Driving track determination method and device, electronic equipment and readable storage medium

Abstract

This invention discloses a method, apparatus, electronic device, and readable storage medium for determining a vehicle trajectory. The method includes: determining a first trajectory based on the motion state information of a target vehicle; determining a second trajectory based on the road attributes information ahead of the target vehicle and the target vehicle's motion state information; and determining the target vehicle's overall trajectory based on the motion state information, the road attributes ahead, the first trajectory, and the second trajectory. This invention solves the technical problem of inaccurate vehicle trajectories predicted under curve conditions because they do not match the driver's intentions.

Description

Technical Field

[0001] This invention relates to the field of vehicle driving technology, and more specifically, to a method and apparatus for determining driving trajectory, an electronic device, and a readable storage medium. Background Technology

[0002] With the continuous development and progress of intelligent driving technology, the vehicle installation rate of advanced driver assistance systems (ADAS) is increasing year by year. AEB (Automatic Emergency Braking) is one of the functions of the popularized AEB system. It is a safety backup for ADAS (Advanced Driving Assistance System), and its performance is directly related to the safety of passengers.

[0003] Existing methods for predicting vehicle trajectories mainly fall into two categories: one uses GPS (Global Positioning System) or in-vehicle high-precision maps and other navigation systems to periodically provide the vehicle's location information. By using sampling points from the past period to perform curve fitting, the method predicts the vehicle's trajectory for the future. However, this prediction method is highly dependent on GPS signals. In areas where GPS signals are weak or unavailable, and where high-precision maps are lacking, the predicted trajectory results may have significant deviations or even become unusable. Furthermore, it adds to the cost of positioning and navigation equipment.

[0004] Another approach uses the vehicle's motion state information. Based on the vehicle's motion pattern, different kinematic formulas are used to predict the vehicle's motion over a period of time. For example, a uniformly accelerated linear motion model is used to predict motion on straight roads, while a uniformly accelerated circular motion model is used to predict motion on curves. However, this method uses the curvature of the vehicle at the current moment. In paths with varying curvature or at points of sudden curvature changes (entering or exiting curves), the calculated predicted trajectory may not match the driver's intentions, potentially leading to malfunctions in the driver assistance functions.

[0005] In an application scenario of existing technology, such as Figure 1 The diagram shows the trajectory of a car entering a curve. Before entering the curve, the car travels straight (curvature is 0). The trajectory of the car is predicted using uniformly accelerated linear motion, as shown below. Figure 1 The middle half of the line indicates this. However, the actual vehicle will turn left along the road, as shown below. Figure 1 As shown by the midpoint line. Figure 1 The target OBJ may be mistakenly selected as the target of AEB.

[0006] In another application scenario of existing technology, such as Figure 2 The diagram shown illustrates the trajectory of a vehicle exiting a curve. The trajectory of the vehicle's circular motion is predicted based on the curvature at the curve's exit point. Figure 2 As shown by the half-line. However, the actual car will move in a straight line after exiting the curve, as shown... Figure 2 As shown by the midpoint line. Figure 2 The target OBJ may be mistakenly selected as the target of AEB.

[0007] It is evident that the predicted vehicle trajectory in the relevant technologies is not accurate enough under actual curve conditions. Summary of the Invention

[0008] This invention provides a method and apparatus for determining driving trajectory, an electronic device, and a readable storage medium, to at least solve the technical problem of inaccurate driving trajectory due to the predicted driving trajectory not conforming to the driver's driving intention under curved conditions.

[0009] According to one aspect of the present invention, a method for determining a driving trajectory is provided, the method comprising: determining a first motion trajectory based on motion state information corresponding to a target vehicle; determining a second motion trajectory based on forward road attribute information corresponding to the target vehicle and the motion state information of the target vehicle; and determining the driving trajectory of the target vehicle based on the motion state information, the forward road attribute information, the first motion trajectory, and the second motion trajectory.

[0010] Further, determining the driving trajectory of the target vehicle based on the motion state information, the road ahead attribute information, the first motion trajectory, and the second motion trajectory includes: determining the driving trajectory of the target vehicle from the first motion trajectory and the second motion trajectory based on the motion state information and the road ahead attribute information.

[0011] Further, determining the first motion trajectory based on the motion state information corresponding to the target vehicle includes: determining the first curvature and first turning radius of the target vehicle based on the yaw rate and vehicle speed of the target vehicle; determining the second curvature and second turning radius of the target vehicle based on the steering wheel angle and steering wheel angle change rate of the target vehicle; determining the motion curvature and motion turning radius of the target vehicle based on the first curvature, the first turning radius, the second curvature, and the second turning radius; and determining the first motion trajectory based on the motion curvature and the motion turning radius.

[0012] Further, determining the motion curvature and motion turning radius of the target vehicle based on the first curvature, the first turning radius, the second curvature, and the second turning radius includes: if the vehicle speed is greater than a first preset speed threshold, then determining the motion curvature as the first curvature and the motion turning radius as the first turning radius; if the vehicle speed is less than a second preset speed threshold, then determining the motion curvature as the second curvature and the motion turning radius as the second turning radius; if the vehicle speed is greater than or equal to the second preset speed threshold and less than or equal to the first preset speed threshold, then determining the motion curvature based on a first difference between the vehicle speed and the first preset speed threshold, a second difference between the vehicle speed and the second preset speed threshold, the first curvature, and the second curvature, and determining the motion turning radius based on the first difference and the second difference.

