CN113448335A - Path planning method and device, vehicle and readable storage medium - Google Patents

Path planning method and device, vehicle and readable storage medium Download PDF

Info

Publication number
CN113448335A
CN113448335A CN202110748764.9A CN202110748764A CN113448335A CN 113448335 A CN113448335 A CN 113448335A CN 202110748764 A CN202110748764 A CN 202110748764A CN 113448335 A CN113448335 A CN 113448335A
Authority
CN
China
Prior art keywords
path
points
point
control points
constraint
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110748764.9A
Other languages
Chinese (zh)
Inventor
温勇兵
刘懿
苏镜仁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Xiaopeng Autopilot Technology Co Ltd
Original Assignee
Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Xiaopeng Autopilot Technology Co Ltd filed Critical Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority to CN202110748764.9A priority Critical patent/CN113448335A/en
Publication of CN113448335A publication Critical patent/CN113448335A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
    • G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application provides a path planning method. The path planning method comprises the steps of obtaining a plurality of path points of a reference path generated based on a road reference line; calculating a plurality of initial control points according to the path points; adjusting the initial control points based on the objective function, the boundary constraint and the curvature constraint to generate target control points; and generating a final path according to the target control point. According to the path planning method, the path planning device, the vehicle and the computer-readable storage medium, the multiple path points of the reference path are obtained, the multiple control points are generated according to the path points, the control points are adjusted according to the objective function, the boundary constraint and the curvature constraint, and the final path is generated according to the target control points.

Description

Path planning method and device, vehicle and readable storage medium
Technical Field
The present disclosure relates to the field of image technologies, and in particular, to a path planning method, a path planning apparatus, a vehicle, and a computer-readable storage medium.
Background
With the development of artificial intelligence, unmanned vehicles have emerged, freeing the driver. At present, routes are planned according to road reference lines mostly by automatic driving vehicles, the road reference lines are generally subjected to intensive sampling, then a complete route is obtained through intermediate interpolation, and finally a route which is along the road reference lines or deviates from the road reference lines by a certain distance is generated, so that the safety of the generated route is low.
Disclosure of Invention
The embodiment of the application provides a path planning method, a path planning device, a vehicle and a computer readable storage medium.
The path planning method comprises the steps of obtaining a plurality of path points of a reference path generated based on a road reference line; calculating a plurality of initial control points according to the path points; adjusting the initial control points based on an objective function, a boundary constraint and a curvature constraint to generate target control points; and generating a final path according to the target control point.
In some embodiments, said calculating a plurality of initial control points from said path points comprises: and calculating a plurality of control points according to the path points and a first equation of the plurality of corresponding control points, and the derivative of the reference path and a second equation of the plurality of corresponding control points.
In some embodiments, said adjusting said initial control points to generate target control points based on an objective function, a boundary constraint, and a curvature constraint comprises: inputting the control points, the objective function, the boundary constraint, and the curvature constraint to a preset optimizer to output a plurality of target control points that minimize an output value of the objective function.
In some embodiments, the objective function includes a first portion, a second portion, a third portion and a fourth portion, the first portion is a distance minimum cost from the reference path, the second portion is a road centering cost, the third portion is a path second order smoothness cost, and the fourth portion is a path third order smoothness cost.
In some embodiments, the boundary constraints include boundary ranges, the boundary constraints being used to cause the control points to be located within corresponding boundary ranges, the boundary ranges corresponding to the control points being generated from at least one of road boundaries and obstacles.
In some embodiments, the boundary constraints further include a start point constraint and/or an end point constraint, the start point constraint being used to make the start point of the final path located at a preset start point position, and the end point constraint being used to make the end point of the final path located at the preset end point position.
In some embodiments, the curvature constraint includes a range of curvatures, the curvature constraint for causing the curvature of the waypoint to lie within the range of curvatures.
In some embodiments, the path planning method further includes obtaining a curvature of a reference point corresponding to the path point on the road reference line; and calculating the curvature of the path point according to the curvature of the reference point and the control point.
