CN116520825A

CN116520825A - Vehicle track planning method, device, electronic equipment and storage medium

Info

Publication number: CN116520825A
Application number: CN202310282222.6A
Authority: CN
Inventors: 刘凯; 曹世卓; 周小成
Original assignee: Uisee Technologies Beijing Co Ltd
Current assignee: Uisee Technologies Beijing Co Ltd
Priority date: 2023-03-21
Filing date: 2023-03-21
Publication date: 2023-08-01

Abstract

The embodiment of the disclosure discloses a vehicle track planning method, a vehicle track planning device, electronic equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining an initial reference track of a target vehicle in a to-be-planned area, maximizing an average degree of projection of the target vehicle on a plane where the initial reference track is located on two sides of the track to be an objective function, limiting conditions by a kinematic model and safety constraint, and sequentially carrying out secondary planning to obtain a target control quantity sequence comprising actual steering curvatures corresponding to all sampling points, further determining the target reference track and all tracking points which are not identical in a running process of the target reference track through the target control quantity sequence, and avoiding the problem that collision risk exists due to the fact that one side of the vehicle is too large relative to the track when the target vehicle runs along the target reference track, and the situation that the side is too close to a road boundary or a roadside obstacle in the area is solved, and the problem that the track passing through a narrow area is difficult to be planned for the vehicle with a long wheelbase in the prior art is solved.

Description

Vehicle track planning method, device, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of automatic driving, and in particular relates to a vehicle track planning method, a vehicle track planning device, electronic equipment and a storage medium.

Background

Along with the continuous maturity of unmanned technique, unmanned car's application is also more and more extensive, and in addition to regular or small-size vehicles such as Robotaxi, robo-release, unmanned bus, container intelligent transfer car, container truck, unmanned heavy truck's big-and-middle-sized vehicles also receive wide attention, and the characteristics of these kind of vehicles are that the wheelbase is longer, and the automobile body is wider, need great steering space when passing through the bend. The unmanned vehicles are gradually unfolded when applied to the scenes such as communities, construction diversion sections and the like, and the scenes are characterized by narrow space and larger local road curvature.

The existing unmanned vehicle track planning method is generally aimed at a conventional wheelbase vehicle, and a fixed tracking point is selected for track planning. It is common to use the center or centroid of the rear axle of the vehicle as the tracking point for trajectory planning. However, this approach is difficult to adapt to long wheelbase vehicles, especially in narrow areas, where a viable trajectory for safe passage through the area cannot be planned.

Disclosure of Invention

In order to solve the above technical problems or at least partially solve the above technical problems, embodiments of the present disclosure provide a vehicle track planning method, apparatus, electronic device, and storage medium, which solve the problem in the prior art that it is difficult to plan a track that safely passes through a narrow area for a long-wheelbase vehicle.

In a first aspect, an embodiment of the present disclosure provides a vehicle track planning method, including:

acquiring an initial reference track of a target vehicle in a region to be planned, wherein the initial reference track comprises sampling points;

maximizing the projection distribution uniformity of the initial reference track as an objective function, and performing sequential quadratic programming under the limiting condition of the kinematic model and the safety constraint of the target vehicle to obtain a target control quantity sequence, wherein the target control quantity sequence comprises actual steering curvatures corresponding to all sampling points;

determining a target reference track based on the target control quantity sequence, and determining each tracking point which enables the difference between the distances between two sides of a vehicle and the target reference track to be minimum in the running process of the target reference track, wherein the tracking points are the position points on the target vehicle running along the target reference track, and the tracking points are not identical;

The projection distribution uniformity is the average degree of the projection distribution of the target vehicle on the two sides of the track on the plane where the initial reference track is located, and is used for reflecting the difference between the distances between the two sides of the vehicle relative to the initial reference track, the projection distribution uniformity is determined according to the state vector of each sampling point, and the state vector of each sampling point is determined according to the kinematic model, the state vector of the adjacent sampling point and the actual steering curvature of the adjacent sampling point.

In a second aspect, an embodiment of the present disclosure further provides a vehicle track planning apparatus, including:

the initial track determining module is used for obtaining an initial reference track of the target vehicle in the area to be planned, wherein the initial reference track comprises sampling points;

the sequential quadratic programming module is used for carrying out sequential quadratic programming under the condition that the projection distribution uniformity of the initial reference track is maximized as an objective function and the kinematic model and the safety constraint of the target vehicle are limited, so as to obtain a target control quantity sequence, wherein the target control quantity sequence comprises actual steering curvatures corresponding to all sampling points;

the target track determining module is used for determining a target reference track based on the target control quantity sequence and determining each tracking point which makes the difference between the distances between the two sides of the vehicle and the target reference track minimum in the running process of the target reference track, wherein the tracking points are the position points on the target vehicle running along the target reference track, and the tracking points are not identical;

The uniformity of the projection distribution is the average degree of the projection distribution of the target vehicle on the plane of the initial reference track on two sides of the track, and is used for reflecting the difference between the distances of the two sides of the vehicle relative to the initial reference track, the uniformity of the projection distribution is determined according to the state vector of each sampling point, and the state vector of each sampling point is determined according to the kinematic model, the state vector of the adjacent sampling point and the actual steering curvature of the adjacent sampling point

In a third aspect, embodiments of the present disclosure further provide an electronic device, including: one or more processors; a storage means for storing one or more programs; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the vehicle trajectory planning method as described above.

In a fourth aspect, the disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a vehicle trajectory planning method as described above.