[0013] Furthermore, the first motion trajectory includes multiple sub-trajectories, each sub-trajectory including a first control point, a second control point, a third control point, and a fourth control point of a third-order Bézier curve, wherein the first control point is the starting point and the fourth control point is the ending point. The step of determining the first motion trajectory based on the motion curvature and the motion turning radius includes: determining the first, second, and third control points of the first sub-trajectory corresponding to the first motion trajectory based on the motion curvature and the motion turning radius; determining the fourth control point of the first sub-trajectory based on the first, second, and third control points of the first sub-trajectory; and sequentially determining each sub-trajectory based on the first, second, third, and fourth control points of the first sub-trajectory.

[0014] Further, determining the fourth control point of the first sub-trajectory based on the first control point, second control point, and third control point of the first sub-trajectory segment includes: if the target vehicle stops, or the motion curvature is less than or equal to a preset curvature threshold, then determining the fourth control point based on the first control point and the vehicle speed; if the motion curvature is greater than the preset curvature threshold, then determining the end curvature corresponding to the end point of the first sub-trajectory segment based on the start curvature corresponding to the initial point of the first sub-trajectory segment; and determining the fourth control point based on the first control point, the start curvature, the end curvature, the vehicle speed, and the acceleration of the target vehicle.

[0015] Further, determining the second trajectory based on the forward road attribute information corresponding to the target vehicle and the motion state information of the target vehicle includes: obtaining a road model of the road where the target vehicle is located based on the forward road attribute information; the road model includes multiple sub-road segments, wherein each sub-road includes a first control point, a second control point, a third control point, and a fourth control point of a third-order Bézier curve, the first control point being the starting point and the fourth control point being the ending point; determining the first control point, the second control point, and the third control point of the sub-road based on the road model and the motion state information of the target vehicle; and determining the fourth control point of the sub-road based on the first control point, the second control point, and the third control point of the sub-road.

[0016] Further, determining the fourth control point of the sub-road based on the first, second, and third control points of the sub-road includes: determining the length of the previous sub-road segment based on the road model and the longitudinal position in the current sub-road; determining the first lateral velocity and first acceleration of the target vehicle in the current sub-road based on the road model and the road length; and determining the fourth control point based on the lateral position, first lateral velocity, and first acceleration of the target vehicle in the current sub-road.

[0017] Further, determining the driving trajectory of the target vehicle from the first motion trajectory and the second motion trajectory based on the motion state information and the road attribute information ahead includes: if the speed of the target vehicle is greater than a third preset speed threshold, the acceleration of the target vehicle is less than a preset acceleration threshold, and the distance between the target vehicle and a preset object is greater than or equal to a preset distance threshold, then the driving trajectory is determined to be the second motion trajectory; otherwise, the driving trajectory is determined to be the first motion trajectory.

[0018] According to another aspect of the present invention, a vehicle trajectory determination device is also provided. The device includes: a first determination module, configured to determine a first trajectory based on motion state information corresponding to a target vehicle; a second determination module, configured to determine a second trajectory based on forward road attribute information corresponding to the target vehicle and the motion state information of the target vehicle; and a third determination module, configured to determine the vehicle trajectory of the target vehicle based on the motion state information, the forward road attribute information, the first trajectory, and the second trajectory.

[0019] According to another aspect of the present invention, an electronic device is also provided, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the driving trajectory determination method as described above.

[0020] According to another aspect of the present invention, a readable storage medium is also provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the driving trajectory determination method as described above.

[0021] In this embodiment of the invention, a first motion trajectory is determined based on the motion state information corresponding to the target vehicle; a second motion trajectory is determined based on the forward road attribute information corresponding to the target vehicle and the motion state information of the target vehicle; and the driving trajectory of the target vehicle is determined based on the motion state information, the forward road attribute information, the first motion trajectory, and the second motion trajectory. In this embodiment, two motion trajectories are determined based on the motion state information of the target vehicle and the forward road attribute information, respectively. Then, a driving trajectory that conforms to the actual working conditions is determined based on the motion state information, the forward road attribute information, etc., thereby improving the accuracy of the driving trajectory under curved conditions and solving the technical problem of inaccurate driving trajectories due to the predicted driving trajectory not conforming to the driver's driving intentions under curved conditions. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0023] Figure 1 This is a schematic diagram of a vehicle's trajectory prediction for entering a curve based on existing technology;

[0024] Figure 2 This is a schematic diagram of a vehicle's predicted trajectory when exiting a curve, based on existing technology.

[0025] Figure 3 This is a flowchart illustrating an optional method for determining a driving trajectory according to an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of an optional circular motion trajectory of a target vehicle according to an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of an optional AEB driving trajectory arbitration process according to an embodiment of the present invention;

[0028] Figure 6 This is a schematic diagram of the frame of an optional vehicle trajectory determination device according to an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] According to an embodiment of the present invention, a method for determining a vehicle trajectory is provided, such as... Figure 3 As shown, the method includes:

[0033] S302, determine the first motion trajectory based on the motion state information corresponding to the target vehicle;

[0034] S304, Determine the second trajectory based on the road attribute information ahead of the target vehicle and the motion state information of the target vehicle;

[0035] S306, based on motion status information, road attribute information ahead, first motion trajectory, and second motion trajectory, determine the driving trajectory of the target vehicle.

[0036] In this embodiment, the motion state information of the target vehicle includes, but is not limited to, the yaw rate, vehicle speed, curvature, turning radius, steering wheel angle, rear wheel deflection angle, and wheel end angle of the target vehicle. Specifically, the motion state information of the target vehicle is acquired through motion sensors, and the first motion trajectory can be obtained based on the motion state information and a third-order Bézier curve.

