CN113671941B

CN113671941B - Trajectory planning method, device, equipment and storage medium

Info

Publication number: CN113671941B
Application number: CN202010414249.2A
Authority: CN
Inventors: 李柏; 边学鹏
Original assignee: Beijing Jingdong Qianshi Technology Co Ltd
Current assignee: Beijing Jingdong Qianshi Technology Co Ltd
Priority date: 2020-05-15
Filing date: 2020-05-15
Publication date: 2024-11-19
Anticipated expiration: 2040-05-15
Also published as: CN113671941A

Abstract

The embodiment of the present invention discloses a trajectory planning method, device, equipment and storage medium, the method comprising: obtaining initial trajectory information obtained by making trajectory decisions for a target vehicle; constructing a nonlinear proposition for target trajectory planning corresponding to the target vehicle, wherein the nonlinear proposition for target trajectory planning comprises: a trajectory cost function and driving constraints, and the driving constraints comprise: a collision avoidance constraint determined based on a tunneling modeling method; solving the nonlinear proposition for target trajectory planning according to the initial trajectory information, and determining the target planning trajectory corresponding to the target vehicle. The technical solution of the embodiment of the present invention can improve the efficiency of trajectory planning.

Description

Track planning method, device, equipment and storage medium

Technical Field

Embodiments of the present invention relate to computer technologies, and in particular, to a track planning method, apparatus, device, and storage medium.

Background

With the rapid development of computer technology, vehicles can be driven automatically without people in structured roads. In unmanned automatic driving scenarios, it is often necessary to make track decisions (i.e., running decisions) on the vehicle to determine which side the vehicle is to detour around obstacles, whether to preempt or let go, etc. After the track decision is made on the vehicle, track planning is needed to be performed so as to perform operations such as smoothing on the decided rough running track and the like to obtain a more accurate planned track.

At present, the existing track planning mode plans according to the information of all obstacles in a driving scene so as to ensure that the vehicle cannot collide with the obstacles when driving along the planned track.

However, in the process of implementing the present invention, the inventors found that at least the following problems exist in the prior art:

Because the length of the vehicle is limited, the vehicle and all obstacles are unlikely to collide at any moment, so that the information of all the obstacles is considered at any moment in the conventional track planning mode, a large amount of redundant calculation exists, and the track planning efficiency is greatly reduced.

Disclosure of Invention

The embodiment of the invention provides a track planning method, a device, equipment and a storage medium, which are used for improving track planning efficiency.

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

Acquiring initial track information obtained by track decision of a target vehicle;

Constructing a target track planning nonlinear proposition corresponding to the target vehicle, wherein the target track planning nonlinear proposition comprises: a trajectory cost function and a travel constraint condition, the travel constraint condition comprising: collision avoidance constraint conditions determined based on a tunneling modeling mode;

And solving the nonlinear proposition of the target track planning according to the initial track information, and determining the target planning track corresponding to the target vehicle.

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

The initial track information acquisition module is used for acquiring initial track information obtained by carrying out track decision on the target vehicle;

the track planning nonlinear proposition construction module is used for constructing a target track planning nonlinear proposition corresponding to the target vehicle, wherein the target track planning nonlinear proposition comprises: a trajectory cost function and a travel constraint condition, the travel constraint condition comprising: collision avoidance constraint conditions determined based on a tunneling modeling mode;

and the target planning track determining module is used for solving the target track planning nonlinear proposition according to the initial track information to determine the target planning track corresponding to the target vehicle.

In a third aspect, an embodiment of the present invention further provides an apparatus, including:

one or more processors;

a memory 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 trajectory planning method as described in any of the embodiments of the present invention.

In a fourth aspect, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a trajectory planning method according to any of the embodiments of the present invention.

The embodiments of the above invention have the following advantages or benefits:

The collision avoidance constraint conditions are determined based on the tunneling modeling mode, namely, the drivable tunnel region of the target vehicle at each moment is obtained, so that obstacles which cannot influence the driving of the target vehicle are not required to be considered in the track planning process, the complexity of the collision avoidance constraint conditions is reduced, a simpler nonlinear proposition of the target track planning is constructed, the nonlinear proposition of the target track planning can be quickly solved in a mode of minimizing a track cost function, the target planning track corresponding to the target vehicle is obtained, redundant calculation is avoided, and the track planning efficiency is improved.

Drawings

Fig. 1 is a flowchart of a track planning method according to a first embodiment of the present invention;

Fig. 2 is an example of a driving scenario according to a first embodiment of the present invention;

FIG. 3 is an example of a two-degree-of-freedom vehicle kinematic model according to a first embodiment of the present invention;

FIG. 4 is an example of a localized tunnel region in accordance with a first embodiment of the present invention;

Fig. 5 is a flowchart of a track planning method according to a second embodiment of the present invention;

FIG. 6 is an example of a construction process of a local tunnel region according to the second embodiment of the present invention;

fig. 7 is a flowchart of a track planning method according to a third embodiment of the present invention;

fig. 8 is a schematic structural diagram of a track planning apparatus according to a fourth embodiment of the present invention;

Fig. 9 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention.

Detailed Description

The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.

Example 1

Fig. 1 is a flowchart of a track planning method according to a first embodiment of the present invention, where the embodiment is applicable to a situation where an autonomous vehicle performs track planning, and in particular, to a situation where an autonomous vehicle in a structured road performs track planning. The method may be performed by a trajectory planning device, which may be implemented in software and/or hardware, integrated in a device with autopilot functionality, such as any type of vehicle. As shown in fig. 1, the method specifically includes the following steps:

S110, obtaining initial track information obtained by track decision of the target vehicle.

