CN116224997A

CN116224997A - Track planning method and device, electronic equipment and storage medium

Info

Publication number: CN116224997A
Application number: CN202211728647.7A
Authority: CN
Inventors: 王泰翔; 邹汉鹏; 吕强
Original assignee: Neolix Technologies Co Ltd
Current assignee: Neolix Technologies Co Ltd
Priority date: 2022-12-30
Filing date: 2022-12-30
Publication date: 2023-06-06

Abstract

The application discloses a track planning method and device, electronic equipment and a storage medium, wherein the method comprises the steps of acquiring scene information of a target vehicle to generate a space-time corridor, wherein the space-time corridor comprises a plurality of steps corresponding to a plurality of time slices in an S-L-T three-dimensional space, and the steps are the drivable range of the target vehicle in the corresponding time slices; constructing a track cost function based on a state quantity and a control quantity of a target vehicle, wherein the state quantity comprises a position, a speed and an acceleration, and the control quantity comprises a degree of impact; under the constraint of the space-time corridor, a running track of the target vehicle in a plurality of steps is planned based on a track cost function, the running track comprises a plurality of spline curve segments respectively corresponding to the steps, and the constraint of the space-time corridor comprises an equality constraint on the state quantity of the target vehicle and an inequality constraint on the state quantity and the control quantity of the target vehicle. Therefore, the automatic planning of the vehicle running track in the automatic driving process can be realized, and the availability of the automatic driving function of the vehicle is ensured.

Description

Track planning method and device, electronic equipment and storage medium

Technical Field

The application belongs to the technical field of automatic driving, and particularly relates to a track planning method and device, electronic equipment and a storage medium.

Background

In recent years, automatic driving technology is rapidly developed, and the aim is to control a vehicle to automatically travel along a road, ensure the safety of the vehicle while reaching a destination as soon as possible, and also ensure that the safety of other traffic participants is not threatened directly or indirectly.

To achieve the above objective, the autopilot software requires a plurality of critical systems, one of which is the trajectory planning system. The track planning aims at planning a track meeting the dynamic requirements of vehicles, the track needs to be capable of avoiding surrounding obstacles (vehicles, pedestrians, static obstacles and the like), and meeting decision-making layer instructions (lane keeping, lane changing and side parking), and stable and reliable track planning is one of the bases for guaranteeing the usability of automatic driving functions.

The information disclosed in this background section is only for enhancement of understanding of the general background of the application and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person of ordinary skill in the art.

Disclosure of Invention

The present application is directed to a trajectory planning method for solving the problem of how to implement automatic driving trajectory planning.

To achieve the above object, the present application provides a trajectory planning method, including:

acquiring scene information of a target vehicle to generate an spatio-temporal corridor, wherein the spatio-temporal corridor comprises a plurality of steps corresponding to a plurality of time slices in an S-L-T three-dimensional space, and the steps are the drivable range of the target vehicle in the corresponding time slices;

constructing a track cost function based on a state quantity and a control quantity of the target vehicle, wherein the state quantity comprises at least one of position, speed and acceleration, and the control quantity comprises a degree of impact;

and planning a running track of the target vehicle in a plurality of steps based on the track cost function under the constraint of the space-time corridor, wherein the running track comprises a plurality of spline curve segments respectively corresponding to the steps, and the constraint of the space-time corridor comprises an equality constraint on a state quantity of the target vehicle and an inequality constraint on the state quantity and a control quantity of the target vehicle.

In one embodiment, constructing the track cost function based on the state quantity and the control quantity of the target vehicle specifically includes:

constructing a state cost sub-function based on the state quantity of the target vehicle, wherein the state cost sub-function comprises a state component weight, and the state component weight corresponds to the position, the speed and the acceleration;

Constructing a control cost sub-function based on the control quantity of the target vehicle, wherein the control cost sub-function comprises a control component weight, and the control component weight corresponds to the impact degree;

and constructing a track cost function based on the state cost sub-function and the control cost sub-function.

In one embodiment, the method further comprises:

based on the continuity of spline curve segment state quantity in each step adjacent to the space-time corridor, constructing an equality constraint on the state quantity of the target vehicle;

and/or the spline curve is segmented into cubic spline curves.

In one embodiment, the inequality constraints on the target vehicle state quantity and the control quantity include joint constraints;

the method further comprises the steps of:

constructing initial joint constraint on the state quantity and the control quantity of the target vehicle based on the space-time corridor and the Bezier curve, wherein the initial joint constraint is constraint on a Bezier curve control point;

determining coefficient mapping of a spline curve and a Bezier curve;

based on the initial joint constraint and the coefficient map, a joint constraint on the target vehicle state quantity and the control quantity is constructed.