According to the vehicle track planning method provided by the embodiment of the disclosure, the initial reference track of the target vehicle in the area to be planned is obtained, the average degree of the projection of the target vehicle on the plane where the initial reference track is located on two sides of the track is maximized as an objective function, a kinematic model and safety constraint are used as limiting conditions, sequential secondary planning is carried out, a target control quantity sequence comprising the actual steering curvature corresponding to each sampling point is obtained, and then the target reference track and each tracking point which is not identical in the running process of the target reference track are determined through the target control quantity sequence, so that each tracking point with the minimum difference between the distances of two sides of the vehicle relative to the track is obtained in the running process of the target reference track, the problem that collision risk exists due to the fact that the distance between one side of the target vehicle and the track is overlarge, and road boundary or roadside obstacle in the area is too close is avoided, and the problem that the vehicle is difficult to plan the track of the safety passing through the narrow area is solved.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a schematic diagram of a prior art trajectory planning in an embodiment of the present disclosure;

FIG. 2 is a schematic plan view of a vehicle trajectory planning method in an embodiment of the present disclosure;

FIG. 3 is a flow chart of a vehicle trajectory planning method in an embodiment of the present disclosure;

FIG. 4 is a schematic illustration of a vehicle lateral deviation in an embodiment of the present disclosure;

FIG. 5 is an approximate schematic of tracking bias in a frenet coordinate system in an embodiment of the present disclosure;

FIG. 6 is a diagram of parameters related to a safety margin reference value in an embodiment of the disclosure;

FIG. 7 is a schematic diagram of a vehicle trajectory planning device in an embodiment of the disclosure;

fig. 8 is a schematic structural diagram of an electronic device in an embodiment of the disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

Before describing the vehicle track planning method provided by the embodiment of the present disclosure in detail, a description is given of a technical problem solved by the vehicle track planning method. In the prior art, a track of an unmanned vehicle is planned, and a fixed tracking point is generally used for controlling the vehicle to travel along the track after the track is determined, for example, the center of a rear axle of the vehicle and the center of mass of the vehicle, wherein the tracking point can be understood as a position point on the vehicle which needs to travel along the track.

However, this prior art trajectory planning approach, when moving along the trajectory using a fixed tracking point, can cause the body to deviate to one side of the road at a time, increasing the likelihood that the vehicle will go beyond the road boundary or collide with roadside obstructions. For example, fig. 1 is a schematic diagram of a track planning in the prior art in an embodiment of the disclosure, and it can be seen from fig. 1 that when a fixed center of a rear axle of a vehicle is used to move along a track, a problem that a collision occurs due to too close proximity of a vehicle body side to a road boundary exists.

Therefore, in order to solve the above technical problems, aiming at the problem that a long-wheelbase vehicle is difficult to safely pass through in a narrow area, the embodiment of the disclosure provides a vehicle track planning method which can be applied to the long-wheelbase vehicle to plan a running track of the long-wheelbase vehicle in the narrow area. By the method, the target reference track and each tracking point in the running process of the target reference track can be obtained, namely each tracking point which is dynamically adjusted in the track is obtained, when the vehicle runs along the track by using the tracking points, the difference between the distances between the two sides of the vehicle and the track can be kept to be minimum all the time, the situation that one side of the vehicle is too close to a road boundary or a roadside obstacle in an area is avoided, the possibility that the vehicle exceeds the road boundary or collides with the obstacle is reduced, and the trafficability and safety of the track are improved. Fig. 2 is a schematic plan view of a vehicle track planning method according to an embodiment of the disclosure, and as can be seen from fig. 2, by determining tracking points that make a difference between distances between two sides of a vehicle and a track always keep minimum, when the tracking points are used to control the vehicle to travel along the track, the vehicle always keeps a maximum distance from a road boundary or a roadside obstacle, so that safety of passing of the vehicle is improved.

Fig. 3 is a flow chart of a vehicle trajectory planning method in an embodiment of the present disclosure. The method may be performed by a vehicle trajectory planning device, which may be implemented in software and/or hardware, which may be configured in an electronic device. As shown in fig. 3, the method specifically may include the following steps:

s110, acquiring an initial reference track of the target vehicle in the area to be planned, wherein the initial reference track comprises sampling points.

The target vehicle may be a vehicle with a current track to be planned, and in this embodiment, the target vehicle may be a large and medium-sized vehicle with a long wheelbase and a wide vehicle body, such as an unmanned bus, a container intelligent transfer vehicle, an unmanned heavy truck, and the like. The area to be planned may be an area to be travelled by the target vehicle, such as a narrow area, and in particular, the narrow area may be an area where the area passing width is small or where the local road area is large.

In this embodiment, for a target vehicle whose track needs to be planned, an initial reference track of the target vehicle in the area to be planned may be determined first. Specifically, a lane line in the area to be planned may be determined, and then the lane line is used as an initial reference track. The purpose of using the lane line as the initial reference track is to: because the lane line is positioned at the center of the lane, the vehicle can be kept at the center of the lane as far as possible when the vehicle runs along the lane line, so as to be far away from the road boundary or the obstacle in the area to be planned as far as possible.

Further, after the initial reference trajectory is obtained, a plurality of sampling points may be determined in the initial reference trajectory. Wherein each sampling point is located on the initial reference track.

Specifically, for the initial reference track, starting from the current projection position of the target vehicle on the initial reference track, and sampling the initial reference track according to a preset sampling distance to obtain a plurality of sampling points. The current projection position may be a point where the current position of the target vehicle is mapped to the initial reference track, and specifically, a line perpendicular to the initial reference track may be made along the current position, where an intersection point of the line and the initial reference track is the current projection position. The preset sampling distance can be preset, or can be determined according to the preset sampling number and the length of the initial reference track, and the distance between two adjacent sampling points is equal to the preset sampling distance.

For example, if the preset sampling distance is Δs, and the number of preset samples from the current projection position onwards is assumed to be N, the length of the initial reference track is n×Δs, and n+1 sampling points may be obtained.