In some embodiments, the generating a final path from the target control point includes: generating a path function according to a preset curve parameter equation and a target control point, wherein the preset curve parameter equation comprises a uniform B spline curve; and generating the final path according to the path function.
The path planning device of the embodiment of the application comprises a first obtaining module, a first calculating module, an adjusting module and a generating module. The acquisition module is used for acquiring a plurality of path points of a reference path generated based on a road reference line; the calculation module is used for calculating a plurality of initial control points according to the path points; the adjusting module is used for adjusting the initial control point based on an objective function, a boundary constraint and a curvature constraint so as to generate a target control point; the generating module is used for generating a final path according to the target control point.
The vehicle of the embodiment of the present application includes a processor. The processor is used for acquiring a plurality of path points of a reference path generated based on a road reference line; calculating a plurality of initial control points according to the path points; adjusting the initial control points based on an objective function, a boundary constraint and a curvature constraint to generate target control points; and generating a final path according to the target control point.
A computer-readable storage medium embodying a computer program which, when executed by one or more processors, causes the processors to perform a path planning method. The path planning method comprises the steps of obtaining a plurality of path points of a reference path generated based on a road reference line; calculating a plurality of initial control points according to the path points; adjusting the initial control points based on an objective function, a boundary constraint and a curvature constraint to generate target control points; and generating a final path according to the target control point.
According to the path planning method, the path planning device, the vehicle and the computer-readable storage medium, the multiple path points of the reference path generated based on the road reference line are obtained, the multiple control points are generated according to the path points, then the control points are adjusted according to the objective function, the boundary constraint and the curvature constraint, and finally the final path is generated according to the target control points.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram of a path planning method according to some embodiments of the present application;
FIG. 2 is a block diagram of a path planner according to some embodiments of the present application;
FIG. 3 is a schematic plan view of a vehicle according to certain embodiments of the present application;
FIG. 4 is a schematic flow chart diagram of a path planning method according to some embodiments of the present application;
FIG. 5 is a schematic diagram of a path planning method according to some embodiments of the present application;
fig. 6-8 are schematic flow charts of a path planning method according to some embodiments of the present disclosure;
FIGS. 9 and 10 are schematic diagrams of a scenario of a path planning method according to some embodiments of the present application;
FIG. 11 is a curvature profile of a final path and a reference path of certain embodiments of the present application; and
FIG. 12 is a schematic diagram of a connection between a processor and a computer readable storage medium according to some embodiments of the present application.
Detailed Description
Embodiments of the present application will be further described below with reference to the accompanying drawings. The same or similar reference numbers in the drawings identify the same or similar elements or elements having the same or similar functionality throughout. In addition, the embodiments of the present application described below in conjunction with the accompanying drawings are exemplary and are only for the purpose of explaining the embodiments of the present application, and are not to be construed as limiting the present application.
When path planning is performed, generally, a road reference line is collected for intensive sampling, then a complete path is obtained through modes such as intermediate interpolation, and if an obstacle exists on the road reference line or the road is tortuous, the generated path cannot well avoid the obstacle, and the path has poor smoothness and is not beneficial to driving safety.
Referring to fig. 1 to 3, a path planning method according to an embodiment of the present disclosure includes the following steps:
011: acquiring a plurality of path points of a reference path generated based on a road reference line;
012: calculating a plurality of initial control points according to the path points;
013: adjusting the initial control points based on the objective function, the boundary constraint and the curvature constraint to generate target control points;
014: and generating a final path according to the target control point.
The path planning apparatus 10 according to the embodiment of the present application includes a first obtaining module 11, a first calculating module 12, an adjusting module 13, and a generating module 14. The first obtaining module 11, the first calculating module 12 and the generating module 14 are configured to perform step 011, step 012, step 013 and step 014, respectively. That is, the first obtaining module 11 is configured to obtain a plurality of path points of a reference path generated based on a road reference line; the first calculating module 12 is configured to calculate a plurality of initial control points according to the path points; the adjusting module 13 is configured to adjust the initial control point based on the objective function, the boundary constraint and the curvature constraint to generate a target control point; the generating module 14 is configured to generate a final path according to the target control point.