In one embodiment, the method specifically includes:

projecting the space-time corridor to an S-T plane and/or an L-T plane, wherein the S-T plane is a plane with a correlation between a travelable longitudinal track and time, and the L-T plane is a plane with a correlation between a travelable transverse track and time;

Determining the intersection boundary of adjacent steps in the space-time corridor on the S-T plane and/or the L-T plane;

and constraining a starting control point and/or a terminating control point of the Bezier curve in the corresponding step by the handover boundary.

In one embodiment, the method further comprises:

constructing an initial constraint on a control quantity of a target vehicle based on the space-time corridor and the Bezier curve, wherein the initial constraint is an inequality constraint on a Bezier curve control point;

determining coefficient mapping of a spline curve and a Bezier curve;

and constructing a constraint on the control quantity of the target vehicle based on the initial constraint and the coefficient mapping.

In one embodiment, under the constraint of the space-time corridor, the track cost function is used for planning the running track of the target vehicle in a plurality of steps, and the method specifically comprises the following steps:

under the constraint of the space-time corridor, calculating a longitudinal track and a transverse track associated with time of the target vehicle based on the track cost function;

and combining the longitudinal track and the transverse track to obtain the running track of the target vehicle.

The application also provides a track planning device, comprising:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring scene information of a target vehicle to generate a space-time corridor, the space-time corridor comprises a plurality of steps corresponding to a plurality of time slices in an S-L-T three-dimensional space, and the steps are the drivable range of the target vehicle in the corresponding time slices;

A building module for building a track cost function based on a state quantity and a control quantity of the target vehicle, wherein the state quantity comprises at least one of position, speed and acceleration, and the control quantity comprises a degree of impact;

and the planning module is used for planning the running track of the target vehicle in a plurality of steps based on the track cost function under the constraint of the space-time corridor, wherein the running track comprises a plurality of spline curve segments respectively corresponding to the steps, and the constraint of the space-time corridor comprises the equality constraint on the state quantity of the target vehicle and the inequality constraint on the state quantity and the control quantity of the target vehicle.

The application also provides an electronic device comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the trajectory planning method as described above.

The present application also provides a machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform a trajectory planning method as described above.

Compared with the prior art, according to the track planning method, the space-time corridor can be generated based on the scene information of the target vehicle, and the space-time corridor is utilized to construct the equality constraint on the state quantity of the target vehicle and the inequality constraint on the state quantity and the control quantity of the target vehicle, so that the track planning of the target vehicle can be converted into the optimal control problem to solve in combination with the construction of the track cost function based on the state quantity and the control quantity of the target vehicle, and the availability of the automatic driving function of the vehicle is guaranteed.

In another aspect, by utilizing the differential flatness of the cubic spline curve, the running track in each step of the space-time corridor can be directly planned by the cubic spline curve, so that the constraint conditions required by optimal control solution are reduced while the running track is smooth, and the vehicle track planning efficiency is improved.

In another aspect, the spline curve and the Bezier curve used as the track planning are subjected to coefficient mapping by utilizing the properties of the Bezier curve such as convex hull property, endpoint property and derivative still, so that the space-time corridor can apply hard constraint on the running track in each step in the space-time corridor from multiple aspects such as position, speed, acceleration, impact degree and the like, and the planned running track is ensured to strictly meet constraint expectations.

Drawings

FIG. 1 is an application scenario diagram of a trajectory planning method according to an embodiment of the present application;

FIG. 2 is a flow chart of a trajectory planning method according to an embodiment of the present application;

FIG. 3 is a scene graph of an S-L-T three-dimensional space in a trajectory planning method according to an embodiment of the present application;

FIG. 4 is a schematic diagram of space-time corridors generated in S-L-T three-dimensional space in a trajectory planning method according to an embodiment of the present application;

FIG. 5 is a schematic diagram of space-time corridor projection onto an S-L plane in a trajectory planning method according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a trajectory planning method using space-time corridors to constrain a travel trajectory and projecting the trajectory onto an S-T plane according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a trajectory planning method using space-time corridors to constrain a travel trajectory and projecting the trajectory onto an L-T plane according to an embodiment of the present application;

FIG. 8 is a trajectory of a target vehicle in an space-time corridor step in S-L-T three-dimensional space according to a trajectory planning method in accordance with an embodiment of the present application;

FIG. 9 is a block diagram of a trajectory planning device according to one embodiment of the present application;

fig. 10 is a hardware configuration diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The present application will be described in detail with reference to the embodiments shown in the drawings. The embodiments are not intended to be limiting and structural, methodological, or functional changes made by those of ordinary skill in the art in light of the embodiments are intended to be included within the scope of the present application.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims of this application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be capable of operation in sequences other than those illustrated or described herein, for example. Furthermore, the terms "comprises," "comprising," and "includes" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

Before introducing embodiments of the present application, basic techniques and some technical terms related to the embodiments of the present application are schematically explained:

automatic driving: the vehicle driving system has the advantages that under the condition that a test driver is not required to execute physical driving operation, the vehicle driving task can be guided and decided, and the test driver operation and control behavior is replaced, so that the vehicle can complete the function of safe driving. Autopilot technology typically includes high-precision mapping, environmental awareness, behavioral decision-making, path planning, motion control, and the like.