S120, maximizing the projection distribution uniformity of the initial reference track as an objective function, and performing sequential quadratic programming under the limiting conditions of a kinematic model and safety constraints of the target vehicle to obtain a target control quantity sequence, wherein the target control quantity sequence comprises actual steering curvatures corresponding to all sampling points.

The projection distribution uniformity is the average degree of the projection distribution of the target vehicle on the two sides of the track on the plane where the initial reference track is located, and is used for reflecting the difference between the distances of the two sides of the vehicle relative to the initial reference track, the projection distribution uniformity is determined according to the state vector of each sampling point, and the state vector of each sampling point is determined according to the kinematic model, the state vector of the adjacent sampling point and the actual steering curvature of the adjacent sampling point.

It should be noted that the uniformity of the projection distribution may be understood as the proximity of the projected area of the target vehicle on one side of the initial reference trajectory to the projected area on the other side. Specifically, the larger the uniformity of the projection distribution, the closer the projected area size of the target vehicle on one side of the initial reference track is to the projected area size of the target vehicle on the other side, the smaller the difference between the distance between one side of the target vehicle and the initial reference track and the distance between the other side of the target vehicle and the initial reference track is, the closer both ends of the target vehicle, which are farthest from the initial reference track, are to the initial reference track, and the farther the distance between the two sides of the target vehicle and the road boundary or obstacle of the area to be planned is.

In this embodiment, the average degree of the projection distribution of the target vehicle on the plane where the initial reference track is located on both sides of the track under each sampling point may be determined according to the state vector of each sampling point, and further, the uniformity of the projection distribution of the initial reference track may be determined according to the average degree of each sampling point.

The state vector of the sampling point may be a vector describing an actual state of the target vehicle at the sampling point, and may be determined according to the kinematic model, an actual steering curvature of a previous sampling point, and a state vector of the previous sampling point. The actual steering curvature of the sampling point may be an actual vehicle steering curvature of the target vehicle at the sampling point, and may be used as a control amount for determining an actual steering curvature of the next sampling point at the sampling point.

For example, the state vector may be a first lateral deviation of the rear axle center point of the target vehicle from the initial reference trajectory, and the kinematic model may be a mathematical model for determining the state vector for each sampling point based on the determination.

In a specific embodiment, before performing the sequential quadratic programming, the method further includes: determining an arc conversion relation between a first transverse deviation of a rear axle center point on a target vehicle relative to an initial reference track, a heading deviation of the rear axle center point and a second transverse deviation of a preset position point on the target vehicle relative to the initial reference track; determining the first lateral deviation, the course deviation and the second lateral deviation as state vectors, and determining a state vector conversion relation between the state vectors of adjacent sampling points; and constructing a kinematic model of the target vehicle according to the arc conversion relation and the state vector conversion relation.

The center point of the rear axle is the center of the rear axle on the target vehicle. The first lateral deviation of the rear axle center point relative to the initial reference trajectory may be a distance between the rear axle center point and a projected point of the rear axle center point on the initial reference trajectory. The heading deviation of the center point of the rear axle can be specifically: the included angle between the tangent line of the projection point on the initial reference track and the central axis of the vehicle; the projection point may be a position point of the rear axis center point projected onto the initial reference track, for example, a straight line perpendicular to the initial reference track is constructed along the rear axis center point, and an intersection point of the straight line and the initial reference track may be used as the projection point.

The preset position point may be a point located on a vehicle center axis of the target vehicle and having a distance from a rear axis center point not smaller than a set value; wherein the set point can be determined according to the wheelbase of the vehicle. The preset position point and the rear axle center point are not limited to the set position of the preset position point, in this embodiment, the preset position point and the rear axle center point are related to a state vector describing the actual state of the target vehicle, and the state vector determines the uniformity of the projection distribution, so the preset position point and the rear axle center point can be understood as position points measuring the uniformity of the projection distribution, which affects the readiness of the uniformity of the projection distribution.

For example, a point which is centrally symmetrical to the central point of the rear axle can be selected as a preset position point on the central axle of the vehicle, namely, the central point of the front axle is taken as the preset position point, so that the accuracy of the calculated projection distribution uniformity is ensured. The second lateral deviation of the preset position point with respect to the initial reference trajectory may be a second lateral deviation of the front axis center point with respect to the initial reference trajectory, i.e., a distance between the front axis center point and a projection point of the front axis center point on the initial reference trajectory.

FIG. 4 is a schematic illustration of a lateral vehicle deviation in accordance with an embodiment of the present disclosure, as shown in FIG. 4, wherein e _d For a first lateral deviation of the rear axle center point of the target vehicle with respect to the initial reference trajectory, e _ψ As the heading deviation of the center point of the rear axle,is a second lateral deviation of the front axis center point from the initial reference trajectory. L (L) ₁ Indicating the wheelbase of the vehicle, < >>Represents the distance from the center of the rear axle of the vehicle to the rear edge of the vehicle,/->The distance from the center of the front axle of the vehicle to the front edge of the vehicle is represented by W, the width of the vehicle is represented by s, the arc length of the projection point of the center point of the rear axle on the initial reference track along the initial reference track is represented by delta, and the front wheel deflection angle of the target vehicle is represented by delta.

In this embodiment, the first lateral deviation, the heading deviation and the second lateral deviation at the sampling point together form a state vector of the sampling point. Compared with a mode of describing the state vector of the target vehicle by only adopting the first transverse deviation of the center point of the rear axle relative to the initial reference track, the method has the advantages that the state vector is described by adopting the transverse deviation of the center point of the rear axle and the preset position point, the method can be more suitable for the motion characteristics of large and medium-sized vehicles, the deviation of the body of the large and medium-sized vehicles relative to the initial reference track is better described, and the safety of the planned track is further ensured.