The target vehicle may be any type of autonomous vehicle in the road where trajectory planning is required. A road may refer to a structured road. The structured road may refer to a road with a driving rule on which the target vehicle is to be driven. Illustratively, the structured road may be a road having a guide wire to indicate a traveling direction, such as an urban road, or the like. The trajectory decision may refer to a decision trajectory for deciding on which side the target vehicle is to detour around an obstacle when encountering the obstacle, deciding on preemption or let go, etc. The initial track information may refer to track information corresponding to a decision track obtained after track decision. For example, the initial trajectory information may include, but is not limited to: and the determined driving path information and driving speed information of the target vehicle.

Specifically, track decision can be performed on the target vehicle based on the information of each static obstacle and each dynamic obstacle in the structured road and the own information of the target vehicle, a reasonable and feasible decision track of the target vehicle running on the road is determined, and the track information of the decision track is used as initial track information of the target vehicle in the track planning process.

S120, constructing a target track planning nonlinear proposition corresponding to a target vehicle, wherein the target track planning nonlinear proposition comprises: track cost function and travel constraint condition, travel constraint condition includes: collision avoidance constraints determined based on tunneled modeling.

The target trajectory planning nonlinear proposition may refer to a trajectory planning task-oriented nonlinear planning (NonLinear Programming, NLP) proposition. The nonlinear proposition of the target track planning can be used as an optimal control proposition, so that the proposition can be solved by a mode of calculating optimal control (Computational Optimal Control) or a mode of numerical optimal control (Numerical Optimal Control). The trajectory planning task may refer to planning a travel trajectory conforming to a travel constraint between a start time motion state and an end time motion state of the target vehicle. The collision avoidance constraint may refer to a constraint that avoids collision with an obstacle in a driving scene. Fig. 2 gives an example of a driving scenario. As shown in fig. 2, a driving scene may include stationary and moving obstacles and a scatter for describing a road edge, and a collision avoidance constraint may be used to describe a condition that a target vehicle (i.e., vehicle i) does not overlap with all of the obstacles and the road edge. The tunneling modeling method may be a method of laying a partial tunnel in a time space based on initial trajectory information and separating an actual travelable area of the target vehicle from an obstacle in the environment. The track cost function may refer to an optimized objective function of a nonlinear proposition of the target track planning, and is an index formula for screening high-quality tracks. In general, there are a plurality of trajectories that satisfy the running constraint conditions, so that it is necessary to screen out an optimal trajectory based on a trajectory cost function as a final result. Because of the running constraint condition and the index type for optimizing in the track planning task, the method can be suitable for describing the track planning proposition of the automatic driving vehicle in the form of an optimal control problem.

Specifically, the travelable tunnel area of the target vehicle at each moment can be determined based on the tunneling modeling mode, so that the complex collision avoidance constraint conditions directly established based on all obstacles in the road are converted into the simple collision avoidance constraint conditions in the boundary constraint mode, only the obstacles around the target vehicle are needed to be considered, the obstacles which are far away and do not influence the travel of the target vehicle are not needed to be considered, and the complexity of the collision avoidance constraint conditions is greatly reduced. The corresponding trajectory cost function may be determined based on the desire that the trajectory be as smooth as possible and as close to the decision trajectory as possible. Based on the track cost function and the collision avoidance constraint condition, a simpler nonlinear proposition of target track planning described by utilizing an optimal control problem mode can be constructed.

And S130, solving a nonlinear proposition of the target track planning according to the initial track information, and determining a target planning track corresponding to the target vehicle.

Specifically, the initial trajectory information can be used as an initial solution to solve a nonlinear proposition of the target trajectory planning, namely, the trajectory cost function is minimized under the condition that the collision avoidance constraint condition determined based on the tunneling modeling mode is met, so that an optimal solution can be obtained, namely, the target planning trajectory corresponding to the target vehicle is determined. The present embodiment may use an interior point algorithm (Interior Point Method, IPM) to solve for the target trajectory planning nonlinear proposition. According to the method and the device, the nonlinear proposition of the simpler target track planning is solved, so that redundant calculation can be avoided, and the track planning efficiency is improved.

According to the technical scheme, the collision avoidance constraint conditions are determined based on the tunneling modeling mode, namely, the drivable tunnel region of the target vehicle at each moment is obtained, so that obstacles which cannot influence the driving of the target vehicle are not required to be considered in the track planning process, the complexity of the collision avoidance constraint conditions is reduced, a simpler nonlinear proposition of the target track planning is constructed, the nonlinear proposition of the target track planning can be quickly solved in a mode of minimizing a track cost function, the target planning track corresponding to the target vehicle is obtained, redundant calculation is avoided, and the track planning efficiency is improved.

On the basis of the technical scheme, the running constraint conditions can further comprise: kinematic constraints of the target vehicle, boundary value constraints, and vehicle interior mechanical constraints.

The kinematic constraint condition of the target vehicle may refer to a limitation of the motion capability of the target vehicle during driving. The boundary value constraint condition may refer to a motion state specified by a start time and an end time of the target vehicle. Vehicle interior mechanical constraints may refer to limitations in the ability of the target vehicle to move internally.

For example, a two-degree-of-freedom model may be used to describe vehicle motion. Fig. 3 gives an example of a two-degree-of-freedom vehicle kinematic model. As shown in fig. 3, the two-degree-of-freedom model may combine two front wheels and two rear wheels of the vehicle into virtual single wheels in the longitudinal axis direction of the vehicle body, and indirectly determine the front wheel rotation angle, the running speed, and the like of the vehicle by determining the rotation angular velocity of the virtual front wheels and the linear acceleration variable of the virtual rear wheels, thereby realizing the movement of the vehicle.