An autopilot system: systems that implement different levels of autopilot functionality of the vehicle, such as a driver assistance system (L2), a high speed autopilot system (L3) that requires human supervision, and a high/full autopilot system (L4/L5).

The intelligent transportation system (Intelligent Traffic System, ITS), also called intelligent transportation system (Intelligent Transportation System), is a comprehensive transportation system which uses advanced scientific technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operation study, artificial intelligence, etc.) effectively and comprehensively for transportation, service control and vehicle manufacturing, and enhances the connection among vehicles, roads and users, thereby forming a comprehensive transportation system which ensures safety, improves efficiency, improves environment and saves energy.

The intelligent vehicle-road cooperative system (Intelligent Vehicle Infrastructure Cooperative Systems, IVICS), which is simply called vehicle-road cooperative system, is one development direction of the intelligent traffic system. The vehicle-road cooperative system adopts advanced wireless communication, new generation internet and other technologies, carries out vehicle-to-vehicle and vehicle-to-road dynamic real-time information interaction in all directions, and develops active safety control and road cooperative management on the basis of full-time empty dynamic traffic information acquisition and fusion, so that effective cooperation of people and vehicles and roads is fully realized, traffic safety is ensured, traffic efficiency is improved, and the formed safe, efficient and environment-friendly road traffic system is formed.

Track planning: by given constraints of initial state (including starting position, speed and acceleration), target state (including target position, speed and acceleration), obstacle position, dynamics and comfort, a smooth track is calculated, so that the vehicle can reach the target state along the track. Trajectory planning generally includes two parts, path planning and speed planning: the path planning is responsible for calculating a smooth path from the starting position to the target position, and the speed planning calculates the speed of each path point on the basis of the path, thereby forming a speed curve.

Flena (Frenet) coordinate system: the road coordinate system is also called, and the coordinates are expressed as (S, L) by taking the starting position of the vehicle as the origin and mutually perpendicular, and are divided into an S-axis direction (i.e., tangential direction along the road reference line, referred to as transverse direction) and an L-axis direction (i.e., current normal direction of the reference line, referred to as longitudinal direction).

The track planning method provided by the embodiment of the application can be applied to an automatic driving automobile and comprises an automatic driving system of L2, L3, L4 and above levels.

Referring to fig. 1, an application scenario of the track planning method provided in the embodiment of the present application is taken as an example. The user can drive the vehicle manually or automatically by means of the intelligent driving system of the vehicle. In the manual driving or automatic driving process, the terminal can collect scene information based on sensors, laser radars, cameras, millimeter wave radars, navigation systems, positioning systems, high-precision maps and the like and provide some decision basis information for vehicle control. The terminal may be a vehicle driven by a user, or an intelligent vehicle-mounted device/module on the vehicle, or a desktop computer, a notebook computer, a smart phone, a tablet computer, a portable wearable device carried by the user, etc. configured on the vehicle during driving of the vehicle.

Referring to fig. 2, an embodiment of the trajectory planning method of the present application is described. In this embodiment, the method includes:

s11, acquiring scene information of the target vehicle to generate a space-time corridor.

In automatic driving of a vehicle, the scene information may include positioning information, map information, environment information, end point information, vehicle-related information, and the like. The vehicle-related information may be information related to the target vehicle and a vehicle adjacent thereto, that is, the vehicle-related information may include a speed, an acceleration of the target vehicle, a speed, an acceleration of a vehicle adjacent to the target vehicle, and the vehicle-related information may further include a positional relationship between the target vehicle and a vehicle adjacent thereto.

The different types of scene information can be respectively obtained through one or more vehicle-mounted devices. For example, the coordinates of the target vehicle in the lane coordinate system may be obtained by a global satellite positioning system (global navigation satellite system, GNSS); the relative speed, relative distance, etc. of the target vehicle and the preceding vehicle may be obtained by means of an ultrasonic radar, a camera, or an ultrasonic radar fused camera.

The definition of the space-time corridor may depend on a configured S-L-T three-dimensional space, where S and L may refer to the above-mentioned flener coordinate system, referred to as the lateral direction and the longitudinal direction, respectively; t represents the time direction.

Referring to fig. 3, based on the above-obtained scene information, a static obstacle and a dynamic obstacle in the surrounding environment of the target vehicle are shown in a schematic scene, wherein x and y axes represent a lateral direction S and a longitudinal direction L, respectively. The static obstacle is represented as a space body extending upward along the T-axis direction in the S-L-T three-dimensional space since its position does not change with time. Dynamic obstacles (e.g., vehicles) are predicted to travel at a speed v in the x-axis direction for a future period of time, and therefore appear in the S-L-T three-dimensional space as a spatial volume extending in the T-axis direction while being stretched obliquely to the x-axis, and the projection slope thereof on the S-T plane is the speed v.