Wherein the second lateral deviation may be determined from the first lateral deviation and the heading deviation. Specifically, the first lateral deviation, the heading deviation and the second lateral deviation have an arc conversion relationship, that is, the arc conversion relationship can be obtained in an approximate manner of arc fitting, so that the second lateral deviation is determined through the first lateral deviation, the heading deviation and the arc conversion relationship. In this embodiment, the kinematic model may be a model describing tracking deviation, and may include an arc conversion relationship. That is, the kinematic model may determine, for each sampling point, a second lateral deviation of the sampling point from the arc transformation relationship, the first lateral deviation of the sampling point, and the heading deviation.

In addition to the arc transformation relationship, the kinematic model may also include a state vector transformation relationship. The state vector conversion relationship may be used to determine the state vector of the adjacent sampling point through the state vector of the sampling point, for example, determine the state vector of the next sampling point according to the state vector of the sampling point and the state vector conversion relationship.

Illustratively, the state vector conversion relationship may be expressed by the following formula:

wherein, the liquid crystal display device comprises a liquid crystal display device, Representing the differentiation of the variable with respect to time, i.e. the variation, s representing the arc length of the projection of the rear axis center point on the initial reference trajectory along the initial reference trajectory, e _y For a first lateral deviation e _ψ For heading bias, v denotes the speed at the center of the rear axle of the vehicle, κ _r (s) the reference curvature of the projection point of the center point of the rear axle on the initial reference trajectory, which can be abbreviated as kappa _r Delta is the front wheel slip angle of the vehicle, and represents the relation between the actual steering curvature kappa of the target vehicle and the front wheel slip angle of the vehicle is kappa=tan delta/L ₁ 。

The conversion of the above formula into a frenet coordinate system can result in:

e′ _d ＝(1-e _d k _r )tane _ψ ；

wherein, (·)' = d (·)/ds, represents the derivative of the variable with respect to the arc length s, e _d Representing a first lateral deviation, e _ψ Indicating heading deviation, and κ indicating actual steering curvature. The first lateral deviation and the rate of change of the heading deviation with respect to the arc length s can be obtained using the above formula. It should be noted that, the purpose of converting the formula into the frenet coordinate system is to: on the one hand, in order to eliminate the influence of the speed factor, on the other hand, the tracking deviation of the center point of the rear axle relative to the initial reference track, namely the first transverse deviation, can be better described.

Further, the state vector conversion relationship can be expressed by the following formula:

χ _i+1 ＝f(χ _i ,κ _i )；

Wherein χ is _i For the state vector at the ith sample point, χ _i+1 For the state vector at the i +1 sample point,κ _i is the actual steering curvature at the i-th sampling point.

For the above formula, the term may be developed and retained by Taylor, and linearization may be performed to obtain:

χ _i+1 ＝A _i χ _i +Bκ _i ；

in the method, in the process of the invention,

by constructing the kinematic model through the arc conversion relation and the state vector conversion relation, the kinematic model which can be used for determining the second transverse deviation of each sampling point and the state vector of the adjacent sampling point is obtained, and compared with the kinematic model which only describes the tracking deviation of the center point of the rear axle, the kinematic model of the embodiment can better describe the tracking deviation of the large and medium-sized vehicles.

Optionally, the arc conversion relationship satisfies the following formula:

wherein c _s ＝s+R _ref sine _ψ ， Representing a second lateral deviation; />Coordinates of the center of the circle fitted for the initial reference trajectory, +.>For the actual arc length corresponding to the preset position point, namely the actual arc length corresponding to the projection point of the preset position point on the initial reference track, R _ref For the turning radius of the initial reference track, s is the actual arc length corresponding to the center point of the rear axle, e _d For a first lateral deviation e _ψ Is the heading deviation.

Specifically, the above-described arc conversion relationship may describe an expression of a second lateral deviation of the front axis center point with respect to the initial reference trajectory in the frenet coordinate system. In the frenet coordinate system, the lateral deviation of each point on the vehicle wheelbase of the target vehicle relative to the initial reference track can be approximately fitted with an arc. Referring to fig. 5 for an exemplary, approximate schematic of tracking bias in a frenet coordinate system in an embodiment of the present disclosure, fig. 5 is a schematic diagram, wherein, Coordinates of the center of the circle fitted for the initial reference trajectory, +.>For the contour point on the target vehicle, +.>The actual arc length corresponding to each contour point.

Through the expression formula of the arc conversion relation, the determination of the second transverse deviation of the preset position point under each sampling point can be realized, so that the actual state of the target vehicle at each sampling point is measured by adopting the first transverse deviation, the second transverse deviation and the course deviation, and the accurate description of the deviation of the vehicle body relative to the initial reference track is realized.

In the present embodiment, the safety constraint may be a constraint that avoids the collision of the target vehicle with a road boundary or obstacle of the area to be planned.

In a specific embodiment, before performing the sequential quadratic programming, the method further includes: according to the fact that the sum of the preset safety distance and the third transverse deviation of the contour point relative to the initial reference track does not exceed the preset collision constraint, constructing the safety constraint of the target vehicle; wherein the contour point is a position point on the vehicle inside or the vehicle outside of the target vehicle, and the preset collision constraint is constituted by a road boundary constraint and an obstacle constraint.

The preset safety distance may be a preset safety distance threshold. The third lateral deviation of the contour point from the initial reference trajectory may be a distance between the contour point and a projection point of the contour point on the initial reference trajectory. The contour point may be any position point on the vehicle inside or the vehicle outside.

Specifically, the security constraint may be expressed by the following formula:wherein d _s For a predetermined safety distance, Pχ is the third lateral deviation,>representing a preset collision constraint consisting of a road boundary constraint and an obstacle constraint.

Among the above-mentioned safety constraints, the constraint purpose of the safety constraint is to: the third lateral deviation of the position point on the vehicle inside or the vehicle outside of the target vehicle with respect to the initial reference trajectory is made to satisfy the preset collision constraint-preset safety distance, that is, the third lateral deviation needs to be within the range of the road boundary constraint and the obstacle constraint minus the preset safety distance.