The vehicle 100 of the embodiment of the present application includes a processor 20. The processor 20 is used for acquiring a plurality of path points of a reference path generated based on the road reference line; calculating a plurality of initial control points according to the path points; adjusting the initial control points based on the objective function, the boundary constraint and the curvature constraint to generate target control points; and generating a final path according to the target control point. That is, step 011, step 012, step 013, and step 014 may be implemented by processor 20. In other embodiments, the vehicle 100 is connected to a cloud (not shown), and the steps 011, 012, 013 and 014 can be implemented by the cloud.
Specifically, the vehicle 100 may embed a high-precision map of a current area, and obtain a road reference line (e.g., a road center line) from the high-precision map, and the vehicle 100 may generate a rough reference path in a Frenet coordinate system based on a preset path generation algorithm, and then obtain a plurality of path points on the reference path, where the path points include a first distance and a second distance (respectively (S, L)), the first distance S is an arc length distance from a foot point to a start point of the road reference line when the position of the vehicle 100 is projected onto the road reference line, and the second distance L is a normal distance from the position of the vehicle 100 and the foot point.
Processor 20 may then calculate a plurality of control points based on the plurality of waypoints, each waypoint being determinable from the plurality of control points. In the present embodiment, the path may be generated by a parameter equation of the uniform B-spline curve and the control points, and each path point may be determined by 2 control points, 3 control points, 4 control points, 5 control points, and the like. For example, each path point is determined by 4 control points when the parametric equation is a uniform 3 rd order B-spline curve, and each path point is determined by 5 control points when the parametric equation is a uniform 4 th order B-spline curve. In this way, a plurality of control points can be calculated from the path points based on the functional relationship between the path points and the control points. In the embodiment of the present application, the parameter equation is a uniform 3-order B-spline curve, and the parameter equation is a uniform 4-order B-spline curve, a uniform 5-order B-spline curve, and the like are basically similar, and are not described herein again.
Processor 20 then adjusts the control points based on the objective function, the boundary constraints, and the curvature constraints. The target function is generated based on the control points, the target function comprises a first part, a second part, a third part and a fourth part, the first part is the minimum distance cost with a reference path, the second part is the road centering cost, the third part is the path second-order smoothness cost, the fourth part is the path third-order smoothness cost, and after the control points are adjusted based on the target function, the output value of the target function is minimum, so that the minimum distance cost, the road centering cost, the path second-order smoothness cost and the path third-order smoothness cost are comprehensively minimized. After the control points are adjusted based on the boundary constraint and the curvature constraint, the path points determined by the control points are always located in the boundary range corresponding to the boundary constraint, and the curvature of the path points determined by the control points is located in the curvature range corresponding to the curvature constraint.
The processor 20 can generate a final path according to the target control point and the parameter equation of the uniform B-spline curve, and the final path meets the boundary constraint and the curvature constraint, so that the final path is smoother, is farther away from the obstacle, and has better safety.
According to the path planning method, the path planning device 10 and the vehicle 100, the multiple path points of the reference path are obtained, the multiple control points are generated according to the path points, the control points are adjusted according to the objective function, the boundary constraint and the curvature constraint, and the final path is generated according to the target control points.
Referring to fig. 2, 3 and 4, in some embodiments, step 012 includes:
0121: a plurality of control points are calculated from the first equation for the path point and the corresponding plurality of control points and the second equation for the derivative of the reference path and the corresponding plurality of control points.
In certain embodiments, the first calculation module 12 is further configured to perform step 0121. That is, the first calculation module 12 is further configured to calculate the plurality of control points according to the first equation of the path point and the corresponding plurality of control points, and the second equation of the derivative of the reference path and the corresponding plurality of control points.
In some embodiments, processor 20 is further configured to calculate a plurality of control points based on the first equation for the path point and the corresponding plurality of control points and the second equation for the derivative of the reference path and the corresponding plurality of control points. That is, step 0121 may be implemented by processor 20.