With reference to fig. 4, the above-mentioned combination of the space bodies corresponding to the static obstacle and the dynamic obstacle forms a space-time obstacle region of the target vehicle in the S-L-T three-dimensional space, and the space-time corridor corresponds to the space-time obstacle region, and provides the target vehicle with a drivable range in the S-L-T three-dimensional space by avoiding the space occupied by the space-time obstacle region. It can be seen that the space-time corridor can be regarded as a "solution set" of all travelable trajectories of the target vehicle in the S-L-T three-dimensional space.

With reference to fig. 5, the projection of the temporal corridor onto the S-L plane can be regarded as a "top view" of the temporal corridor in the S-L-T three-dimensional space, wherein each step occupies a corresponding time slice. It will be appreciated that the overlapping of projections on the S-L plane does not represent overlapping of steps in the S-L-T three-dimensional space, and in fact, the respective steps are stacked consecutively on the time axis T in the S-L-T three-dimensional space.

Similarly, referring to fig. 6 and 7, the s-T plane and the L-T plane are planes with time axes reserved, respectively, a plane with time-associated longitudinal trajectories and a plane with time-associated lateral trajectories. Adjacent steps in the space-time corridor meet at projected boundaries of the S-T plane and the L-T plane.

The optimal generation of the space-time corridor may rely on an optimal solution of the motion planning layer of the autonomous vehicle, typical generation processes including seed generation, cube expansion and constraint correlation, and cube relaxation.

Specifically:

(1) seed generation: seeds for the space-time corridor are generated by projecting the forward simulation state of the behavior planner into the S-L-T three-dimensional space. Since the forward simulation state is discretized, the feasibility of the spatio-temporal corridor generation process depends on the complexity of the environment and the seed resolution. To ensure the success of the spatio-temporal corridor generation process, the initial cube constructed from successive seeds may be required to be collision-free. The motivation for creating space-time corridors around seeds is to model the topologically equivalent free space entirely while retaining the same high-level behavior. Here, the expansion seeds may be obtained by sampling in the S-T and L-T topological spaces (planes), respectively.

(2) Cube expansion with semantic boundaries: the spatio-temporal corridors are generated by iterating the seeds, which are already contained in the last expanded cube, are skipped, since they are topologically equivalent. The initial cube is generated based on two consecutive seeds, which are considered as two cube vertices. The key feature of the cube expansion is to consider the semantic boundary, and the goal of the cube expansion process is to generate cubes that match the semantic boundary so that constraints can be easily correlated.

In particular, when the initial cube intersects a certain semantic boundary, the expansion direction opposite to the inlet direction is disabled, so that the expanded cube can almost match the semantic boundary. For one expansion step, the expansion alternates between the S-L-T directions, and if the step collides with an obstacle or intersects a certain semantic boundary, the expansion is terminated.

(3) Cube relaxation: through the cube expansion process, the expanded cubes nearly match the semantic boundaries. However some constraints, such as lane change duration constraints are soft constraints, and additional space should be left for optimization. To this end, a cube relaxation process may be employed to relax cube boundaries, the maximum margin allowed for relaxation being systematically determined by constraints applied to two consecutive cubes. For example, in the machine direction, the margin may be determined by a speed matching distance according to a speed constraint. For the lateral (i.e. lane change case) the margin can be calculated by the allowed fluctuation of the lane change duration.

Referring to fig. 4, the space-time corridor generated according to the method may include a plurality of steps (i.e. cubes) corresponding to a plurality of time slices, each step representing the driving range of the target vehicle in the corresponding time slice, and each step occupying a time t _k 。

S12, constructing a track cost function based on the state quantity and the control quantity of the target vehicle.

In various embodiments of the present application, it is desirable to utilize spline curves to plan the travel trajectories of the various steps in the space-time corridor. The spline curve may be a common cubic spline curve, a cubic spline curve, or the like. In particular, in the present embodiment, it is desirable to plan the travel locus of each step in the space-time corridor using a cubic spline curve, and correspondingly, the travel locus in each step of the space-time corridor may be referred to as "spline curve segment".

Taking the S-T plane as an example, the cubic spline curve segment in one step of the space-time corridor can be expressed as:

wherein, the definition domain of the cubic spline curve segment is from t _i To t _i+1 I.e. length h in T direction across a step in the space-time corridor, it is known that h=t _i+1 -t _i (i.e., Δt), j represents the sequence number of the step in the space-time corridor.

