cumulative distance from the starting point to the current sampling point along the center line of the lane.

[0153] It should be understood that when calculating the arc length, the actual position and motion state of the vehicle need to be considered to ensure that the arc length of the sampling point matches the actual path of the vehicle.

[0154] Step A43: Obtain the target path in the target coordinate system according to the lateral offset constraint, the lateral offset first-order derivative constraint, the lateral offset second-order derivative constraint and the arc length corresponding to each trajectory sampling point.

[0155] In the specific implementation, the target path in the target coordinate system is obtained according to the lateral offset constraint, the first-order derivative constraint of the lateral offset, the second-order derivative constraint of the lateral offset and the arc length corresponding to each trajectory sampling point, and the optimization results are converted into actual path points, which define the trajectory that the vehicle should follow.

[0156] This embodiment provides a method for trajectory planning of an autonomous driving vehicle, and a quadratic programming formula is established based on a target optimization function and target vehicle constraints. The trajectory sampling points are processed by the quadratic programming formula to obtain a target path in a target coordinate system, and a trajectory that meets vehicle dynamics and safety requirements and is smooth and comfortable can be systematically generated. The path also meets the set constraints, and a safe trajectory that meets the requirements of lane change and does not cross lane boundaries can be planned.

[0157] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the autonomous driving vehicle trajectory planning method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0158] This application also provides a trajectory planning device for an autonomous driving vehicle, please refer to Figure 7 , the autonomous driving vehicle trajectory planning device comprises:

[0159] A lane determination module 10, for determining a target lane;

[0160] A coordinate system conversion module 20, for converting the target lane into a target coordinate system based on the lane centerline of the target lane, wherein the ordinate of the target coordinate system is the arc length and the abscissa is the lateral offset;

[0161] A sampling module 30 is used to perform sampling along the ordinate direction of the target coordinate system at a preset resolution to obtain a plurality of trajectory sampling points;

[0162] The trajectory planning module 40 is used to plan and analyze the trajectory sampling points to obtain the target path in the target coordinate system.

[0163] The autonomous driving vehicle trajectory planning device provided by the present application adopts the autonomous driving vehicle trajectory planning method in the above embodiment, which can solve the technical problem that the vehicle length causes the front of the vehicle to run out of the road boundary in the planned path. Compared with the prior art, the beneficial effects of the autonomous driving vehicle trajectory planning device provided by the present application are the same as the beneficial effects of the autonomous driving vehicle trajectory planning method provided by the above embodiment, and the other technical features in the autonomous driving vehicle trajectory planning device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0164] In one embodiment, the trajectory planning module 40 is further used to determine a target optimization function based on a quadratic programming strategy;

[0165] Acquire vehicle information, and determine target vehicle constraint conditions based on the vehicle information, where the target vehicle constraint conditions include lateral boundary constraint, upper and lower boundary constraint, heading angle constraint, and curvature constraint;

[0166] The trajectory sampling points are processed based on the target optimization function and the target vehicle constraints to obtain the target path in the target coordinate system.

[0167] In one embodiment, the trajectory planning module 40 is further used to determine the lane change state of the vehicle based on the vehicle information, where the lane change state of the vehicle includes the vehicle changing lanes to the left and the vehicle changing lanes to the right;

[0168] Determine a left lane restriction and a right lane restriction based on a lane change state of the vehicle;

[0169] Determine the lateral boundary constraint and the upper and lower boundary constraints of the target coordinate system based on the left lane constraint and the right lane constraint;

[0170] Determine the heading angle constraint based on the lateral boundary constraint and the upper and lower boundary constraints of the target coordinate system;

[0171] The curvature constraint is determined based on the heading angle constraint.

[0172] In one embodiment, the trajectory planning module 40 is further used to obtain a set lateral offset of the left lane of the target coordinate system when determining that the vehicle lane change state is that the vehicle is changing lanes to the left;

[0173] Based on the vehicle information, the inclination angle of the vehicle along the longitudinal axis direction of the target coordinate system, the distance from the center of the rear axle of the vehicle to the front of the vehicle, and the width of the vehicle are determined to determine the offset of the left front point of the vehicle relative to the center line of the left lane;

[0174] The left lane constraint of the target vehicle constraint condition is determined based on the set lateral offset of the left lane of the target coordinate system and the offset of the left front point of the vehicle relative to the center line of the left lane.