By limiting the third transverse deviation to be located in the range of subtracting the preset safety distance from the range of the road boundary constraint and the obstacle constraint, the vehicle body can be located in the road boundary when the track is planned, and the distance between the vehicle body and the road boundary or the obstacle meets a certain safety distance threshold, so that the collision between the target vehicle and the road boundary or the obstacle is avoided, and the safety of the target vehicle passing through the area to be planned is improved.

Optionally, the third lateral deviation is obtained according to the first lateral deviation and the heading deviation, and the calculation of the third lateral deviation satisfies the following formula:

Wherein c _s ＝s+R _ref sine _ψ ， Third lateral deviation of the mth contour point,/->Coordinates of the center of the circle fitted for the initial reference trajectory, +.>For the actual arc length corresponding to the contour point, R _ref Turning radius, e, being the initial reference trajectory _d For a first lateral deviation e _ψ For course deviation, r _± Taking R when the contour point is a position point on the vehicle interior side of the target vehicle _ref -W/2，r _± Taking R when the contour point is a position point on the vehicle outside of the target vehicle _ref +W/2, W is the width of the target vehicle.

In particular, for contour points on the vehicle outside or on the vehicle inside, a third lateral deviation of the contour points may be determined in a circular arc fit. Specifically, the third lateral deviation of the contour point on the vehicle outside and the contour point on the vehicle inside may be calculated using the following formulas, respectively:

in the method, in the process of the invention,third lateral deviation representing contour point on the outside of the vehicle body, +.>A third lateral deviation representing a contour point on the vehicle body inner side. M represents the number of contour points on the vehicle inside and the vehicle outside, and m.epsilon. (0, 1.,.

Through the formula, the third transverse deviation is accurately determined, and a result meeting the condition that the third transverse deviation does not exceed the difference between the preset collision constraint and the preset safety distance is solved according to the safety constraint.

Specifically, in this embodiment, the projection distribution uniformity of the initial reference trajectory may be maximized as an objective function, and sequential quadratic programming may be performed under the constraint of a kinematic model and a safety constraint, to obtain a target control amount sequence including the actual steering curvature corresponding to each sampling point. The calculation of the projection distribution uniformity can be determined by the areas of the projection distribution of the target vehicle on the two sides of the track on the plane where the initial reference track is located.

In a specific embodiment, with the projection distribution uniformity of the initial reference trajectory maximized as an objective function and with the kinematic model of the target vehicle and the safety constraint as limiting conditions, performing sequential quadratic programming to obtain a target control amount sequence, including:

determining safety margin reference values of all sampling points according to the weighted sum of the first transverse deviation and the second transverse deviation of all the sampling points, and determining the sum of the safety margin reference values of all the sampling points as passing safety so as to describe the uniformity of projection distribution through the passing safety; and sequentially performing secondary planning by taking the traffic safety of the initial reference track as an objective function and taking a kinematic model and safety constraint of the target vehicle as limiting conditions to obtain a target control quantity sequence.

Specifically, the projection distribution uniformity may be described by using a traffic safety, where the traffic safety is a sum of safety margin reference values of each sampling point, and the safety margin reference values are a weighted sum of the first lateral deviation and the second lateral deviation. The weight corresponding to the second lateral deviation and the second transverse line deviation may be a set value, or may be calculated according to the turning radius of the center point of the rear axle.

That is, the projection distribution uniformity may be described by a first lateral deviation and a second lateral deviation. The smaller the safety margin reference value of each sampling point is, the higher the safety margin of each sampling point is, namely the higher the safety margin of the passing of the target vehicle under each sampling point is, the smaller the passing safety is, the greater the uniformity of projection distribution is, and the higher the safety of the running of the target vehicle along the track is.

In the above embodiment, the projection distribution uniformity is described through the traffic safety, and under the condition that the kinematic model and the safety constraint are satisfied, an optimal control quantity sequence capable of realizing minimization of the traffic safety is obtained, the area of the target vehicle distributed on two sides of the track is not required to be calculated independently, the weighted sum of the first lateral deviation and the second lateral deviation is calculated, the track safety is ensured, and meanwhile, the track planning efficiency is improved.

Optionally, determining the safety margin reference value of each sampling point according to a weighted sum of the first lateral deviation and the second lateral deviation of each sampling point includes: determining the turning radius of a rear axle center point according to the distance from the preset position point to the front edge of the target vehicle, the wheelbase of the target vehicle and the width of the target vehicle; determining a weight corresponding to the second lateral deviation based on the turning radius of the rear axle center, the turning radius of the initial reference track and the wheelbase of the target vehicle; and determining the product of the weight corresponding to the second lateral deviation and the second lateral deviation, and determining a safety margin reference value according to the sum of the product and the first lateral deviation.

The turning radius of the rear axle center point is determined according to the distance from the preset position point to the front edge of the target vehicle, the wheelbase of the target vehicle and the width of the target vehicle, and the following formula can be satisfied:

wherein R is ₁ Is the turning radius of the center point of the rear axle, L ₁ R is the wheelbase of the target vehicle _ref The turning radius for the initial reference trajectory, W, is the width of the target vehicle.

Specifically, the above formula for determining the turning radius of the center point of the rear axle can be derived from the following formula, referring to fig. 6, fig. 6 is a schematic diagram of the relevant parameters of a safety margin reference value in the embodiment of the disclosure, for the turning radius R of any center point of the rear axle ₁ From the geometrical relationship, it is possible to:

wherein R is _1,r The maximum turning radius of the target vehicle may specifically be the turning radius corresponding to the position point of the target vehicle farthest from the initial reference track, as shown in fig. 6, may be the upper left corner end point of the target vehicle, and the corresponding turning radius is R _bus,r ；R _1,l The minimum turning radius of the target vehicle may specifically be a turning radius corresponding to a position point on the target vehicle closest to the initial reference track, as shown in fig. 6, may be a tire at the lower right corner of the target vehicle, where the corresponding turning radius is R _bus,l . R in FIG. 6 _road 、R ₁ Respectively turning radius corresponding to the initial reference track and turning radius corresponding to the center point of the rear axle,a second lateral deviation of the front axle center point, e _y Is the first lateral deviation of the rear axle center point.