Based on fig. 3, the kinematic constraints of the target vehicle can be expressed as:

Wherein, the driving time t epsilon [0, t _f],t_f represents the termination time, which can be constant or variable; (x _i(t),y_i (t)) represents the rear axle midpoint coordinates of the vehicle i in the cartesian coordinate system XOY (i.e., rectangular coordinate system); v _i (t) and a _i (t) represent the speed and acceleration, respectively, in the longitudinal direction of the vehicle body so that the direction in which the vehicle advances is the positive direction; phi _i (t) represents the deflection angle of the front wheel of the vehicle, and the left turning direction is taken as the positive direction; omega _i (t) represents the front wheel deflection angular velocity to be positive outwards perpendicular to the XOY coordinate system; θ _i (t) represents the attitude angle of the vehicle in the XOY coordinate system, i.e., the rotation angle from the positive direction of the X axis of the coordinate system to the positive direction of the longitudinal axis of the vehicle body, in the counterclockwise direction. Where x _i(t)、y_i(t)、φ_i(t)、θ_i (t) and v _i (t) belong to the state variables x (t), a _i (t) and ω _i (t) belong to the control variables u (t). If the motion state x (0) of the vehicle i at the initial moment and u (t) on the time domain of [0, t _f ] are obtained, the motion state x (t) on the time domain can be determined one by one through integration, and then a specific motion track of the vehicle i is obtained.

Since the time t=t _f is not the macroscopic end point of the entire driving process, t _f can be set to a preset ratio of the track decision time domain length t _decision, i.e. t _f＝t_decision·γ_rate, where 0 < γ _rate < 1 represents a preset ratio coefficient.

Based on fig. 3, the starting point constraint in the edge constraint can be expressed as:

[v_i(0),φ_i(0),x_i(0),y_i(0),θ_i(0)]＝[v_0i,p_0i,x_0i,y_0i,θ_0i] (2)

Wherein, [ v _0i,φ_0i,x_0i,y_0i,θ_0i ] may be motion state information acquired by an in-vehicle sensor. The termination time t _f is not the end point of the macroscopic upward driving process, so that the end point of the local planning time domain can not be hard limited.

Based on fig. 3, the vehicle interior mechanical constraints can be expressed as:

|φ_i(t)|≤Φ_max,|a_i(t)|≤a_max,|v_i(t)|≤v_max,|ω_i(t)|≤Ω_max,t∈[0,t_f]. (3)

Where Φ _max、a_max、v_max and Ω _max are the maximum magnitudes of the respective state and control variables, respectively. Phi _max represents the maximum allowable yaw angle value of the vehicle front wheel steering angle phi _i (t); v _max is the upper limit of safe driving speed of the vehicle in low speed scenarios; to ensure passenger comfort, a _max and Ω _max are maximum magnitudes of linear acceleration and front wheel rotational speed, respectively. For example, if a smooth change in the acceleration variable is desired, the differential variable jerk _i(t)＝da_i (t)/dt of the acceleration may be supplemented and limited.

Based on fig. 3, the track cost function of the target vehicle i can be expressed as:

Where (x _decision(t),y_decision(t),θ_decision (t)) represents the decision trajectory of the target vehicle i.

Specifically, the track cost function is minimized by taking the collision avoidance constraint condition, the kinematic constraint condition of the target vehicle, the boundary value constraint condition and the mechanical constraint condition in the vehicle which are determined based on the tunneling modeling mode as the running constraint condition, so that a more accurate target planning track can be obtained, and the track planning accuracy is further improved.

It should be noted that, in this embodiment, the track planning is performed under the cartesian coordinate system XOY independent of the guiding wires, so that the task of track planning on the road may be completely independent of the guiding wires.

Based on the technical scheme, determining collision avoidance constraint conditions based on the tunneling modeling mode can comprise: covering two circular areas with preset radiuses on a body area of a target vehicle, and determining movement tracks of two circle centers; determining a local tunnel region corresponding to each circle center at each sampling time in a track planning time domain according to the motion tracks of the two circle centers and a preset radius; and determining collision avoidance constraint conditions according to the local tunnel region.

Wherein the preset radius may be set based on the size of the target vehicle. For example, the radius of two circumscribed circles of the target vehicle may be taken as the preset radius. As shown in fig. 3, the preset radius may be determined based on the front-rear wheel distance L _w, the vehicle front suspension distance L _f, the vehicle rear suspension distance L _r, and the vehicle width L _b. For example, the preset radius corresponding to the target vehicle i is: The local tunnel region corresponding to each center may refer to a drivable region of the target vehicle.

Specifically, the circle centers of two circumscribed circles of the target vehicle can be utilized to represent the target vehicle, and corresponding local tunnel areas are constructed for each circle center, so that tunneling modeling of the target vehicle can be realized. For example, a rectangular body region of the target vehicle may be uniformly covered with two circles of a preset radius R _i. Based on the initial track information (x _decision(t),y_decision(t),θ_decision (t)) corresponding to the decision track and the corresponding relation between the center position coordinates and the center point coordinates of the rear wheel axle of the vehicle position, the motion track of two centers can be determined and respectively recorded as: p _r = (xr (t), yr (t)) and P _f = (xf (t), yf (t)). The corresponding relation between the center position coordinate and the midpoint coordinate of the rear wheel axle of the vehicle position can be expressed as follows:

It can be seen that the constraint that the vehicle does not collide with an obstacle can be translated into: p _r and P _f keep at least a distance R _i from the obstacle, so that P _r and P _f keep at least a distance R _i from the obstacle by limiting the value range of P _r and P _f, and further simpler collision avoidance constraint conditions are obtained. For example, the track planning time domain [0, t _f ] may be uniformly sampled (N _fe +1) for time instants based on the discretized accuracy parameter N _fe in the numerical optimization, where time instant _k is t _k＝t_f·(k-1)/N_fe. For each sampling time, a local tunnel region corresponding to each circle center can be determined, and then the value ranges of P _r and P _f, namely collision avoidance constraint conditions, can be obtained based on the local tunnel region. According to the embodiment, the target vehicle is represented by using the two circle centers as mass points, and the corresponding local tunnel area is constructed for each circle center, so that the tunneling modeling process of the target vehicle can be realized more rapidly, simpler collision avoidance constraint conditions are obtained, and the track planning efficiency is further improved.