[0037] In this embodiment, the road ahead attribute information includes, but is not limited to, the lateral position of the road centerline at the initial moment, the angle between the road centerline and the vehicle's longitudinal axis, the road curvature, the longitudinal length of the preceding (m-1) segment of the road, and the rate of change of road curvature.

[0038] Specifically, in this embodiment, the target vehicle's image acquisition device collects the road attribute information in real time, or the target vehicle's road attribute information is obtained in real time from a preset road database. Based on the road attribute information and the aforementioned motion state information, the second motion trajectory can be obtained using a third-order Bézier curve.

[0039] In a specific example, step S306 determines the driving trajectory of the target vehicle based on the motion state information, the road ahead attribute information, the first motion trajectory, and the second motion trajectory, specifically including:

[0040] Based on the motion state information and the road ahead attribute information, the driving trajectory of the target vehicle is determined from the first motion trajectory and the second motion trajectory.

[0041] In this embodiment, under curved road conditions, a first trajectory is determined based on the target vehicle's motion state information, and a second trajectory is determined based on the road attributes and motion state information of the target vehicle. Then, based on the target vehicle's motion state information, the road attributes, the first trajectory, and the second trajectory, a trajectory that better matches the road conditions and the target vehicle's motion state is selected as the target vehicle's driving trajectory.

[0042] In one example, if the distance between the target vehicle and the obstacle in the road ahead attribute information is less than the preset safe distance, and the vehicle speed in the motion status information is less than or equal to the preset vehicle speed, then the second motion trajectory is determined to be the driving trajectory of the target vehicle.

[0043] In another example, if the road ahead attribute information corresponding to the target vehicle does not contain any obstacles, and the vehicle speed in the motion state information is greater than the preset vehicle speed and the acceleration is greater than the preset acceleration threshold, then the first motion trajectory is determined to be the driving trajectory of the target vehicle.

[0044] It should be noted that, in this embodiment of the invention, a first motion trajectory is determined based on the motion state information corresponding to the target vehicle; a second motion trajectory is determined based on the forward road attribute information corresponding to the target vehicle and the motion state information of the target vehicle; and the driving trajectory of the target vehicle is determined based on the motion state information, the forward road attribute information, the first motion trajectory, and the second motion trajectory. In this embodiment, two motion trajectories are determined based on the motion state information of the target vehicle and the forward road attribute information, respectively. Then, a driving trajectory that conforms to the actual working conditions is determined based on the motion state information, the forward road attribute information, etc., thereby improving the accuracy of the driving trajectory under curved conditions and solving the technical problem of inaccurate driving trajectories due to the predicted driving trajectory not conforming to the driver's driving intentions under curved conditions.

[0045] Optionally, in this embodiment, the first motion trajectory is determined based on the motion state information corresponding to the target vehicle, including but not limited to: determining the first curvature and the first turning radius of the target vehicle based on the yaw rate and vehicle speed of the target vehicle; determining the second curvature and the second turning radius of the target vehicle based on the steering wheel angle and the rate of change of the steering wheel angle of the target vehicle; determining the motion curvature and the motion turning radius of the target vehicle based on the first curvature, the first turning radius, the second curvature, and the second turning radius; and determining the first motion trajectory based on the motion curvature and the motion turning radius.

[0046] Specifically, firstly, using the target vehicle's yaw rate (YawRate) and speed (V), the target vehicle's first curvature and first turning radius are estimated using the following formula:

[0047] R1 = VYawRate

[0048] Curv1=YawRateV (1)

[0049] CurvRate1 = 0

[0050] Where V is the vehicle speed, YawRate is the yaw rate, Curv1 is the first curvature, CurvRate1 is the first rate of change of curvature, and R1 is the first turning radius.

[0051] Secondly, using the target vehicle's steering wheel angle SteerAngle, and based on a vehicle dynamics model centered on the target vehicle's center of gravity, the second curvature and second turning radius of the target vehicle are estimated. The calculation formula is as follows:

[0052]

[0053] Where k_SteerAngle2WheelAngle is the conversion gain of the steering wheel angle and wheel end angle of the target vehicle, SteerAngle is the steering wheel angle of the target vehicle, WheelAngle is the wheel end angle of the target vehicle, RearSlipAngle is the rear wheel slip angle of the target vehicle, FrontSlipAngle is the front wheel slip angle of the target vehicle, B is the front and rear wheelbase, Lf is the distance from the vehicle's center of mass to the center of the front axle, Lr is the distance from the vehicle's center of mass to the center of the rear axle, Cf is the front wheel lateral stiffness, Cr is the rear wheel lateral stiffness, M is the vehicle mass, β is the slip angle, R2_cog is the second turning radius with the center of mass as the origin, R2 is the second turning radius with the rear axle of the target vehicle as the origin, and Curv2 is the second curvature.

[0054] Meanwhile, by replacing the steering wheel angle SteerAngle in the above derivation formula (2) with the steering wheel angle change rate SteerAngleRate, the curvature change rate CurvRate2 can be obtained.

[0055] Next, the motion curvature and turning radius of the target vehicle are determined based on its actual operating conditions. In this embodiment, the motion curvature and turning radius of the target vehicle are determined based on a first curvature, a first turning radius, a second curvature, and a second turning radius. For example, the actual motion curvature and turning radius of the target vehicle can be determined based on different vehicle speeds.

[0056] Finally, the first motion trajectory of the target vehicle is determined based on the motion curvature and turning radius that conform to the actual working conditions of the target vehicle.