Further, if the projection of the target vehicle on the plane where the initial reference track is located is distributed on both sides of the initial reference track as evenly as possible, the turning radius of the initial reference track needs to satisfy:

and synthesizing the formulas to obtain the formula for determining the turning radius of the center point of the rear axle. Further, the weight corresponding to the second lateral deviation may be calculated according to the turning radius of the rear axle center, the turning radius of the initial reference track, and the wheelbase. For example, see the following formula:

Wherein G is _k And the weight corresponding to the second transverse deviation. Further, a safety margin reference valueBy the method, the safety margin reference value under each sampling point is accurately calculated, and further the optimization solution with the sum of the safety margin reference values minimized as an objective function is realized.

It should be noted that the sequential quadratic programming process may be a process of iterative optimization solution. Sequential quadratic programming may be a method such as SQP (Sequential Quadratic Programming ), IPOPT (Interior Point OPTimizer, interior point optimizer) or CiLQR (Constrained Iterative Linear Quadratic Regulator ).

Optionally, minimizing the traffic safety of the initial reference track as an objective function, and performing sequential quadratic programming under the restriction condition of a kinematic model and a safety constraint of the target vehicle to obtain a target control quantity sequence, including:

the method comprises the steps of determining a current control quantity sequence by taking the traffic safety of an initial reference track as an objective function and taking a kinematic model and safety constraint of a target vehicle as limiting conditions; and judging whether the iteration cut-off condition is met, if not, updating the initial reference track based on the current control quantity sequence, returning to execute the step of minimizing the traffic safety as an objective function, and determining the current control quantity sequence by using the kinematic model and the safety constraint as limiting conditions until the iteration cut-off condition is met, so as to obtain the target control quantity sequence.

The iteration cut-off condition may be that the iteration number reaches a preset number, or that the difference between the traffic safety of the initial reference track obtained after each iteration gradually converges.

Specifically, the lane line can be used as an initial reference track, the current control quantity sequence can be solved according to the objective function and the limiting condition, the initial reference track can be redetermined according to the current control quantity sequence and the kinematic model, the projection distribution uniformity of the newly-determined initial reference track is redefined as the objective function, the kinematic model and the safety constraint are used as limiting conditions, the current control quantity sequence can be solved again, if the iteration cut-off condition is not met, the initial reference track can be determined according to the current control quantity sequence and the kinematic model continuously, the process is repeated until the iteration cut-off condition is met, and the current control quantity sequence determined at last is used as the target control quantity sequence.

It should be noted that, when the initial reference track is updated, the sampling points in the initial reference track may also be updated together. The actual steering curvature corresponding to each sampling point in the target control amount sequence may be an actual steering curvature issued before the projection point of the target vehicle reaches the next sampling point of the sampling point. Through the iterative optimization solving process, an optimal control quantity sequence can be obtained after multiple iterations, and therefore the safety of the track is improved.

In addition to considering the safety of the track, in this embodiment, the smoothness of the track may also be considered, so as to plan a track with high smoothness while ensuring the safety.

In a specific embodiment, the method further comprises: determining a smoothness reference value of the sampling point according to the difference value between the actual steering curvature of the sampling point and the actual steering curvature of the previous sampling point, and determining the sum of the smoothness reference values of the sampling points as the passing smoothness; determining a traffic reference quantity according to the traffic smoothness and the traffic safety, minimizing the traffic reference quantity of the initial reference track as an objective function, and performing sequential quadratic programming under the limiting conditions of a kinematic model and safety constraint of the target vehicle to obtain a target control quantity sequence.

The square value of the difference between the actual steering curvature of the sampling point and the actual steering curvature of the previous sampling point can be used as a smoothness reference value of the sampling point, and then the sum of average smoothness reference values of all the sampling points is used as the passing smoothness. Specifically, the smaller the traffic smoothness is, the higher the smoothness of the track is.

Further, taking the sum of the traffic smoothness and the traffic safety as a traffic reference quantity, minimizing the traffic reference quantity as an objective function, and solving a target control quantity sequence under the condition that the limiting condition is met. According to the embodiment, the optimal control quantity sequence with smaller traffic smoothness and traffic safety can be obtained, and further, a track with high safety and smoothness is planned.

Considering that the actual steering curvature is too large or the variation is too large, the smoothness and safety of the target vehicle passing through the area to be planned can be affected. Optionally, the method provided in this embodiment further includes: maximizing the projection distribution uniformity of the initial reference track as an objective function, and performing sequential quadratic programming under the limiting conditions of a kinematic model, a safety constraint, a first steering curvature constraint and a second steering curvature constraint of a target vehicle to obtain a target control quantity sequence; the first steering curvature constraint is used for constraining the actual steering curvature of each sampling point to be not more than a preset threshold value, and the second steering curvature constraint is used for constraining the difference value between the actual steering curvatures of adjacent sampling points to be not more than a preset variation.

That is, the constraints may include a first steering curvature constraint and a second steering curvature constraint in addition to the kinematic model and the safety constraint. Wherein the first steering curvature constraint is used to constrain the actual steering curvature not to exceed a preset threshold, e.g., |κ _i |≤κ _max I e (0, 1,) N-1. The change amount of the actual steering curvature of the second steering curvature constraint does not exceed the preset changeThe amount, e.g., |kappa _i -κ _i-1 |≤Δκ _max I e (0, 1,., N-1), N is the number of sampling points.