Set χ (t) =f _j (t)，χ _i And χ (x) _i+1 And the ordinate (coordinate value of the transverse direction in the S-T plane and coordinate value of the longitudinal direction in the L-T plane) respectively representing the starting position and the ending position of the cubic spline curve segment in the corresponding step. The method can obtain the following steps:

Wherein, the liquid crystal display device comprises a liquid crystal display device,

respectively represent χ _i At t _i First, second, third derivatives at (i.e.)>

Respectively corresponding to the target vehicles at t _i Speed, acceleration, jerk at the location.

Similarly, it is also possible to obtain:

/>

respectively represent χ _i+1 At t _i+1 First, second, third derivatives at (i.e.,

respectively corresponding to the target vehicles at t _i+1 Speed, acceleration, jerk at the location.

In various embodiments of the present application, the state quantity may include at least one of a position, a speed, and an acceleration of the target vehicle, and the control quantity may include an impact degree of the target vehicle. Here, the trajectory planning method of the present embodiment will be described taking as an example the construction of a trajectory cost function by simultaneously using the position, the velocity, and the acceleration in the state quantity, and the degree of impact in the control quantity.

Specifically, the state quantity is set

Control amount->

The method can obtain the following steps:

writing formula (4) in a matrix form in combination of formula (2) and formula (3) can give:

after obtaining the relation model of spline curve segment in one step corresponding to the space-time corridor and related to the formula (5), the current state quantity of the target vehicle

In the known case, the entire space-time corridor is set up:

and->

Respectively, the whole time and space The state quantity and the control quantity of the target vehicle in the corridor range.

Then, a state cost sub-function may be constructed based on the state quantity of the target vehicle, and a control cost sub-function may be constructed based on the control quantity of the target vehicle, respectively.

The state quantity includes a position, a velocity, an acceleration, etc. referred to as a "state component", the state cost sub-function may include a state component weight corresponding to the position, the velocity, and the acceleration. The state cost sub-function may be expressed as:

represents->

And Q represents the state component weights. It will be appreciated that the state component weights are in matrix form and the weights of the corresponding state components in the control cost sub-functions may be adjusted separately.

Similarly, the degree of impact included in the control amount is referred to as a "control component", and the control cost sub-function includes a control component weight corresponding to the degree of impact. The control cost sub-function may be expressed as:

represents->

R represents the control component weights. It will be appreciated that the control component weights are in matrix form and mayThe weights of the control components in the control cost subfunction are adjusted. / >

And finally, constructing a track cost function based on the state cost sub-function and the control cost sub-function. The trajectory cost function may be determined by direct or weighted summation of the state cost sub-function and the control cost sub-function, for example. In one embodiment, considering the objective with minimum acceleration and jerk in the planned driving trajectory, the trajectory cost function may be expressed as:

wherein w is ₁ And w ₂ The weights of the corresponding state cost subfunction and the control cost subfunction are respectively. It will be appreciated that w in the trajectory cost function of equation (9) ₁ And/or w ₂ May also be omitted.

S13, under the constraint of the space-time corridor, planning the running track of the target vehicle in a plurality of steps based on the track cost function.

In the present embodiment, the constraints of the space-time corridor include an equality constraint on the target vehicle state quantity, and an inequality constraint on the target vehicle state quantity and the control quantity.

(1) Equation constraint

In this embodiment, the state quantity at the spline curve segment connection point in each step adjacent to the space-time corridor is expected to be the same, so as to ensure smoothness and comfort of the planned running track. That is, it is desirable that the spline curve segment state quantity in each step adjacent to the space-time corridor has continuity.

In combination with the above equation (4), the relationship between the starting position and the ending position of the spline section in each step of the space-time corridor has been given. Whereas for two adjacent steps the ending position of the spline segment in the preceding step corresponds to the starting position of the spline segment in the following step. Therefore, the continuity of the spline curve segment state quantity in each step as above can be defined by the form of the expression (4) itself.

(2) Inequality constraint

In this embodiment, the planned running track is a spline curve segment in the space-time corridor step, and due to the differential flat property of such polynomial curves, the curve with a fixed order can be directly determined by the states of two end points of the curve, and the curve coefficient cannot be constrained by using hard constraint, that is, the path point of the running track and its derivative (corresponding to the speed, acceleration, impact degree, etc.) cannot be explicitly constrained.

The bezier curve has convex hull properties, which refers to the smallest convex polygon that contains all the control points of the bezier curve. Either side of the convex polygon is elongated, the other side being on its side, the Bezier curve will always be in the smallest convex polygon that contains all control points. The bezier curve also has an end point, i.e. the bezier curve passes only the control points (start control point and end control point) of two end points, all other control points being only approximations, typically not. Furthermore, the derivative of the bezier curve is also a bezier curve.

Based on the above characteristics of the bezier curve, the application proposes that the constraint problem of the spline curve is expected to be converted into the constraint problem of the bezier curve by using the coefficient mapping of the spline curve and the bezier curve, so that the hard constraint is added to the passing points of the running track and the derivative thereof in each step of the time space corridor.