[0057] Through the above example, based on the yaw rate and speed of the target vehicle, and based on the steering wheel angle and the rate of change of the steering wheel angle, the motion curvature and turning radius that conform to the actual working conditions of the target vehicle are determined; based on the motion curvature and turning radius, the first motion trajectory is determined, thereby improving the accuracy of the first motion trajectory of the target vehicle.

[0058] Optionally, in this embodiment, the motion curvature and motion turning radius of the target vehicle are determined based on the first curvature, the first turning radius, the second curvature, and the second turning radius, including but not limited to: if the vehicle speed is greater than a first preset speed threshold, then the motion curvature is determined to be the first curvature and the motion turning radius is the first turning radius; if the vehicle speed is less than a second preset speed threshold, then the motion curvature is determined to be the second curvature and the motion turning radius is the second turning radius; if the vehicle speed is greater than or equal to the second preset speed threshold and less than or equal to the first preset speed threshold, then the motion curvature is determined based on the first difference between the vehicle speed and the first preset speed threshold, the second difference between the vehicle speed and the second preset speed threshold, the first curvature, and the second curvature, and the motion turning radius is determined based on the first difference and the second difference.

[0059] Specifically, in this embodiment, under high-speed conditions, when the vehicle speed is greater than the first preset speed threshold V > V_Limit1, the curvature estimated using the yaw rate is more accurate, the motion curvature is the first curvature Curvature = Curv1, and the motion turning radius is the first turning radius.

[0060] Under low-speed conditions, when the vehicle speed is less than the second preset speed threshold V < V_Limit2, the curvature estimated by the steering wheel angle is more accurate, the motion curvature is the second curvature Curvature = Curv2, and the motion turning radius is the second turning radius.

[0061] In another scenario, the target vehicle's speed falls between two thresholds: V_Limit2 ≤ V ≤ V_Limit1. Within the speed range corresponding to the first and second preset speed thresholds, the motion curvature is calculated linearly. Based on the first difference between the vehicle speed and the first preset speed threshold, the second difference between the vehicle speed and the second preset speed threshold, the first curvature, and the second curvature, the motion curvature is determined as follows:

[0062]

[0063] Similarly, the turning radius of the target vehicle is calculated using a linear ratio.

[0064] The above examples demonstrate how the motion curvature and turning radius of a target vehicle can be determined based on its different operating conditions, thereby improving the accuracy of these parameters.

[0065] Optionally, in this embodiment, the first motion trajectory includes multiple sub-trajectories, each sub-trajectory including a first control point, a second control point, a third control point, and a fourth control point of a third-order Bézier curve, where the first control point is the starting point and the fourth control point is the ending point. Determining the first motion trajectory based on the motion curvature and the motion turning radius includes: determining the first, second, and third control points of the first sub-trajectory corresponding to the first motion trajectory based on the motion curvature and the motion turning radius; determining the fourth control point of the first sub-trajectory based on the first, second, and third control points of the first sub-trajectory; and sequentially determining each sub-trajectory based on the first, second, third, and fourth control points of the first sub-trajectory.

[0066] Specifically, in this embodiment, assuming the target vehicle moves according to the current curvature, the predicted trajectory of the target vehicle is defined as follows: the first trajectory comprises multiple sub-trajectories, which are described by dividing the first trajectory into n segments (0 to nT) based on a third-order Bézier curve. Each segment has four control points (first control point P0, second control point P1, third control point P2, and fourth control point P3). In this embodiment, by utilizing the segmented recursiveness and continuity of the Bézier curve, the vehicle's trajectory can be predicted more accurately on the pre-aimed variable curvature road without abrupt curvature changes.

[0067] The predicted trajectory of the target vehicle within the time interval [0, T] is derived as follows:

[0068] 1) The predicted displacement of the target vehicle can be described as:

[0069] x(τ)=P3·τ 3 +3·P2·τ 2 (1-τ)+3·P1·τ(1-τ) 2 +P0·(1-τ) 3 (4)

[0070] τ=(t-0)(T-0)t∈[0,T]

[0071] Differentiating formula (5) yields the predicted expression for the target vehicle's speed:

[0072] v(τ)=3·P3·τ 2 +6·P2·τ·(1-τ)-3·P2·τ 2 +3·P1(1-τ) 2 -6·P1·τ·(1-τ)-3·P0·(1-τ) 2 (5)

[0073] After further differentiation, the predicted expression for the target vehicle's acceleration is obtained:

[0074] a(τ)=6·P3·τ+6·P2·(1-τ)-12·P2·τ-12·P1(1-τ)+6·P1·τ+6·P0·(1-τ) (6)

[0075] 2) Solve for control points P0, P1, and P2

[0076] From the above prediction expressions for displacement, vehicle speed, and acceleration (Formulas 4-6), we can see that:

[0077] When t=0, τ=0:

[0078] x(τ)=P0

[0079] v(τ)=3·P1-3·P0 (7)

[0080] a(τ)=6·P2-12·P1+6·P0

[0081] When t = T, τ = 1:

[0082] x(τ)=P3

[0083] v(τ)=3·P3-3·P2 (8)

[0084] a(τ)=6·P3-12·P2+6·P1

[0085] Given the position, speed, and acceleration of the target vehicle at t=0, substituting these values ​​into formula (8) for τ=0, we can solve for P0, P1, and P2.

[0086]

[0087] Where ALat(0) and ALgt(0) are the lateral and longitudinal accelerations at the current time, VLat(0) and VLgt(0) are the lateral and longitudinal velocities at the current time, and XLat(0) and XLgt(0) are the lateral and longitudinal positions at the current time.