In the above embodiment, by using the first steering curvature constraint and the second steering curvature constraint as the constraint conditions, the optimal control amount sequence satisfying the first steering curvature constraint and the second steering curvature constraint can be solved, and the safety and smoothness of the planned trajectory can be further improved.

S130, determining a target reference track based on the target control quantity sequence, and determining each tracking point which enables the difference between the distances between the two sides of the vehicle and the target reference track to be minimum in the running process of the target reference track, wherein the tracking points are the position points of the target vehicle running along the target reference track, and the tracking points are not identical.

Specifically, after the target control amount sequence is obtained, a target reference track with the same turning curvature as the actual turning curvature at each sampling point can be obtained through each actual turning curvature in the target control amount sequence.

Further, tracking points for realizing the respective actual steering curvatures can be obtained by the respective actual steering curvatures. The tracking point may be a position point for controlling the vehicle to travel along the target reference trajectory.

In the present embodiment, the speed control information during the travel of the target reference trajectory may also be determined. Specifically, the speed information and the acceleration information can be used as state vectors together, and then the speed information and the acceleration information at each sampling point can be obtained through a kinematic model and the target control quantity sequence after the target control quantity sequence is solved.

After the target reference track and each tracking point in the target reference track are obtained, the target reference track and each tracking point can be issued to an automatic driving control system of the target vehicle, so that the automatic driving control system controls the target vehicle to run along the target reference track through each tracking point.

According to the vehicle track planning method provided by the embodiment, the initial reference track of the target vehicle in the area to be planned is obtained, the average degree of the projection of the target vehicle on the plane of the initial reference track on two sides of the track is maximized as an objective function, a kinematic model and safety constraint are used as limiting conditions, sequential quadratic programming is carried out, a target control quantity sequence comprising the actual steering curvature corresponding to each sampling point is obtained, and then the target reference track and each tracking point which is not identical in the running process of the target reference track are determined through the target control quantity sequence, so that each tracking point with the minimum difference between the distances of two sides of the vehicle relative to the track is obtained in the running process of the target reference track, the problem that collision risk exists between one side of the target vehicle and the road boundary or roadside obstacle in the area due to overlarge distance between the one side and the track is avoided, the problem that the vehicle can safely pass through the narrow area is solved, and the problem that the track of the narrow area is difficult to plan for the vehicle with the long wheelbase in the prior art is solved.

Fig. 7 is a schematic structural diagram of a vehicle trajectory planning device in an embodiment of the disclosure. As shown in fig. 7: the device comprises: an initial trajectory determination module 710, a sequential quadratic programming module 720, and a target trajectory determination module 730.

An initial track determining module 710, configured to obtain an initial reference track of the target vehicle in the area to be planned, where the initial reference track includes sampling points;

the sequential quadratic programming module 720 is configured to perform sequential quadratic programming according to the projection distribution uniformity of the initial reference trajectory as an objective function and the kinematic model and the safety constraint of the target vehicle as constraints, so as to obtain a target control amount sequence, where the target control amount sequence includes actual steering curvatures corresponding to the sampling points;

a target track determining module 730, configured to determine a target reference track based on the target control amount sequence, and determine each tracking point that minimizes a difference between distances between two sides of a vehicle relative to the target reference track during a driving process of the target reference track, where the tracking points are location points on the target vehicle that drive along the target reference track, and each tracking point is not identical;

The vehicle track planning device provided by the embodiment of the present disclosure may execute steps in the vehicle track planning method provided by the embodiment of the present disclosure, and the execution steps and the beneficial effects are not described herein.

Fig. 8 is a schematic structural diagram of an electronic device in an embodiment of the disclosure. Referring now in particular to fig. 8, a schematic diagram of an electronic device 500 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device shown in fig. 8 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.

As shown in fig. 8, an electronic device 500 may include a processing means (e.g., a central processor, a graphics processor, etc.) 501 that may perform various suitable actions and processes to implement the methods of embodiments as described in the present disclosure according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart, thereby implementing the vehicle trajectory planning method as described above. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or from the storage means 508, or from the ROM 502. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 501.

It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to:

Alternatively, the electronic device may perform other steps described in the above embodiments when the above one or more programs are executed by the electronic device.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Scheme 1, a vehicle trajectory planning method, the method comprising:

Solution 2, the method according to solution 1, before the performing sequential quadratic programming, the method further includes:

determining an arc conversion relation among a first transverse deviation of a rear axle center point on the target vehicle relative to an initial reference track, a course deviation of the rear axle center point and a second transverse deviation of a preset position point on the target vehicle relative to the initial reference track;

determining the first lateral deviation, the course deviation and the second lateral deviation as state vectors, and determining a state vector conversion relation between the state vectors of the adjacent sampling points;

and constructing a kinematic model of the target vehicle according to the arc conversion relation and the state vector conversion relation.

Scheme 3, the method according to scheme 2, the arc transformation relation satisfies the following formula:

wherein c _s ＝s+R _ref sine _ψ ， Representing the second lateral deviation;coordinates of the center of a circle fitted to the initial reference trajectory,/->For the actual arc length corresponding to the preset position point, R _ref A turning radius of the initial reference track, s is the center point pair of the rear axleActual arc length of the reaction, e _d For the first lateral deviation e _ψ And (5) the heading deviation.

In the scheme 4, according to the method of the scheme 2, the projection distribution uniformity of the initial reference track is maximized as an objective function, and the kinematic model and the safety constraint of the target vehicle are used as limiting conditions to perform sequential quadratic programming, so as to obtain a target control quantity sequence, which includes:

determining a safety margin reference value of each sampling point according to a weighted sum of the first lateral deviation and the second lateral deviation of each sampling point, and determining the sum of the safety margin reference values of each sampling point as a passing safety degree so as to describe the projection distribution uniformity through the passing safety degree;

and sequentially performing secondary planning by taking the traffic safety of the initial reference track as an objective function and taking the kinematic model and the safety constraint of the target vehicle as limiting conditions to obtain a target control quantity sequence.