Illustratively, determining collision avoidance constraints from the local tunnel region may include: determining position coordinates of four regional vertexes of a local tunnel region in a Cartesian coordinate system; and determining a constraint range of the position coordinates of each circle center at each sampling time according to the position coordinates of the vertexes of the four areas, and obtaining collision avoidance constraint conditions.

Wherein the local tunnel region may be a rectangular region. Region vertices may refer to four vertices of a rectangular region. For example, fig. 4 gives an example of a local tunnel region. Fig. 4 shows the movement path P _r (t) of the center P _r and the position P _r(t_k of the center P _r at the sampling point t _k. In fig. 4, a small rectangular region represents a partial tunnel region corresponding to the center P _r at the sampling time t _k. The large rectangular area boundary represents the critical point at which the target vehicle collides with the obstacle. The distance between the two rectangular areas in fig. 4 may be a preset radius R _i to ensure that P _r is at least a distance R _i from the obstacle.

Specifically, the position coordinates of the four area vertices of the local tunnel area can be obtained under the cartesian coordinate system XOY in fig. 3, and the position coordinates of the corresponding circle centers can be limited based on the position coordinates of the four area vertices, so as to ensure that the position coordinates of the corresponding circle centers are located in the local tunnel area, thereby obtaining the collision avoidance constraint condition. For example, as in fig. 4, the constraint range of the center position coordinates at the sampling time t _k of the center P _r = (xr (t), yr (t)) is: x _{r_lb_k}≤xr(t_k)≤x_{r_ub_k},y_{r_lb_k}≤yr(t_k)≤y_{r_ub_k}. Similarly, the constraint range of the position coordinate of the center P _f may also be determined based on the local tunnel region corresponding to the center P _f. The collision avoidance constraint condition constituted with the simple boundary in the present embodiment can be expressed as:

It should be noted that no matter how many obstacles exist in the driving scene, only constraint conditions of 2 (N _fe +1) group forms such as (6) exist, so that stability of solution of proposition can be realized.

Illustratively, the target trajectory planning nonlinear proposition P _NLP0 can be expressed in its entirety as:

minimization: track cost function (4)

S.t. kinematic constraints (1)

Side value constraint (2)

Vehicle interior mechanical constraint (3)

Center association (5)

Collision avoidance restraint (6)

Specifically, by solving the nonlinear proposition P _NLP0 of the target track planning, the value of the track cost function can be minimized on the premise of meeting all constraint conditions, so that a more accurate target planning track can be obtained, and meanwhile, the track planning efficiency and the track planning accuracy are improved.

Example two

Fig. 5 is a schematic diagram of a track planning method according to a second embodiment of the present invention, where the "determining a local tunnel area corresponding to each circle center at each sampling time in a track planning time domain according to a motion track of two circle centers and a preset radius" is optimized on the basis of the foregoing embodiments. Wherein the explanation of the same or corresponding terms as those of the above embodiments is not repeated herein.

Referring to fig. 5, the track planning method provided in this embodiment specifically includes the following steps:

s210, obtaining initial track information obtained by track decision of the target vehicle.

S220, covering the two circular areas with preset radiuses on the body area of the target vehicle, and determining the movement track of the two circle centers.

Specifically, based on the initial track information (x _decision(t),y_decision(t),θ_decision (t)) and the correspondence between the center position coordinates and the center point coordinates of the rear wheel axle of the vehicle position, the motion tracks of the two centers can be determined and respectively recorded as: p _r = (xr (t), yr (t)) and P _f = (xf (t), yf (t)).

S230, determining the circle center positions of the two circle centers at each sampling time in the planning time domain according to the motion tracks of the two circle centers.

Specifically, for each circle center, the circle center position of the circle at each sampling time can be determined based on the motion track of the circle center. For example, based on the movement locus P _r (t) of the center P _r, it can be determined that the center position of the center P _r at the sampling time t _k is P _r(t_k.

S240, based on a preset radius, performing incremental expansion by taking the circle center position of each circle center as the center, and determining a local tunnel region corresponding to each circle center at each sampling time.

Specifically, the circle center position at each sampling time is taken as the center, the area range with the preset radius can be obtained, and the local tunnel area of each circle center at each sampling time can be determined by performing incremental expansion on the periphery of the area range. According to the method, the device and the system, the accurate local tunnel region can be obtained through incremental expansion of the positions of each circle center, so that the accuracy of determining collision avoidance constraint conditions is improved, and the accuracy of track planning is further improved.

Illustratively, S240 may include: taking the center position of the current center of a circle at the current sampling moment as the center, respectively expanding the length to be the distance of a preset radius along the positive and negative directions of the X axis and the Y axis, and constructing a quadrangle taking the center position as the center; sequentially expanding the four expanding edges of the quadrangle outwards for a preset distance to obtain an expanding area of each expansion; if no overlapping part exists between the expansion area and the obstacle area in the driving scene is detected, updating the quadrangle based on the expansion area, and continuing the expansion operation of the updated quadrangle; if the overlapping part of the expansion area and the obstacle area in the driving scene is detected, stopping the expansion operation of the expansion edge corresponding to the expansion area, and continuing the expansion operation of other expansion edges; and when the expansion operation of the four expansion edges is stopped, determining a local tunnel region corresponding to the current circle center at the current sampling time according to the current quadrangle.