[0088] 3) Calculate whether the target vehicle has stopped within this segment of the trajectory;

[0089] Specifically, a vehicle is considered to have stopped on a given section when either of the following two conditions is met:

[0090] A) The initial speed VLgt(0) is less than the stopping speed threshold V_StopLimit;

[0091] B) Initial acceleration ALgt(0) < 0, and 0 <StopTime=VLgt(0) / ALgt(0)<T;

[0092] If the target vehicle stops in this section, the lateral and longitudinal displacements of the target vehicle before it stopped are:

[0093]

[0094] Further optionally, in this embodiment, a fourth control point of the first sub-trajectory is determined based on the first control point, the second control point, and the third control point of the first sub-trajectory segment, including but not limited to: if the target vehicle stops, or the motion curvature is less than or equal to a preset curvature threshold, then the fourth control point is determined based on the first control point and the vehicle speed; if the motion curvature is greater than the preset curvature threshold, then the end curvature corresponding to the end point of the first sub-trajectory segment is determined based on the start curvature corresponding to the initial point of the first sub-trajectory segment; the fourth control point is determined based on the first control point, the start curvature, the end curvature, the vehicle speed, and the acceleration of the target vehicle.

[0095] Specifically, at the fourth control point P3 at time t=T (τ=1), the position of the target vehicle at the end of this segment can be divided into the following three cases:

[0096] A) The target vehicle stops at this section:

[0097]

[0098] B) If the curvature of the target vehicle is very small and the motion curvature is less than or equal to the preset curvature threshold (Curvature≤CurMove_Limit), then the target vehicle can be approximated as performing uniformly accelerated linear motion.

[0099]

[0100] C) If the curvature of the motion is greater than the preset curvature threshold (Curvature > CurMove_Limit), the vehicle will perform circular motion. A rate of change of curvature is introduced. The curvature at the end position is calculated from the initial curvature c1 of the vehicle in that segment. The vehicle's position is predicted using c1 and c2 as the curvatures for circular motion, respectively, reducing the error caused by using only c1 to predict the vehicle's position.

[0101] In one example, such as Figure 4 As shown, using the x2-y2 coordinate system as the reference, the coordinate change from point A to point B within the calculation time is as follows:

[0102]

[0103] Transform x2, y2 into the vehicle coordinate system x1, y1:

[0104]

[0105] The above x1 and y1 represent the coordinate changes calculated when R is r1 (the radius of curvature at point A). Considering the rate of change of curvature, the coordinate changes x2 and y2 when R is r2 (the radius of curvature at point B) can also be obtained. The positions at time T are obtained by proportionally combining factor (0 ≤ factor ≤ 1) and (1 - factor).

[0106]

[0107] Where factor is the proportion of R in the actual circular motion between the radius r1 and the radius r2.

[0108] The above derivation yields the calculation of control points P0 to P3 within the time interval [0,T]. Substituting τ = 1 (t = T) into the formula, we can obtain the position, velocity, and acceleration at time T. Due to the continuity of the Bézier curve, time T is the tail point of the [0,T] trajectory, and also the starting point of the [T,2T] trajectory. By repeating the above steps using the motion information at time T, we can calculate the control points P0 to P3 of the Bézier curve corresponding to the second sub-trajectory. Then, we can sequentially calculate the expressions for the Bézier curves corresponding to the n sub-trajectories, thus determining each sub-trajectory in the first motion trajectory.

[0109] Through the above examples, by utilizing the segmented recursion and continuity of Bézier curves, the vehicle's trajectory can be predicted more accurately on pre-planned variable curvature roads, making the predicted trajectory more consistent with the driver's intentions.

[0110] Optionally, in this embodiment, the second motion trajectory is determined based on the forward road attribute information corresponding to the target vehicle and the motion state information of the target vehicle, including but not limited to: obtaining a road model of the road where the target vehicle is located based on the forward road attribute information, the road model including multiple sub-roads, wherein the sub-roads include a first control point, a second control point, a third control point, and a fourth control point of a third-order Bézier curve, the first control point being the starting point and the fourth control point being the ending point; determining the first control point, the second control point, and the third control point of the sub-road based on the road model and the motion state information of the target vehicle; and determining the fourth control point of the sub-road based on the first control point, the second control point, and the third control point of the sub-road.

[0111] Specifically, in this embodiment, the road where the target vehicle is located is divided into m segments, and the second motion trajectory is described by dividing it into n segments (0 to nT) according to the third-order Bézier curve. Each segment of the road has four control points (first control point P0, second control point P1, third control point P2, and fourth control point P3).

[0112] First, a road model is established using the road attribute information ahead, including the initial lateral position (Offset) of the road centerline, the angle between the road centerline and the vehicle's longitudinal axis (Heading), the road curvature, and the longitudinal length (SegLen) and curvature rate of change (CurvatureRate) of the preceding (m-1) segment of the road. A cubic polynomial model of the m-segment road is then calculated.

[0113] 0≤x1≤SegLen(1)

[0114] y1 = a1 + b1·x1 + c1·x1 2 +d1·x1 3

[0115] y1′=b1+2·c1·x1+3·d1·x1 2 (16)

[0116] y1″=22c1+6·d1·x1

[0117] y1″′=6·d1

[0118] Where x1 represents the longitudinal displacement of the first road segment in the target vehicle coordinate system, and y1 represents the lateral displacement of the first road segment in the target vehicle coordinate system. Initially, x1 = 0, y1 = offset, y1′ = Headingy1″ = Curvature, and y1″′ = CurvatureRate1. The calculated values ​​are...