Specifically, an initial joint constraint on the state quantity and the control quantity of the target vehicle can be constructed based on the space-time corridor and the Bezier curve, and coefficient mapping of the spline curve and the Bezier curve is determined; and constructing the joint constraint on the state quantity and the control quantity of the target vehicle based on the initial joint constraint and the coefficient mapping.

The initial joint constraint is a constraint on the Bezier curve control points, where the control points correspond to the coefficients of the Bezier curve in a mathematical sense, so that the mutual transformation can be performed by mapping the coefficients of the spline curve and the Bezier curve. The mapping of the cubic spline curve and the third-order bezier curve will be specifically described below as an example.

First, the cubic spline f (t) and the third-order bezier curve B (t) in each step in the space-time corridor can be expressed in segments as:

where t is the range of each time slice, C is the control point of each Bezier curve segment, and b is the Bernstein base function.

In this embodiment, in order to correspond to the cubic spline curve segment, the bezier curve segment should be a third-order bezier curve, that is, each bezier curve segment in equation (10) has four control points C (i=0 to 3).

Writing a cubic spline f (t) of formula (10) and a bezier curve B (t) of formula (11) in the form of a matrix:

then, let:

/>

on this basis, assuming that the segments of the bezier curve and the spline curve are identical, there may be:

it can be seen that equation (14) can be understood as a coefficient map of spline curves and bezier curves.

On the basis of equation (14), the spline curve can be converted into the form of a Bezier curve control point, and the derivation process is as follows.

Writing formula (2) in the form of a matrix:

combining formula (14) and formula (15) can be obtained:

and (3) making:

in this case, since the lengths h (i.e., Δt) of the respective steps of the space-time corridor in the T direction may not be the same, the mapping relationship between the bezier curve segments and the spline curve segments in the respective steps may not be the same, and the segment attention mapping is required.

In this embodiment, since the bezier curve has a constraint relationship for all control points, and the (third-order) bezier curve includes the state quantity and the control quantity of the target vehicle mentioned in this embodiment, an initial joint constraint may be determined based on the derivative formula of the bezier curve.

The (k-th) derivative formula of the (n-th) bezier curve is expressed as:

also for convenience of representation, converting Δt in formula (11) to the form of h, can yield:

the element change is carried out by combining the formula (18) and the formula (19), so that the following steps are obtained:

from equation (20), the first order (k=1), second order (k=2) and third order (k=3) forms of the bezier curve can be determined, thereby making the position, speed, acceleration and jerk of the target vehicle travel trajectory at each control point constraint. Thus, the initial joint constraint on the target vehicle may be written as:

the spline curve and the Bezier curve defined in the application are two-dimensional curves of the travel track in the space-time corridor projected to the S-T plane and the L-T plane, so that when space-time corridor constraint is utilized, the space-time corridor projection is utilized to constrain the space-time corridor in the S-T plane and the L-T plane respectively. In the S-T plane, p _{j_min} 、v _min 、a _min 、j _min 、p _{j_max} 、v _max 、a _max 、j _max The constraints of each step of the space-time corridor on the minimum position, the minimum speed, the minimum acceleration, the minimum impact degree, the maximum position, the maximum speed, the maximum acceleration and the maximum impact degree of the target vehicle in the transverse direction are respectively set; similarly, in the L-T plane, p _{j_min} 、v _min 、a _max 、j _min 、p _{j_max} 、v _max 、a _max 、j _max The minimum position and minimum speed of each step of the space-time corridor to the longitudinal direction of the target vehicle Degree, minimum acceleration, minimum jerk, maximum position, maximum velocity, maximum acceleration, and maximum jerk.

In the above constraining the position of the target vehicle at the control point with the space-time corridor, the start control point and/or the end control point of the bezier curve segment in each step of the space-time corridor may be constrained as shown below.

With continued reference to fig. 6 and 7, the space-time corridor may be projected onto the S-T plane and/or the L-T plane, and a boundary between adjacent steps in the space-time corridor on the S-T plane and/or the L-T plane may be determined, and then the starting control point and/or the ending control point of the bezier curve segment in the corresponding step may be constrained by the boundary.

The constraints herein may be accomplished using the endpoints of the Bezier curve. Taking the S-T plane as an example, the ending control point position of the bezier curve segment in the first square is constrained to the interval of [0,100], and the starting control point position of the bezier curve segment in the second square is constrained to the interval of [50,150 ]. Obviously, the intersection of these two intervals (the intersection boundary) may jointly constrain the above-mentioned end control point and start control point, i.e. both lie on the intersection boundary.

Further, the formula (21) may be written as follows:

and->

The above minimum and maximum constraint amounts, phi, representing the initial joint constraints, respectively _j Representative and

a matrix of multiplied coefficients.