Specifically, the number of the path points is n, and when a plurality of control points are calculated according to the path points, n first equations may be established according to a functional relationship between each path point and the plurality of control points for determining the path point:
Figure BDA0003145301070000051
Figure BDA0003145301070000052
wherein l0A path point corresponding to the starting point of the reference path, liRepresenting path points in the reference path,/n-1Indicating a path point, Q, corresponding to the end point of the reference pathiDenotes a control point, i is a natural number.
In the uniform 3 rd order B-spline curve, the number of control points is 2 more than the number of path points, therefore, n first equation associations cannot be solved for n +2 control points, and the derivative of the reference path and the corresponding control points can be usedThe functional relationship of the points, the second equation is again established, e.g. the derivative of the starting point satisfies the following functional relationship:
Figure BDA0003145301070000053
Figure BDA0003145301070000054
referring to fig. 5, Δ s is a distance between two adjacent waypoints, and is a predetermined value.
The functional relationship between a waypoint and the plurality of control points used to determine the waypoint may be determined according to the parametric equation of a uniform 3 rd order B-spline curve. The parameter equation of the B spline curve is as follows:
Figure BDA0003145301070000055
wherein the content of the first and second substances,
Figure BDA0003145301070000056
the q-order differential expression of the parametric equation for a B-spline curve can be obtained as follows:
Figure BDA0003145301070000057
in the path image in the Frenet coordinate system shown in fig. 5, an abscissa s is an arc length distance (i.e., a first distance) from a starting point of the path to a drop-foot point when the vehicle 100 is projected on the path in the Frenet coordinate system, and L is a normal distance (i.e., a second distance) between the vehicle 100 and the drop-foot point; s is located in each curve segment determined by the above parameter equation (e.g./in FIG. 5)0l1、l1l2Etc.) between the start and end points (s e s as shown in FIG. 5i，si+1]) At the determination of siCorresponding to liAnd si+1Corresponding to li+1Then, through s in [ s ]i，si+1]Obtaining the curve l by internal value takingili+1。
Figure BDA0003145301070000058
Mk+1Any element in the matrix can be represented by the formula:
Figure BDA0003145301070000059
calculating to obtain; m isi，jRepresents Mk+1The ith, j-th element of the matrix ((k +1) × (k +1) square). Thus, the base matrix M of the uniform cubic B-spline curve can be obtained4：
Figure BDA0003145301070000061
In addition to this, the present invention is,
b(0)＝[1 u u2u3 … uk]T；
b(1)＝[0 1 2u 3u2 … kuk-1]T；
b(2)＝[0 0 2 6u … k(k-1)uk-2]T；
b(3)＝[0 0 0 6 …k(k-1)(k-2)uk-3]T；
the reference path is composed of a plurality of curves, the collected path points are nodes in the reference path, that is, the starting point or the end point of each curve, the path points can be obtained by sampling at equal distances, for example, one path point is collected on the reference path every Δ s (which is a predetermined value and can be determined according to the number of collected path points and the length of the reference path), and for the nodes, u is 0, so that the functional relationship between the path points and the control points of the B-spline curve for 3 times can be calculated according to the formula:
Figure BDA0003145301070000062
Figure BDA0003145301070000063
Figure BDA0003145301070000064
Figure BDA0003145301070000065
referring to fig. 2, 3 and 6, in some embodiments, step 013 includes the following steps:
0131: the control points, the objective function, the boundary constraint, and the curvature constraint are input to a preset optimizer to output a plurality of target control points that minimize an output value of the objective function.
In certain embodiments, the adjusting module 13 is further configured to perform step 0131. That is, the adjusting module 13 is further configured to input the control points, the objective function, the boundary constraint, and the curvature constraint to a preset optimizer to output a plurality of target control points that minimize the output value of the objective function.
In some embodiments, the processor 20 is further configured to input the control points, the objective function, the boundary constraints, and the curvature constraints to a preset optimizer to output a plurality of target control points that minimize an output value of the objective function. That is, step 0131 may be implemented by processor 20.
Specifically, optimization of the control points can be achieved by setting optimization conditions through an optimizer. The optimizer may be, for example, non-linear optimization software such as Ipopt, NLopt, snpot, etc.