[0119]

[0120] Because of the continuity of the road, the end point of the first segment is also the beginning point of the second segment. Substituting x1 = SegLen(1) into the cubic polynomial of the first segment, we get the beginning point of the second segment as:

[0121] y2=a1+b1·SegLen(1)+c1·SegLen(1) 2 +d1·SegLen(1) 3

[0122] y2′=b1+2·c1·SegLen(1)+3·d1·SegLen(1) 2 (18)

[0123] y2″=2·c1+6·d1·SegLen(1)

[0124] y2″′=CurvatureRate2

[0125] The cubic curve of the road model for the second segment can be described as:

[0126]

[0127] Since y2, y2′, y2″, and y2″′ are all known when x2 = 0, the coefficients a2 to d2 of the second segment can be calculated. Repeating this process, the expression for the (m-1)th segment can be obtained, which will not be elaborated here.

[0128] Taking the predicted trajectory of the target vehicle within the time interval [0,T] as an example, the derivation method of control points P0-P2 is the same as that of P0-P2 in the first trajectory mentioned above, and will not be repeated here. The derivation method of the fourth control point P3 is described below:

[0129] Further optionally, in this embodiment, the fourth control point of the sub-road is determined based on the first control point, the second control point, and the third control point of the sub-road, including but not limited to: determining the road length of the previous sub-road segment based on the road model and the longitudinal position in the current sub-road; determining the first lateral velocity and the first acceleration of the target vehicle in the current sub-road based on the road model and the road length; and determining the fourth control point based on the lateral position, the first lateral velocity, and the first acceleration of the target vehicle in the current sub-road.

[0130] Specifically, in this embodiment, the process of calculating P3 based on the road model is as follows:

[0131] Assuming the target vehicle maintains its current speed, the predicted longitudinal position at time nT is:

[0132]

[0133] Based on the road model and the predicted longitudinal position at time nT, the lengths of each road segment in the LookAheadDistance and the road model are compared to determine the current sub-road traveled by the target vehicle at time nT. The length of the sub-road segment above LookAheadDistance is then substituted into the road model corresponding to the current sub-road to obtain the lateral position XLat, Heading, and Curvature of the target vehicle at time nT. Furthermore, the lateral velocity and acceleration of the target vehicle are calculated.

[0134]

[0135] Using the lateral position, vehicle speed, and acceleration at time nT, substituting τ=n into the following system of cubic equations, we can obtain the following result.

[0136] x(τ)=P3·τ 3 +3·P2·τ 2 (1-τ)+32P1·τ(1-τ) 2 +P0·(1-τ) 3

[0137] v(τ)=3·P3·τ 2 +6·P2·τ·(1-τ)-3·P2·τ 2 +3·P1(1-τ) 2 -6·P1·τ·(1-τ)-3·P0·(1-τ) 2 (twenty two)

[0138] a(τ)=6·P3·τ+6·P2·(1-τ)-12·P2·τ-12·P1(1-τ)+6·P1·τ+6·P0·(1-τ)

[0139] P3y can be represented as P3y = f(P0y, P1y, P2y, n, XLat, VLat, ALat). The relationship between P3y and n can be derived from the above formula. For example, substituting n = 3 into the formula yields the vertical position of P3:

[0140] P3y=single((1 / 6*ALat-VLat / 2+7 / 2*P2y–P1y+XLat / 2) / 3) (23)

[0141] Based on P3y and P2y, the lateral velocity at time T = τ = 1 can be calculated as Vy = (P3y – P2y) / 3. The resultant velocity at time T is known to be V = V0 + A0 * T, and the longitudinal velocity at time T is... Since Vx = (P3x – P2x) / 3, the lateral position of P3 can be determined as follows:

[0142]

[0143] By utilizing the segmented recursion and continuity of Bézier curves, the vehicle's trajectory can be predicted more accurately on pre-aimed roads with varying curvature, making the predicted second trajectory more consistent with the driver's intentions.

[0144] Optionally, in this embodiment, the driving trajectory of the target vehicle is determined from the first motion trajectory and the second motion trajectory based on the motion state information and the road attribute information ahead. This includes, but is not limited to: if the speed of the target vehicle is greater than a third preset speed threshold, the acceleration of the target vehicle is less than a preset acceleration threshold, and the distance between the target vehicle and a preset object is greater than or equal to a preset distance threshold, the driving trajectory is determined to be the second motion trajectory; otherwise, the driving trajectory is determined to be the first motion trajectory.

[0145] Specifically, in this embodiment, such as Figure 5 The flowchart shown below illustrates the AEB (Autonomous Emergency Braking) trajectory arbitration process, which may include the following steps:

[0146] S51, Determine whether the information on the attribute of the road ahead is valid, whether the total length of m segments of the road is greater than the minimum threshold of the road length, whether the speed of the target vehicle is greater than the third preset speed threshold, and whether the acceleration of the target vehicle is less than the preset acceleration threshold;

[0147] Specifically, if the information on the attribute of the road ahead is valid, the total length of m segments of the road is greater than the minimum threshold of the road length, the speed of the target vehicle is greater than the third preset speed threshold V≥V_Limit, and the lateral acceleration of the vehicle itself ALat = VLgt·YawRate < ALat_Limit, jump to S52; otherwise, jump to S54.

[0148] S52, Determine whether the curvature of the road ahead suddenly changes when detected and whether the distance from the target object is greater than the preset distance threshold;

[0149] Specifically, if it is detected that the curvature of the road ahead suddenly changes and the distance of the target Jump to S53; otherwise, jump to S54.