[0175] In one embodiment, the trajectory planning module 40 is further used to obtain a set lateral offset of the right lane of the target coordinate system when determining that the vehicle lane change state is that the vehicle is changing lanes to the right;

[0176] Based on the vehicle information, the inclination angle of the vehicle along the longitudinal axis direction of the target coordinate system, the distance from the center of the rear axle of the vehicle to the front of the vehicle, and the width of the vehicle are determined to determine the offset of the right front point of the vehicle relative to the center line of the right lane;

[0177] The right lane constraint of the target vehicle constraint condition is determined based on the set lateral offset of the right lane of the target coordinate system and the offset of the right front point of the vehicle relative to the center line of the right lane.

[0178] In one embodiment, the trajectory planning module 40 is further used to establish a quadratic programming formula based on the target optimization function and the target vehicle constraint conditions;

[0179] The trajectory sampling points are processed through the quadratic programming formula to obtain the target path in the target coordinate system.

[0180] In one embodiment, the trajectory planning module 40 is further used to process the trajectory sampling points through a quadratic programming formula to obtain a lateral offset constraint, a lateral offset first-order derivative constraint, and a lateral offset second-order derivative constraint corresponding to each trajectory sampling point;

[0181] Determine the arc length of each trajectory sampling point according to a preset resolution;

[0182] The target path in the target coordinate system is obtained according to the lateral offset constraint, the lateral offset first-order derivative constraint, the lateral offset second-order derivative constraint and the arc length corresponding to each trajectory sampling point.

[0183] The present application provides an autonomous driving vehicle trajectory planning device, which 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 autonomous driving vehicle trajectory planning method in the above-mentioned embodiment one.

[0184] Reference below Figure 8 , which shows a schematic diagram of the structure of an autonomous driving vehicle trajectory planning device suitable for implementing the embodiment of the present application. The autonomous driving vehicle trajectory planning device 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. Figure 8 The autonomous driving vehicle trajectory planning device shown is merely an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present application.

[0185] like Figure 8As shown, the autonomous driving vehicle trajectory planning device 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 autonomous driving vehicle trajectory planning device 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. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the autonomous vehicle trajectory planning device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows an autonomous vehicle trajectory planning device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0186] 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.

[0187] The autonomous driving vehicle trajectory planning device provided by the present application adopts the autonomous driving vehicle trajectory planning method in the above embodiment, which can solve the technical problem that the vehicle length causes the front of the vehicle to run out of the road boundary in the planned path. Compared with the prior art, the beneficial effects of the autonomous driving vehicle trajectory planning device provided by the present application are the same as the beneficial effects of the autonomous driving vehicle trajectory planning device method provided by the above embodiment, and the other technical features in the autonomous driving vehicle trajectory planning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0188] 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.

[0189] 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.

[0190] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the autonomous driving vehicle trajectory planning method in the above-mentioned embodiment.

[0191] 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.

[0192] The above-mentioned computer-readable storage medium may be included in the autonomous driving vehicle trajectory planning device; or it may exist independently without being assembled into the autonomous driving vehicle trajectory planning device.

[0193] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the autonomous driving vehicle trajectory planning device, the autonomous driving vehicle trajectory planning device: obtains device information; determines the target lane; converts the target lane into a target coordinate system based on the lane centerline of the target lane, wherein the ordinate of the target coordinate system is the arc length and the abscissa is the lateral offset; samples along the ordinate direction of the target coordinate system at a preset resolution to obtain a number of trajectory sampling points; and plans and analyzes the trajectory sampling points to obtain the target path in the target coordinate system.

[0194] 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).

[0195] 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.

[0196] 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.

[0197] 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 autonomous driving vehicle trajectory planning method, and can solve the technical problem that the vehicle length causes the front of the vehicle to run out of the road boundary in the planned path. 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 autonomous driving vehicle trajectory planning method provided by the above-mentioned embodiment, and will not be repeated here.

[0198] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the autonomous driving vehicle trajectory planning method as described above.

[0199] The computer program product provided by this application can solve the technical problem that the vehicle length causes the front of the vehicle to run out of the road boundary in the planned path. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the automatic driving vehicle trajectory planning method provided by the above embodiment, which will not be repeated here.

[0200] 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 method for trajectory planning of an autonomous driving vehicle, characterized in that: The autonomous driving vehicle trajectory planning method comprises: Determine the target lane; The target lane is converted into a target coordinate system based on the lane centerline of the target lane, wherein the ordinate of the target coordinate system is the arc length and the abscissa is the lateral offset; Sampling along the ordinate direction of the target coordinate system at a preset resolution to obtain a plurality of trajectory sampling points; The trajectory sampling points are planned and analyzed to obtain the target path in the target coordinate system.