Any sampling time can be used as the current sampling time, and any circle center can be used as the current circle center, so that the local tunnel region of each circle center at each sampling time can be determined by utilizing the determination mode of the local tunnel region.

Specifically, fig. 6 shows an example of a construction process of a local tunnel region. As shown in a) in fig. 6, a quadrangle, i.e., a rectangle, centered on the center position P _r(t_k) can be constructed by expanding the length to the distance of the preset radius R _i along the positive and negative directions of the X axis and the Y axis in the XOY coordinate system with the center position P _r(t_k) of the current center P _r at the current sampling time t _k as the center. As shown in b) of fig. 6, the preset distance Δstep may be continuously expanded outwards along the four expansion sides of the quadrangle according to the clockwise direction or the counterclockwise direction, respectively, to obtain an expansion area of each expansion, as indicated by the serial number in b). The order of the sequence numbers may be used to characterize the expansion order. After each expansion, it may be detected whether an overlap exists between the expansion area and the obstacle area in the driving scene, for example, the position of the moving obstacle in the driving scene at time t _k, the position of the stationary obstacle and the scattered point position of the road edge may be stored in the set V, so that it may be determined whether an overlap exists by detecting whether there is an element position contained in the expansion area in the set V. If not, the target vehicle is indicated not to collide with the obstacle when running in the expansion area, namely the expansion area is an effective area, and the expansion area can be merged into the quadrangle at the moment so as to update the quadrangle, and the expansion operation is continued on the updated quadrangle. If there is an overlapping portion between the expansion area and the obstacle area in the driving scene, it indicates that the target vehicle collides with the obstacle when driving in the expansion area, that is, the expansion area is an ineffective area, and at this time, there is no need to merge the expansion area, the expansion operation of the expansion edge corresponding to the expansion area is stopped, and the expansion operation of other expansion edges is continued. If the expansion operation of the four expansion edges is detected to stop, the current quadrangle obtained at the current time is indicated to be the movable maximum area of the current circle center P _r, as shown in the figure c). In order to ensure that the target vehicle does not collide with the obstacle, the current quadrilateral area corresponding to the current circle center can be reduced so as to obtain the local tunnel area corresponding to the current circle center at the current sampling time.

Illustratively, determining, according to the current quadrangle, a local tunnel region corresponding to the current center of a circle at the current sampling time may include: and (3) shrinking the four sides of the current quadrangle towards the center to obtain the distance with the preset radius, and determining the area of the shrunk quadrangle as the local tunnel area corresponding to the current circle center at the current sampling time. As shown in d) of fig. 6, a smaller quadrilateral is obtained by shrinking the four sides of the current quadrilateral towards the center by a distance of a preset radius R _i, and at this time, the area of the shrunk quadrilateral can be determined as a local tunnel area corresponding to the current circle center at the current sampling time, so that the distance between each circle center and the obstacle can be ensured to be at least R _i, and the collision between the target vehicle and the obstacle is avoided.

S250, determining collision avoidance constraint conditions according to the local tunnel region.

S260, constructing a target track planning nonlinear proposition corresponding to a target vehicle, wherein the target track planning nonlinear proposition comprises: track cost function and travel constraint condition, travel constraint condition includes: collision avoidance constraints determined based on tunneled modeling.

And S270, solving a nonlinear proposition of the target track planning according to the initial track information, and determining a target planning track corresponding to the target vehicle.

According to the technical scheme, the local tunnel region can be accurately obtained by performing incremental expansion on the position of each circle center at each sampling time, so that the accuracy of determining collision avoidance constraint conditions can be improved, and the accuracy of track planning is further improved.

Example III

Fig. 7 is a schematic diagram of a track planning method according to a third embodiment of the present invention, where the "constructing a target track planning nonlinear proposition corresponding to a target vehicle" is optimized based on the foregoing embodiments, and the "solving the target track planning nonlinear proposition according to initial track information, and determining a target planning track corresponding to the target vehicle" is also optimized based on the foregoing embodiments. Wherein the explanation of the same or corresponding terms as those of the above embodiments is not repeated herein.

Referring to fig. 7, the track planning method provided in this embodiment specifically includes the following steps:

s310, obtaining initial track information obtained by track decision of the target vehicle.

S320, constructing a first track planning nonlinear proposition corresponding to the target vehicle, wherein the first track planning nonlinear proposition comprises: the method comprises the steps of determining an objective function and a boundary constraint condition, wherein the objective function is determined based on a track cost function, a kinematic constraint condition of a target vehicle and a circle center association relationship of two circle centers corresponding to a collision avoidance constraint condition determined based on a tunneling modeling mode.

The boundary constraint condition may be a condition that is limited by a boundary form. For example, the boundary constraints may include collision avoidance constraints, edge constraints, and vehicle interior mechanical constraints determined based on tunneled modeling. The objective function may refer to an optimization objective of the first trajectory planning nonlinear proposition P _NLP1.

Specifically, since the two centers P _r and P _f in the target trajectory planning nonlinear proposition P _NLP0 form a nonlinear relationship with the optimization variables x _i、y_i and θ _i (see formula (5)), the collision avoidance constraint condition (see formula (6)) is a non-convex constraint. It can be seen that the non-convex nonlinear constraint condition in the target trajectory planning nonlinear proposition P _NLP0 may include the kinematic constraint condition of the target vehicle (see formula (1)) and the center association relationship of the two centers (see formula (5)), resulting in lower solution efficiency of the target trajectory planning nonlinear proposition P _NLP0. For this, xr (t), yr (t), xf (t) and yf (t) may also be optimized as optimization variables, i.e. the optimization variables of the objective function in the constructed first trajectory planning nonlinear proposition P _NLP1 include: xr (t), yr (t), xf (t), yf (t), x _i、y_i, and θ _i, such that the constraints in the first trajectory planning nonlinear proposition P _NLP1 are all linear boundary constraints.