[0150] It should be noted that if the difference between the curvature of the current sub-road and the curvature of the previous sub-road is greater than the preset curvature difference threshold, it is determined that the curvature of the road ahead suddenly changes; otherwise, it is determined that the curvature of the road ahead does not suddenly change.

[0151] S53, Determine that the driving trajectory is the second motion trajectory;

[0152] S54, Determine that the driving trajectory is the first motion trajectory.

[0153] In the embodiments of the present invention, the first motion trajectory is determined according to the motion state information corresponding to the target vehicle; the second motion trajectory is determined according to the information on the attribute of the road ahead corresponding to the target vehicle and the motion state information of the target vehicle; according to the motion state information and the information on the attribute of the road ahead, the driving trajectory of the target vehicle is determined from the first motion trajectory and the second motion trajectory. In this embodiment, two motion trajectories are predicted respectively according to the motion state information of the target vehicle and the information on the attribute of the road ahead, and then the driving trajectory that conforms to the actual working condition is determined according to the motion state information, the information on the attribute of the road ahead, etc., achieving the purpose of improving the accuracy of the driving trajectory under the curve working condition, and further solving the technical problem that the predicted driving trajectory does not conform to the driver's driving intention and the driving trajectory is inaccurate under the curve working condition.

[0154] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0155] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0156] Example 2

[0157] According to embodiments of the present invention, a vehicle trajectory determination device for implementing the above-described vehicle trajectory determination method is also provided, such as... Figure 6 As shown, the device includes:

[0158] The first determining module 60 is used to determine the first motion trajectory based on the motion state information corresponding to the target vehicle.

[0159] The second determining module 62 is used to determine the second motion trajectory based on the forward road attribute information corresponding to the target vehicle and the motion state information of the target vehicle.

[0160] The third determining module 64 is used to determine the driving trajectory of the target vehicle based on the motion state information, the road ahead attribute information, the first motion trajectory, and the second motion trajectory.

[0161] Through this embodiment of the invention, a first motion trajectory is determined based on the motion state information of the target vehicle; a second motion trajectory is determined based on the road attribute information ahead of the target vehicle and the motion state information of the target vehicle; and the driving trajectory of the target vehicle is determined based on the motion state information, the road attribute information ahead, the first motion trajectory, and the second motion trajectory. In this embodiment, two motion trajectories are predicted based on the motion state information of the target vehicle and the road attribute information ahead, respectively. Then, a driving trajectory that conforms to the actual working conditions is determined based on the motion state information, the road attribute information ahead, etc., thereby improving the accuracy of the driving trajectory under curved conditions and solving the technical problem of inaccurate driving trajectories due to the predicted driving trajectory not conforming to the driver's driving intentions under curved conditions.

[0162] Optionally, specific examples in this embodiment can refer to the examples described in Embodiment 1 above, and will not be repeated here.

[0163] Example 3

[0164] According to an embodiment of the present invention, an electronic device is also provided, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the driving trajectory determination method as described above.

[0165] Optionally, in this embodiment, the memory is configured to store program code for performing the following steps:

[0166] S1, determine the first motion trajectory based on the motion state information corresponding to the target vehicle;

[0167] S2, determine the second trajectory based on the road attribute information ahead of the target vehicle and the motion state information of the target vehicle;

[0168] S3, determine the driving trajectory of the target vehicle based on the motion state information, the road attribute information ahead, the first motion trajectory, and the second motion trajectory.

[0169] Optionally, specific examples in this embodiment can refer to the examples described in Embodiment 1 above, and will not be repeated here.

[0170] Example 4

[0171] Embodiments of the present invention also provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the driving trajectory determination method as described above.

[0172] Optionally, in this embodiment, the readable storage medium is configured to store program code for performing the following steps:

[0173] S1, determine the first motion trajectory based on the motion state information corresponding to the target vehicle;

[0174] S2, determine the second trajectory based on the road attribute information ahead of the target vehicle and the motion state information of the target vehicle;

[0175] S3, determine the driving trajectory of the target vehicle based on the motion state information, the road attribute information ahead, the first motion trajectory, and the second motion trajectory.

[0176] Optionally, the readable storage medium is also configured to store program code for performing the steps included in the method of Embodiment 1 above, which will not be described again in this embodiment.

[0177] Optionally, in this embodiment, the aforementioned readable storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0178] Optionally, specific examples in this embodiment can refer to the examples described in Embodiment 1 above, and will not be repeated here.

[0179] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0180] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0181] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0182] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0183] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0184] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0185] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining a vehicle trajectory, characterized in that, The method includes: The first motion trajectory is determined based on the motion status information of the target vehicle. The second trajectory is determined based on the road attribute information ahead of the target vehicle and the motion state information of the target vehicle. The driving trajectory of the target vehicle is determined based on the motion state information, the road attribute information ahead, the first motion trajectory, and the second motion trajectory. The step of determining the first motion trajectory based on the motion state information corresponding to the target vehicle includes: Based on the yaw rate and speed of the target vehicle, determine the first curvature and the first turning radius of the target vehicle; Based on the steering wheel angle and the rate of change of the steering wheel angle of the target vehicle, determine the second curvature and the second turning radius of the target vehicle; Determining the motion curvature and motion turning radius of the target vehicle based on the first curvature, the first turning radius, the second curvature, and the second turning radius includes: If the vehicle speed is greater than a first preset speed threshold, then the motion curvature is determined to be the first curvature, and the motion turning radius is the first turning radius; If the vehicle speed is less than the second preset speed threshold, then the motion curvature is determined to be the second curvature, and the motion turning radius is the second turning radius; If the vehicle speed is greater than or equal to the second preset speed threshold and less than or equal to the first preset speed threshold, then the motion curvature is determined based on the first difference between the vehicle speed and the first preset speed threshold, the second difference between the vehicle speed and the second preset speed threshold, the first curvature, and the second curvature; and the motion turning radius is determined based on the first difference and the second difference. The first motion trajectory is determined based on the motion curvature and the motion turning radius.