According to the method of the scheme 5, according to the scheme 4, the minimizing the traffic safety of the initial reference trajectory is used as an objective function, and the sequential quadratic programming is performed under the restriction conditions of the kinematic model and the safety constraint of the target vehicle, so as to obtain a target control quantity sequence, which comprises:

determining a current control quantity sequence by taking the traffic safety of the initial reference track as an objective function and taking a kinematic model and safety constraint of the target vehicle as limiting conditions;

And judging whether an iteration cut-off condition is met, if not, updating the initial reference track based on the current control quantity sequence, returning to execute the step of minimizing the traffic safety as an objective function, and determining the current control quantity sequence by using the kinematic model and the safety constraint as the limiting condition until the iteration cut-off condition is met, so as to obtain the objective control quantity sequence.

Solution 6, the method according to claim 4, wherein determining the safety margin reference value of each sampling point according to a weighted sum of the first lateral deviation and the second lateral deviation of each sampling point includes:

determining the turning radius of the rear axle center point according to the distance from the preset position point to the front edge of the target vehicle, the wheelbase of the target vehicle and the width of the target vehicle;

determining a weight corresponding to the second lateral deviation based on a turning radius of the rear axle center, a turning radius of the initial reference track, and a wheelbase of the target vehicle;

and determining the product of the weight corresponding to the second lateral deviation and the second lateral deviation, and determining a safety margin reference value according to the sum of the product and the first lateral deviation.

Solution 7 the method according to solution 2, further comprising, prior to said performing sequential quadratic programming;

constructing a safety constraint of the target vehicle according to the fact that the sum of the preset safety distance and the third transverse deviation of the contour point relative to the initial reference track does not exceed the preset collision constraint;

wherein the contour point is a position point on a vehicle inside or a vehicle outside of the target vehicle, and the preset collision constraint is constituted by a road boundary constraint and an obstacle constraint.

The method according to claim 8, wherein the third lateral deviation is obtained according to the first lateral deviation and the heading deviation, and the calculation of the third lateral deviation satisfies the following formula:

wherein c _s ＝s+R _ref sine _ψ ， Third lateral deviation of the mth contour point,/->Coordinates of the center of a circle fitted to the initial reference trajectory,/->For the actual arc length corresponding to the contour point, R _ref E, turning radius of the initial reference track _d For the first lateral deviation e _ψ For the course deviation, r _± Taking R when the contour point is a position point on the vehicle inside of the target vehicle _ref -W/2，r _± Taking R when the contour point is a position point on the vehicle outside of the target vehicle _ref +W/2, W is the width of the target vehicle.

Solution 9, the method according to solution 4, the method further comprising:

determining a smoothness reference value of the sampling point according to the difference value between the actual steering curvature of the sampling point and the actual steering curvature of the previous sampling point, and determining the sum of the smoothness reference values of the sampling points as the passing smoothness;

determining a traffic reference quantity according to the traffic smoothness and the traffic safety, minimizing the traffic reference quantity of the initial reference track as an objective function, and performing sequential quadratic programming under the restriction conditions of the kinematic model and the safety constraint of the target vehicle to obtain a target control quantity sequence.

Solution 10, the method according to solution 1, the method further comprising:

maximizing the projection distribution uniformity of the initial reference track as an objective function, and performing sequential quadratic programming under the limiting conditions of a kinematic model, a safety constraint, a first steering curvature constraint and a second steering curvature constraint of the target vehicle to obtain a target control quantity sequence;

the first steering curvature constraint is used for constraining the actual steering curvature of each sampling point to be not more than a preset threshold value, and the second steering curvature constraint is used for constraining the difference value between the actual steering curvatures of the adjacent sampling points to be not more than a preset variation.

Scheme 11, a vehicle trajectory planning device, comprising:

Scheme 12, an electronic device, the electronic device comprising:

one or more processors;

a storage means for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the methods of any of aspects 1-10.

Aspect 13, a computer readable storage medium, having stored thereon a computer program, which when executed by a processor, implements the method according to any of aspects 1-10.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).

Claims

1. A vehicle trajectory planning method, the method comprising:

2. The method of claim 1, wherein prior to said performing sequential quadratic programming, the method further comprises:

3. The method of claim 2, wherein the arc transformation relationship satisfies the following formula:

wherein c _s ＝s+R _ref sine _ψ ， Representing the second lateral deviation; />Coordinates of the center of a circle fitted to the initial reference trajectory,/->For the actual arc length corresponding to the preset position point, R _ref S is the actual arc length corresponding to the center point of the rear axle, e _d For the first lateral deviation e _ψ And (5) the heading deviation.

4. The method according to claim 2, wherein the step of sequentially performing quadratic programming with the projection distribution uniformity of the initial reference trajectory maximized as an objective function and with the kinematic model of the target vehicle and the safety constraint as constraints to obtain a target control amount sequence includes:

5. The method according to claim 4, wherein the step of sequentially performing quadratic programming with the traffic safety of the initial reference trajectory minimized as an objective function and with the kinematic model of the target vehicle and the safety constraint as constraints to obtain a target control amount sequence includes:

6. The method of claim 4, wherein determining the safety margin reference value for each of the sampling points based on a weighted sum of the first lateral deviation and the second lateral deviation for each of the sampling points comprises:

7. The method of claim 2, wherein prior to said performing sequential quadratic programming, the method further comprises:

8. A vehicle trajectory planning device, characterized by comprising:

9. An electronic device, the electronic device comprising:

one or more processors;

a storage means for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-7.