Illustratively, determining the objective function based on the track cost function, the kinematic constraint condition of the objective vehicle, and the circle center association relationship of two circle centers corresponding to the collision avoidance constraint condition determined based on the tunnelling modeling manner may include: performing polynomial representation on the relationship between the centers of circles corresponding to the kinematic constraint condition of the target vehicle and the collision avoidance constraint condition determined based on the tunneling modeling mode, and determining each punishment item; and determining an objective function according to each punishment item and the track cost function.

For example, the kinematic constraint condition (see formula (1)) of the target vehicle and the circle center association relationship (see formula (5)) of the two circle centers may be modified into penalty polynomials, so as to obtain corresponding penalty terms, and the track cost function and the penalty terms may be added to obtain the target function. For example, the objective function may be expressed as follows:

illustratively, the first trajectory planning nonlinear proposition P _NLP1 can be expressed in its entirety as:

minimization: objective function (7)

S.t. edge constraint (2)

Vehicle interior mechanical constraint (3)

Collision avoidance restraint (6)

S330, solving the nonlinear proposition of the first track planning according to the initial track information, and determining the first planning track corresponding to the target vehicle.

Specifically, by solving the first trajectory planning nonlinear proposition P _NLP1 with the initial trajectory information as an initial solution, a first planned trajectory corresponding to the target vehicle can be obtained. The trajectory cost function (4) is temporarily ignored in P _NLP1, and the focus is on obtaining a first planned trajectory that is more kinematically compliant, while ensuring that no collision occurs. Since the first trajectory planning nonlinear proposition P _NLP1 constraint conditions are all simple boundary constraint conditions, P _NLP1 must have a solution, so that the solution speed of solving P _NLP1 by IPM is higher than that of solving P _NLP0.

Note that, the present embodiment is not limited to the execution sequence of S330, and step S330 may be executed after step S320 or after step S340.

S340, constructing a second track planning nonlinear proposition corresponding to the target vehicle, wherein the second track planning nonlinear proposition comprises: trajectory cost function and travel constraints.

Specifically, the second trajectory planning nonlinear proposition P _NLP2 is consistent with the optimization objective of the target trajectory planning nonlinear proposition P _NLP0, and both are trajectory cost functions. The driving constraint condition may include a collision avoidance constraint condition determined based on a tunneled modeling manner, and may further include: kinematic constraints of the target vehicle, boundary value constraints, and vehicle interior mechanical constraints.

Illustratively, the second trajectory planning nonlinear proposition P _NLP2 can be expressed in its entirety as:

minimization: track cost function (4)

S.t. kinematic constraints (1)

Side value constraint (2)

Vehicle interior mechanical constraint (3)

Center association (5)

Collision avoidance restraint (6)

For example, based on the tunneling modeling manner provided in the above embodiments, the collision avoidance constraint condition (6) in the second trajectory planning nonlinear proposition P _NLP2 may be redetermined according to the trajectory information of the first planned trajectory and the center association relationship (see formula (5)) of the two centers of circles, so as to further improve the accuracy of the path planning.

And S350, solving a second track planning nonlinear proposition according to the first planning track, and determining a target planning track corresponding to the target vehicle.

Specifically, by solving the second trajectory planning nonlinear proposition P _NLP2 by taking the first trajectory information as an initial solution, a target planning trajectory corresponding to the target vehicle can be obtained. On the premise of ensuring the kinematic feasibility in P _NLP2, the method is focused on minimizing the track cost function (5), so that the target planning track can be solved more quickly. The target track planning nonlinear proposition has three tasks which are required to be completed simultaneously, namely rigid vehicle kinematics constraint, rigid collision avoidance constraint and track cost function optimization, so that the solving difficulty of the target track planning nonlinear proposition is high. By disassembling the target track planning nonlinear proposition into a first track planning nonlinear proposition and a second track planning nonlinear proposition, the solving difficulty can be reduced, and the track planning efficiency is further improved.

According to the technical scheme, the first track planning nonlinear proposition and the second track planning nonlinear proposition are solved step by step, so that the solving difficulty of the track planning task can be reduced, and the track planning efficiency is further improved.

The following is an embodiment of a track planning apparatus according to an embodiment of the present invention, which belongs to the same inventive concept as the track planning method of the above embodiments, and reference may be made to the embodiments of the track planning method for details that are not described in detail in the embodiments of the track planning apparatus.

Example IV

Fig. 8 is a schematic structural diagram of a trajectory planning device according to a fourth embodiment of the present invention, where the embodiment is applicable to a case of performing trajectory planning on an autonomous vehicle, and in particular, a case of performing trajectory planning on an autonomous vehicle on a structured road. As shown in fig. 8, the apparatus specifically includes: an initial trajectory information acquisition module 410, a trajectory planning nonlinear proposition construction module 420, and a target planning trajectory determination module 430.

The initial track information obtaining module 410 is configured to obtain initial track information obtained by performing a track decision on a target vehicle; the track planning nonlinear proposition construction module 420 is configured to construct a target track planning nonlinear proposition corresponding to a target vehicle, where the target track planning nonlinear proposition includes: track cost function and travel constraint condition, travel constraint condition includes: collision avoidance constraint conditions determined based on a tunneling modeling mode; the target planning track determining module 430 is configured to solve the target track planning nonlinear proposition according to the initial track information, and determine a target planning track corresponding to the target vehicle.