After the objective function, the control points, the boundary constraint and the curvature constraint are all input into the optimizer, the optimizer can automatically calculate and output the optimized control points which enable the output value of the objective function to be minimum and meet the boundary constraint and the curvature constraint.
The objective function is:
Figure BDA0003145301070000071
Figure BDA0003145301070000072
wherein the first part
Figure BDA0003145301070000073
Figure BDA0003145301070000074
For the minimum distance cost from the reference path, the second part i is 0n-3Qi +2-Qi2 Δ s2 for road centering cost, and the third part is road centering cost
Figure BDA0003145301070000075
Is the path second order smoothness cost; fourth section
Figure BDA0003145301070000076
The third order smoothness cost of the path. Omegaref、ωdl、ωddl、ωdddlWeight coefficients respectively representing the terms, ω, of the vehicle 100 under different scenesref、ωdl、ωddl、ωdddlIn contrast, e.g. for scenes with higher smoothness requirements, ω will beddl、ωdddlHigher weight setting of (c), e.g. in a centrally demanding scenario, ωdlThe weight setting is higher, so that the path optimization effect under different scenes is improved.
The boundary constraint comprises a boundary range, the boundary constraint is used for enabling the control point to be located in the corresponding boundary range, and the boundary range corresponding to the control point is generated according to the road boundary. The boundary range may also take into account more factors, such as obstacles, to generate a more accurate boundary range from the road boundary and the obstacles.
For example, the boundary range of each control point is: li，min≤Qi≤li，max，li，minAnd li，maxThe information such as the road boundary corresponding to the control point and the obstacles near the control point is calculated, so that the control point is ensured to be always positioned in the road boundary, and the obstacles can be well bypassed according to the final path generated by the control point, and the driving safety is ensured.
In addition, the boundary constraint may further include a start point constraint and/or an end point constraint, by which a start point of the final path may be located at a preset start point position; with the end point constraint, the end point of the final path may be located at the preset end point position, so that the start point and the end point of the final path are the start point and the end point of the travel of the vehicle 100, respectively.
For example, the starting point constraint may be to locate the starting point of the final path at the starting point of the reference path, and the starting point constraint may be performed by a functional relationship between the path point and the control point:
Figure BDA0003145301070000077
for another example, the end point constraint may not be set, or may be set so that the end point of the final path is located at the end point of the reference path, and the end point constraint may be performed by a functional relationship between the path point and the control point:
Figure BDA0003145301070000078
the curvature constraints include a range of curvatures, and the curvature k (i) corresponding to each path point lies within the range of curvatures: kappamin≤k(i)≤kmaxFor example κmin＝-0.2，κmaxThe curvature of the final path is always within the curvature range, and the final path is smoother.
Referring again to fig. 2, 3 and 7, in some embodiments, the path planning method further includes:
015: acquiring the curvature of a reference point corresponding to the path point on a road reference line;
016: and calculating the curvature of the path point according to the curvature of the reference point and the control point.
In some embodiments, the path planning apparatus further includes a second obtaining module 15 and a second calculating module 16, and the second obtaining module 15 and the second calculating module 16 are respectively configured to perform steps 015 and 016. That is, the second obtaining module 15 is configured to obtain the curvature of a reference point corresponding to the path point on the road reference line; the second calculation module 16 is used for calculating the curvature of the path point according to the curvature of the reference point and the control point.
In some embodiments, the processor 20 is further configured to obtain a curvature of a reference point corresponding to the waypoint on the road reference line; the curvature of the upper path point is calculated based on the curvature of the reference point, the path point, and the control point. That is, step 015 and step 016 may be implemented by the processor 20.
Specifically, to implement the curvature constraint, the processor 20 needs to calculate the curvature of each waypoint and make the curvature of the waypoint lie within the curvature range. The curvature of each path point determined by the control point sees k (i) the calculation formula is as follows:
Figure BDA0003145301070000081
wherein k isriThe curvature of the path point at the matched point on the road reference line, the reference point on the road reference line and the curvature thereof are preset values, and the processor 20 can directly obtain the curvature. And then, carrying out functional relation between the path points and the control points of the 3-time B-spline curve obtained by the calculation:
Figure BDA0003145301070000082
the curvature at the path point can be determined by substituting the formula. The curvature of the path point is determined according to a formula formed by the control points, and the curvature of the path point is in a curvature range, so that the control points are also restricted by the curvature range, and the control points are adjusted through curvature restriction.