Further, the state quantity and the control quantity of the running track in each step of the space-time corridor can be written in the following matrix form:

substitution of formula (23) with formulas (16) and (17) can give:

further, H in formula (24) may be _M Moving the term to the right of the equation, writing to be a Bezier curve segment control point

Relation form between the state quantity and the control quantity of the running track:

finally, based on equations (25) and (22), the form of the hard constraint on the travel trajectory (i.e., spline curve) in the time-space corridor can be obtained as follows:

wherein b _{unequ_min} And (3) with

Correspondingly, b _{unequ_max} And->

Corresponding to the above.

On the basis of the above constructed combined constraint on the state quantity and the control quantity of the target vehicle, in this embodiment, the control quantity of the target vehicle may be further independently constrained to ensure the comfort level of the planned driving track of the target vehicle.

Similarly, an initial constraint on the target vehicle control amount may be constructed based on the space-time corridor and the Bezier curve, and the constraint on the target vehicle control amount may be constructed in combination with coefficient mapping of the spline curve and the Bezier curve. The initial constraint is also an inequality constraint on the Bezier curve control point, and the process of deriving the initial constraint into the constraint on the control amount of the target vehicle can refer to the derivation of the joint constraint, and will not be described herein.

The inequality constraint on the target vehicle control amount is as follows:

box _{unequ_min} ≤U≤box _{unequ_max} (27)

in this embodiment, the travel track of the target vehicle in the steps of the space-time corridor may be planned with the objective of minimizing the track cost function of the equation (9) under the equality constraint of the equation (4), the inequality constraint of the equation (26), and the inequality constraint of the equation (27).

In conjunction with FIG. 8, as described above, in various embodiments of the present application, it may be that space-time corridors are projected onto the S-T plane and the L-T plane to constrain the target vehicle travel trajectory (spline curve). Therefore, when the driving track is planned, the transverse track on the S-T plane and the longitudinal track on the L-T plane are obtained through solving, and then the longitudinal track and the transverse track can be combined to obtain the driving track of the target vehicle in the space-time corridor (S-L-T space).

Referring to fig. 9, an embodiment of the trajectory planning device of the present application is described. In this embodiment, the trajectory planning device includes an acquisition module 21, a construction module 22, and a planning module 23.

The acquisition module is used for acquiring scene information of a target vehicle to generate a space-time corridor, wherein the space-time corridor comprises a plurality of steps corresponding to a plurality of time slices in an S-L-T three-dimensional space, and the steps are the drivable range of the target vehicle in the corresponding time slices; the construction module is used for constructing a track cost function based on the state quantity and the control quantity of the target vehicle, wherein the state quantity comprises at least one of position, speed and acceleration, and the control quantity comprises the impact degree; the planning module is used for planning the running track of the target vehicle in a plurality of steps based on the track cost function under the constraint of the space-time corridor, wherein the running track comprises a plurality of spline curve segments respectively corresponding to the steps, and the constraint of the space-time corridor comprises an equality constraint on the state quantity of the target vehicle and an inequality constraint on the state quantity and the control quantity of the target vehicle.

In one embodiment, the construction module 22 is specifically configured to construct a state cost sub-function based on the state quantity of the target vehicle, where the state cost sub-function includes a state component weight, and the state component weight corresponds to the position, the speed, and the acceleration; constructing a control cost sub-function based on the control quantity of the target vehicle, wherein the control cost sub-function comprises a control component weight, and the control component weight corresponds to the impact degree; and constructing a track cost function based on the state cost sub-function and the control cost sub-function.

In one embodiment, the planning module 23 is further configured to construct an equality constraint on the state quantity of the target vehicle based on continuity of the spline segment state quantity in each step adjacent to the space-time corridor.

In one embodiment, the spline is segmented into cubic splines.

the planning module 23 is further configured to construct an initial joint constraint on the state quantity and the control quantity of the target vehicle based on the space-time corridor and the bezier curve, where the initial joint constraint is a constraint on a control point of the bezier curve; determining coefficient mapping of a spline curve and a Bezier curve; based on the initial joint constraint and the coefficient map, a joint constraint on the target vehicle state quantity and the control quantity is constructed.

In one embodiment, the planning module 23 is specifically configured to project the space-time corridor to an S-T plane and/or an L-T plane, where the S-T plane is a plane in which a travelable longitudinal track is associated with time, and the L-T plane is a plane in which a travelable transverse track is associated with time; determining the intersection boundary of adjacent steps in the space-time corridor on the S-T plane and/or the L-T plane; and constraining a starting control point and/or a terminating control point of the Bezier curve in the corresponding step by the handover boundary.

In one embodiment, the planning module 23 is further configured to construct an initial constraint on the control quantity of the target vehicle based on the space-time corridor and the bezier curve, where the initial constraint is an inequality constraint on a control point of the bezier curve; determining coefficient mapping of a spline curve and a Bezier curve; and constructing a constraint on the control quantity of the target vehicle based on the initial constraint and the coefficient mapping.