Optionally, the apparatus further comprises: the collision avoidance constraint condition determination module includes:

the motion trail determination submodule is used for covering two circular areas with preset radiuses on a body area of the target vehicle and determining motion trail of two circle centers;

the local tunnel region determining submodule is used for determining a local tunnel region corresponding to each circle center at each sampling time in the track planning time domain according to the motion track of the two circle centers and a preset radius;

and the collision avoidance constraint condition determination submodule is used for determining the collision avoidance constraint condition according to the local tunnel region.

Optionally, the local tunnel region determination submodule includes:

The circle center position determining unit is used for determining the circle center positions of the two circle centers at each sampling time in the planning time domain according to the motion tracks of the two circle centers;

The local tunnel region determining unit is used for performing incremental expansion by taking the circle center position of each circle center as the center based on the preset radius, and determining the local tunnel region corresponding to each circle center at each sampling time.

Optionally, the local tunnel region determining unit is specifically configured to:

Taking the center position of the current center of a circle at the current sampling moment as the center, respectively expanding the length to be the distance of a preset radius along the positive and negative directions of the X axis and the Y axis, and constructing a quadrangle taking the center position as the center; sequentially expanding the four expanding edges of the quadrangle outwards for a preset distance to obtain an expanding area of each expansion; if no overlapping part exists between the expansion area and the obstacle area in the driving scene is detected, updating the quadrangle based on the expansion area, and continuing the expansion operation of the updated quadrangle; if the overlapping part of the expansion area and the obstacle area in the driving scene is detected, stopping the expansion operation of the expansion edge corresponding to the expansion area, and continuing the expansion operation of other expansion edges; and when the expansion operation of the four expansion edges is stopped, determining a local tunnel region corresponding to the current circle center at the current sampling time according to the current quadrangle.

Optionally, the local tunnel region determining unit is further specifically configured to: and (3) shrinking the four sides of the current quadrangle towards the center to obtain the distance with the preset radius, and determining the area of the shrunk quadrangle as the local tunnel area corresponding to the current circle center at the current sampling time.

Optionally, the collision avoidance constraint determination submodule is specifically configured to:

Determining position coordinates of four regional vertexes of a local tunnel region in a Cartesian coordinate system; and determining a constraint range of the position coordinates of each circle center at each sampling time according to the position coordinates of the vertexes of the four areas, and obtaining collision avoidance constraint conditions.

Optionally, the driving constraint further includes: kinematic constraints of the target vehicle, boundary value constraints, and vehicle interior mechanical constraints.

Optionally, the track planning nonlinear proposition construction module 420 is specifically configured to: constructing a first track planning nonlinear proposition corresponding to a target vehicle, wherein the first track planning nonlinear proposition comprises: the target function is determined based on a track cost function, a kinematic constraint condition of a target vehicle and a circle center association relationship of two circle centers corresponding to a collision avoidance constraint condition determined based on a tunneling modeling mode; constructing a second track planning nonlinear proposition corresponding to the target vehicle, wherein the second track planning nonlinear proposition comprises: track cost function and running constraint conditions;

Accordingly, the objective planning track determining module 430 is specifically configured to: solving a first track planning nonlinear proposition according to the initial track information, and determining a first planning track corresponding to the target vehicle; and solving the nonlinear proposition of the second track planning according to the first planning track, and determining the target planning track corresponding to the target vehicle.

Optionally, the apparatus further includes an objective function determining module configured to: performing polynomial representation on the relationship between the centers of circles corresponding to the kinematic constraint condition of the target vehicle and the collision avoidance constraint condition determined based on the tunneling modeling mode, and determining each punishment item; and determining an objective function according to each punishment item and the track cost function.

The track planning device provided by the embodiment of the invention can execute the track planning method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the track planning method.

It should be noted that, in the embodiment of the track planning apparatus, each unit and module included are only divided according to the functional logic, but not limited to the above-mentioned division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.

Example five

Fig. 9 is a schematic structural diagram of a device according to a fifth embodiment of the present invention. Fig. 9 shows a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 9 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.

As shown in fig. 9, device 12 is in the form of a general purpose computing device. Components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 9, commonly referred to as a "hard disk drive"). Although not shown in fig. 9, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.

Device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with device 12, and/or any devices (e.g., network card, modem, etc.) that enable device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Also, device 12 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, via network adapter 20. As shown, network adapter 20 communicates with other modules of device 12 over bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing a track planning method step provided by the present embodiment, the method comprising:

Constructing a target track planning nonlinear proposition corresponding to a target vehicle, wherein the target track planning nonlinear proposition comprises: track cost function and travel constraint condition, travel constraint condition includes: collision avoidance constraint conditions determined based on a tunneling modeling mode;

Of course, those skilled in the art will understand that the processor may also implement the technical solution of the track planning method provided in any embodiment of the present invention.

Example five

The present embodiment provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a trajectory planning method according to any of the embodiments of the present invention, the method comprising:

The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: 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 this document, 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.

The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. 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: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

It will be appreciated by those of ordinary skill in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device, or distributed over a network of computing devices, or they may alternatively be implemented in program code executable by a computer device, such that they are stored in a memory device and executed by the computing device, or they may be separately fabricated as individual integrated circuit modules, or multiple modules or steps within them may be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims

1. A method of trajectory planning, comprising:

Constructing a target track planning nonlinear proposition corresponding to the target vehicle, wherein the target track planning nonlinear proposition comprises: the track cost function and the running constraint condition are determined based on the fact that the track is as smooth as possible and is close to the decision track as possible; the travel constraint condition includes: collision avoidance constraint conditions determined based on a tunneling modeling mode; the tunneling modeling mode is a mode of separating an actual travelable area of a target vehicle from obstacles in the environment based on the initial track information and paving a local tunnel on a time space;

2. The method of claim 1, wherein determining collision avoidance constraints based on tunneled modeling includes:

Covering two circular areas with preset radiuses on the body area of the target vehicle, and determining the movement track of two circle centers;

Determining a local tunnel region corresponding to each circle center at each sampling time in a track planning time domain according to the motion tracks of the two circle centers and the preset radius;

and determining collision avoidance constraint conditions according to the local tunnel region.