2. The automatic driving vehicle trajectory planning method according to claim 1, characterized in that: The step of planning and analyzing the trajectory sampling points to obtain the target path in the target coordinate system includes: Based on the quadratic programming strategy, determine the target optimization function; Acquire vehicle information, and determine target vehicle constraint conditions based on the vehicle information, wherein the target vehicle constraint conditions include lateral boundary constraints, upper and lower boundary constraints, heading angle constraints, and curvature constraints; The trajectory sampling points are processed based on the target optimization function and the target vehicle constraint conditions to obtain a target path in the target coordinate system.

3. The automatic driving vehicle trajectory planning method according to claim 2, characterized in that: The step of acquiring vehicle information and determining the target vehicle constraint condition based on the vehicle information includes: Determine a lane change state of the vehicle based on the vehicle information, the lane change state of the vehicle including the vehicle changing lanes to the left and the vehicle changing lanes to the right; determining a left lane restriction and a right lane restriction based on the vehicle lane change state; Determine a lateral boundary constraint and an upper and lower boundary constraint of the target coordinate system based on the left lane constraint and the right lane constraint; Determining a heading angle constraint based on a lateral boundary constraint and an upper and lower boundary constraint of the target coordinate system; A curvature constraint is determined based on the heading angle constraint.

4. The automatic driving vehicle trajectory planning method according to claim 3, characterized in that: The step of determining the left lane constraint and the right lane constraint based on the vehicle lane change state comprises: When determining that the lane change state of the vehicle is that the vehicle is changing lanes to the left, obtaining a set lateral offset of the left lane of the target coordinate system; Determine the inclination angle of the vehicle along the longitudinal axis direction of the target coordinate system, the distance from the center of the rear axle of the vehicle to the front of the vehicle, and the width of the vehicle to determine the offset of the left front point of the vehicle relative to the center line of the left lane based on the vehicle information; A left lane constraint of the target vehicle constraint condition is determined based on a set lateral offset of the left lane of the target coordinate system and an offset of the left front point of the vehicle relative to a center line of the left lane.

5. The automatic driving vehicle trajectory planning method according to claim 3, characterized in that: The step of determining the left lane constraint and the right lane constraint based on the vehicle lane change state comprises: When determining that the lane change state of the vehicle is that the vehicle is changing lanes to the right, obtaining a set lateral offset of the right lane of the target coordinate system; Based on the vehicle information, determine the inclination angle of the vehicle along the longitudinal axis direction of the target coordinate system, the distance from the center of the rear axle of the vehicle to the front of the vehicle, and the vehicle width to determine the offset of the right front point of the vehicle relative to the center line of the right lane; A right lane constraint of the target vehicle constraint condition is determined based on a set lateral offset of the right lane of the target coordinate system and an offset of the right front point of the vehicle relative to a center line of the right lane.

6. The automatic driving vehicle trajectory planning method according to claim 2, characterized in that: The step of processing the trajectory sampling points based on the target optimization function and the target vehicle constraint conditions to obtain the target path in the target coordinate system includes: Establishing a quadratic programming formula based on the target optimization function and the target vehicle constraint condition; The trajectory sampling points are processed by the quadratic programming formula to obtain the target path in the target coordinate system.

7. The automatic driving vehicle trajectory planning method according to claim 6, characterized in that: The step of processing the trajectory sampling points by using the quadratic programming formula to obtain the target path in the target coordinate system includes: The trajectory sampling points are processed by the quadratic programming formula to obtain a lateral offset constraint, a lateral offset first-order derivative constraint, and a lateral offset second-order derivative constraint corresponding to each trajectory sampling point; Determining the arc length of each trajectory sampling point according to the preset resolution; The target path in the target coordinate system is obtained according to the lateral offset constraint, the lateral offset first-order derivative constraint, the lateral offset second-order derivative constraint and the arc length corresponding to each trajectory sampling point.

8. An automatic driving vehicle trajectory planning device, characterized in that: The device comprises: A lane determination module, used to determine a target lane; A coordinate system conversion module, used to convert the target lane into a target coordinate system based on the lane centerline of the target lane, wherein the ordinate of the target coordinate system is the arc length and the abscissa is the lateral offset; A sampling module, used for sampling along the ordinate direction of the target coordinate system at a preset resolution to obtain a plurality of trajectory sampling points; The trajectory planning module is used to plan and analyze the trajectory sampling points to obtain the target path in the target coordinate system.

9. An autonomous driving vehicle trajectory planning device, 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 autonomous driving vehicle 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, on which a computer program is stored. When the computer program is executed by a processor, the steps of the automatic driving vehicle trajectory planning method as described in any one of claims 1 to 7 are implemented.

Images