2. The method according to claim 1, characterized in that, Determining the driving trajectory of the target vehicle based on the motion state information, the road ahead attribute information, the first motion trajectory, and the second motion trajectory includes: Based on the motion state information and the road ahead attribute information, the driving trajectory of the target vehicle is determined from the first motion trajectory and the second motion trajectory.

3. The method according to claim 1, characterized in that, The first motion trajectory includes multiple sub-trajectories, each sub-trajectory including a first control point, a second control point, a third control point, and a fourth control point of a third-order Bézier curve, wherein the first control point is the starting point and the fourth control point is the ending point. Determining the first motion trajectory based on the motion curvature and the motion turning radius includes: Based on the motion curvature and the motion turning radius, determine the first control point, the second control point, and the third control point of the first sub-trajectory corresponding to the first motion trajectory; Based on the first control point, second control point, and third control point of the first sub-trajectory segment, determine the fourth control point of the first sub-trajectory segment; Based on the first control point, second control point, third control point and fourth control point of the first segment of the sub-trajectory, each sub-trajectory is determined sequentially.

4. The method according to claim 3, characterized in that, Determining the fourth control point of the first sub-trajectory based on the first control point, second control point, and third control point of the first sub-trajectory segment includes: If the target vehicle stops, or the motion curvature is less than or equal to a preset curvature threshold, then the fourth control point is determined based on the first control point and the vehicle speed. If the motion curvature is greater than a preset curvature threshold, then the end curvature corresponding to the end point of the first sub-trajectory is determined based on the start curvature corresponding to the initial point of the first sub-trajectory. The fourth control point is determined based on the first control point, the start curvature, the end curvature, the vehicle speed, and the acceleration of the target vehicle.

5. The method according to claim 1, characterized in that, The step of determining the second trajectory based on the road attribute information ahead of the target vehicle and the motion state information of the target vehicle includes: The road model of the road where the target vehicle is located is obtained based on the road attribute information ahead. The road model includes multiple sub-roads, wherein each sub-road includes a first control point, a second control point, a third control point, and a fourth control point of a third-order Bézier curve. The first control point is the starting point, and the fourth control point is the ending point. The first control point, second control point, and third control point of the sub-road are determined based on the road model and the motion state information of the target vehicle. The fourth control point of the sub-road is determined based on the first control point, the second control point, and the third control point of the sub-road.

6. The method according to claim 5, characterized in that, Determining the fourth control point of the sub-road based on the first, second, and third control points includes: Based on the road model and the longitudinal position in the current sub-road, determine the length of the previous sub-road segment; Based on the road model and the road length, determine the first lateral velocity and first acceleration of the target vehicle in the current sub-road; The fourth control point is determined based on the target vehicle's lateral position, first lateral velocity, and first acceleration in the current sub-road.

7. The method according to claim 2, characterized in that, Determining the driving trajectory of the target vehicle from the first and second motion trajectories based on the motion state information and the road ahead attribute information includes: If the speed of the target vehicle is greater than a third preset speed threshold, the acceleration of the target vehicle is less than a preset acceleration threshold, and the distance between the target vehicle and the preset object is greater than or equal to a preset distance threshold, then the driving trajectory is determined to be the second motion trajectory. Otherwise, the driving trajectory is determined to be the first motion trajectory.

8. A vehicle trajectory determination device, characterized in that, The device includes: The first determining module is used to determine the first motion trajectory based on the motion state information corresponding to the target vehicle. The second determining module is used to determine the second motion trajectory based on the forward road attribute information corresponding to the target vehicle and the motion state information of the target vehicle. The third determining module is used to determine the driving trajectory of the target vehicle based on the motion state information, the road attribute information ahead, the first motion trajectory, and the second motion trajectory. The device further includes: The step of determining the first motion trajectory based on the motion state information corresponding to the target vehicle includes: Based on the yaw rate and speed of the target vehicle, determine the first curvature and the first turning radius of the target vehicle; Based on the steering wheel angle and the rate of change of the steering wheel angle of the target vehicle, determine the second curvature and the second turning radius of the target vehicle; Determining the motion curvature and motion turning radius of the target vehicle based on the first curvature, the first turning radius, the second curvature, and the second turning radius includes: If the vehicle speed is greater than a first preset speed threshold, then the motion curvature is determined to be the first curvature, and the motion turning radius is the first turning radius; If the vehicle speed is less than the second preset speed threshold, then the motion curvature is determined to be the second curvature, and the motion turning radius is the second turning radius; If the vehicle speed is greater than or equal to the second preset speed threshold and less than or equal to the first preset speed threshold, then the motion curvature is determined based on the first difference between the vehicle speed and the first preset speed threshold, the second difference between the vehicle speed and the second preset speed threshold, the first curvature, and the second curvature; and the motion turning radius is determined based on the first difference and the second difference. The first motion trajectory is determined based on the motion curvature and the motion turning radius.

9. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the driving trajectory determination method as described in any one of claims 1-7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the driving trajectory determination method as described in any one of claims 1-7.

Images