In one embodiment, the planning module 23 is specifically configured to calculate, under the constraint of the space-time corridor, a longitudinal track and a transverse track associated with time of the target vehicle based on the track cost function; and combining the longitudinal track and the transverse track to obtain the running track of the target vehicle.

The trajectory planning method according to the embodiment of the present specification is described above with reference to fig. 1 to 8. The details mentioned in the description of the method embodiments above apply equally to the trajectory planning device of the embodiments of the present description. The above trajectory planning device may be implemented in hardware, or in software, or in a combination of hardware and software.

Fig. 10 shows a hardware configuration diagram of an electronic device according to an embodiment of the present specification. As shown in fig. 10, the electronic device 30 may include at least one processor 31, a memory 32 (e.g., a non-volatile memory), a memory 33, and a communication interface 34, and the at least one processor 31, the memory 32, the memory 33, and the communication interface 34 are connected together via an internal bus 35. The at least one processor 31 executes at least one computer readable instruction stored or encoded in the memory 32.

It should be understood that the computer-executable instructions stored in the memory 32, when executed, cause the at least one processor 31 to perform the various operations and functions described above in connection with fig. 1-8 in various embodiments of the present description.

In embodiments of the present description, electronic device 30 may include, but is not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile electronic devices, smart phones, tablet computers, cellular phones, personal Digital Assistants (PDAs), handsets, messaging devices, wearable electronic devices, consumer electronic devices, and the like.

According to one embodiment, a program product, such as a machine-readable medium, is provided. The machine-readable medium may have instructions (i.e., elements described above implemented in software) that, when executed by a machine, cause the machine to perform the various operations and functions described above in connection with fig. 1-8 in various embodiments of the specification. In particular, a system or apparatus provided with a readable storage medium having stored thereon software program code implementing the functions of any of the above embodiments may be provided, and a computer or processor of the system or apparatus may be caused to read out and execute instructions stored in the readable storage medium.

In this case, the program code itself read from the readable medium may implement the functions of any of the above embodiments, and thus the machine-readable code and the readable storage medium storing the machine-readable code form part of the present specification.

Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or cloud by a communications network.

It will be appreciated by those skilled in the art that various changes and modifications can be made to the embodiments disclosed above without departing from the spirit of the invention. Accordingly, the scope of protection of this specification should be limited by the attached claims.

It should be noted that not all the steps and units in the above flowcharts and the system configuration diagrams are necessary, and some steps or units may be omitted according to actual needs. The order of execution of the steps is not fixed and may be determined as desired. The apparatus structures described in the above embodiments may be physical structures or logical structures, that is, some units may be implemented by the same physical client, or some units may be implemented by multiple physical clients, or may be implemented jointly by some components in multiple independent devices.

In the above embodiments, the hardware units or modules may be implemented mechanically or electrically. For example, a hardware unit, module or processor may include permanently dedicated circuitry or logic (e.g., a dedicated processor, FPGA or ASIC) to perform the corresponding operations. The hardware unit or processor may also include programmable logic or circuitry (e.g., a general purpose processor or other programmable processor) that may be temporarily configured by software to perform the corresponding operations. The particular implementation (mechanical, or dedicated permanent, or temporarily set) may be determined based on cost and time considerations.

The detailed description set forth above in connection with the appended drawings describes exemplary embodiments, but does not represent all embodiments that may be implemented or fall within the scope of the claims. The term "exemplary" used throughout this specification means "serving as an example, instance, or illustration," and does not mean "preferred" or "advantageous over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.

The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

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

2. The trajectory planning method according to claim 1, characterized in that constructing a trajectory cost function based on the state quantity and the control quantity of the target vehicle specifically includes:

3. The trajectory planning method of claim 1, further comprising:

and/or the spline curve is segmented into cubic spline curves.

4. The trajectory planning method of claim 1, wherein the inequality constraints on the target vehicle state quantity and the control quantity include joint constraints;

the method further comprises the steps of:

determining coefficient mapping of a spline curve and a Bezier curve;

5. The trajectory planning method according to claim 4, characterized in that it comprises in particular:

6. The trajectory planning method of claim 1, further comprising:

determining coefficient mapping of a spline curve and a Bezier curve;

7. The trajectory planning method according to claim 1, characterized in that, under the constraint of the space-time corridor, a travel trajectory of the target vehicle in a plurality of steps is planned based on the trajectory cost function, and specifically comprises:

8. A trajectory planning device, comprising:

9. An electronic device, comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the trajectory planning method of any one of claims 1 to 7.

10. A machine readable storage medium storing executable instructions that when executed cause the machine to perform the trajectory planning method of any one of claims 1 to 7.