3. The method according to claim 2, wherein determining the local tunnel region corresponding to each circle center at each sampling time in the track planning time domain according to the motion track of two circle centers and the preset radius comprises:

determining the circle center positions of the two circle centers at each sampling time in the planning time domain according to the motion tracks of the two circle centers;

based on the preset radius, performing incremental expansion by taking the circle center position of each circle center as the center, and determining a local tunnel region corresponding to each circle center at each sampling time.

4. The method of claim 3, wherein the determining the local tunnel region corresponding to each center of each sampling time based on the preset radius by performing incremental expansion centering on the center position of each center of the circle comprises:

taking the center position of the current center of a circle at the current sampling moment as the center, respectively expanding the distances with the lengths of a preset radius along the positive and negative directions of an X axis and a Y axis, and constructing a quadrangle taking the center position as the center;

sequentially expanding the four expansion edges of the quadrangle outwards for a preset distance to obtain an expansion area expanded each time;

If no overlapping part exists between the expansion area and the obstacle area in the driving scene, updating the quadrangle based on the expansion area, and continuing the expansion operation of the updated quadrangle;

If the overlapping part of the expansion area and the obstacle area in the driving scene is detected, stopping the expansion operation of the expansion edge corresponding to the expansion area, and continuing the expansion operation of other expansion edges;

And when the expansion operation of the four expansion edges is stopped, the length of the four edges of the current quadrangle shrinking towards the center is a distance with a preset radius, and the area of the contracted quadrangle is determined to be a local tunnel area corresponding to the current circle center at the current sampling time.

5. The method of claim 2, wherein determining collision avoidance constraints from the local tunnel region comprises:

Determining position coordinates of four area vertices of the local tunnel area in a Cartesian coordinate system;

And determining the constraint range of the position coordinates of each circle center at each sampling time according to the position coordinates of the vertexes of the four areas, and obtaining collision avoidance constraint conditions.

6. The method of claim 1, wherein the travel constraints further comprise: kinematic constraints of the target vehicle, boundary value constraints, and vehicle interior mechanical constraints.

7. The method of any one of claims 1-6, wherein constructing a target trajectory planning nonlinear proposition corresponding to the target vehicle comprises:

Constructing a first track planning nonlinear proposition corresponding to the target vehicle, wherein the first track planning nonlinear proposition comprises: the method comprises the steps of determining an objective function and a boundary constraint condition, wherein the objective function is determined based on a track cost function, a kinematic constraint condition of a target vehicle and a circle center association relationship of two circle centers corresponding to a collision avoidance constraint condition determined based on a tunneling modeling mode; the circle center association relation of the two circle centers is the corresponding relation between the position coordinates of the circle centers and the midpoint coordinates of the rear wheel axle of the vehicle position; the objective function is an optimization target of the first trajectory planning nonlinear proposition; the boundary constraint conditions comprise collision avoidance constraint conditions, boundary constraint conditions and vehicle internal mechanical constraint conditions which are determined based on a tunneling modeling mode;

Constructing a second track planning nonlinear proposition corresponding to the target vehicle, wherein the second track planning nonlinear proposition comprises: track cost function and running constraint conditions; the second track planning nonlinear proposition is consistent with the optimization target of the target track planning nonlinear proposition, and is a track cost function; the driving constraint conditions comprise a collision avoidance constraint condition, a target vehicle kinematics constraint condition, a boundary value constraint condition and a vehicle internal mechanical constraint condition which are determined based on a tunneling modeling mode;

the first track planning nonlinear proposition and the second track planning nonlinear proposition are obtained by disassembling a target track planning nonlinear proposition;

correspondingly, according to the initial track information, solving the nonlinear proposition of the target track planning, and determining the target planning track corresponding to the target vehicle, wherein the method comprises the following steps:

Solving the first track planning nonlinear proposition according to the initial track information, and determining a first planning track corresponding to the target vehicle;

And solving the second track planning nonlinear proposition according to the first planning track, and determining a target planning track corresponding to the target vehicle.

8. The method of claim 7, wherein determining the objective function based on a center association of two centers corresponding to the trajectory cost function, the kinematic constraint of the objective vehicle, and the collision avoidance constraint determined based on the tunneling modeling, comprises:

performing polynomial representation on the relationship between the centers of circles corresponding to the kinematic constraint condition of the target vehicle and the collision avoidance constraint condition determined based on the tunneling modeling mode, and determining each punishment item;

and determining an objective function according to each punishment item and the track cost function.

9. A trajectory planning device, comprising:

The track planning nonlinear proposition construction module is used for constructing a target track planning nonlinear proposition corresponding to the target vehicle, wherein the target track planning nonlinear proposition comprises: the track cost function and the running constraint condition are determined based on the fact that the track is as smooth as possible and is close to the decision track as possible; the travel constraint condition includes: collision avoidance constraint conditions determined based on a tunneling modeling mode; the tunneling modeling mode is a mode of separating an actual travelable area of a target vehicle from obstacles in the environment based on the initial track information and paving a local tunnel on a time space;

10. An apparatus, the apparatus comprising:

one or more processors;

a memory 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 trajectory planning method of any one of claims 1-8.

11. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements a trajectory planning method as claimed in any one of claims 1-8.