Referring to fig. 2, 3 and 8, in some embodiments, step 014 includes the steps of:
0141: generating a path function according to a preset curve parameter equation and the target control point, wherein the preset curve parameter equation comprises a uniform B spline curve; and
0142: and generating a final path according to the path function.
In certain embodiments, generation module 14 is further configured to perform steps 0141 and 0142. That is, the generating module 14 is further configured to generate a path function according to a preset curve parameter equation and the target control point, where the preset curve parameter equation includes a uniform B-spline curve; and generating a final path according to the path function.
In some embodiments, the processor 20 is further configured to generate a path function according to a preset curve parameter equation and the target control point, the preset curve parameter equation including a uniform B-spline curve; and generating a final path according to the path function. That is, steps 0141 and 0142 may be implemented by processor 20.
Specifically, the preset curve parameter equation may be a parameter equation of a uniform B-spline curve:
Figure BDA0003145301070000083
after the target control point is determined, the parameter equation of the uniform B spline curve can be determined according to the control point, so that the s is in the [ s ]i，si+1]Obtaining the curve l by internal value takingili+1Thereby generating a B-spline curve between each two waypoint to form the final path.
A comparison of the final path M3, the reference path M2 and the road reference line M1 generated from the control points adjusted by the objective function, the boundary constraint and the curvature constraint is shown in fig. 9 and 10, where fig. 10 is a detailed enlarged view of the region M in fig. 9, and it can be seen that the final path M3 is smoother and more distant from the obstacle Z than the reference path M2. Thus, the security of the final path m1 is good.
In addition, referring to fig. 11, according to the curvature distribution diagrams of the final path m3 and the reference path m2, it can be seen that the curvatures of the final path m3 are both located between the intervals [ -0.2,0.2], so that the curvature constraint is satisfied, and the smoothness is good.
Referring to fig. 12, a computer readable storage medium 300 storing a computer program 302 according to an embodiment of the present disclosure, when the computer program 302 is executed by one or more processors 20, the processor 20 may execute the path planning method according to any of the above embodiments.
For example, referring to fig. 1, the computer program 302, when executed by the one or more processors 20, causes the processors 20 to perform the steps of:
011: acquiring a plurality of path points of a reference path generated based on a road reference line;
012: calculating a plurality of initial control points according to the path points;
013: adjusting the initial control points based on the objective function, the boundary constraint and the curvature constraint to generate target control points;
014: and generating a final path according to the target control point.
For another example, referring to fig. 4, when the computer program 302 is executed by the one or more processors 20, the processors 20 may further perform the steps of:
0121: a plurality of control points are calculated from the first equation for the path point and the corresponding plurality of control points and the second equation for the derivative of the reference path and the corresponding plurality of control points.
In the description herein, references to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example" or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more program modules for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Although embodiments of the present application have been shown and described above, it is to be understood that the above embodiments are exemplary and not to be construed as limiting the present application, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (12)

1. A method of path planning, comprising:
acquiring a plurality of path points of a reference path generated based on a road reference line;
calculating a plurality of initial control points according to the path points;
adjusting the initial control points based on an objective function, a boundary constraint and a curvature constraint to generate target control points;
and generating a final path according to the target control point.
2. The path planning method according to claim 1, wherein the calculating a plurality of initial control points according to the path points comprises:
and calculating a plurality of control points according to the path points and a first equation of the plurality of corresponding control points, and the derivative of the reference path and a second equation of the plurality of corresponding control points.
3. The path planning method according to claim 1, wherein the adjusting the initial control points based on the objective function, the boundary constraint, and the curvature constraint to generate target control points comprises:
inputting the control points, the objective function, the boundary constraints, and the curvature constraints to a preset optimizer to output a plurality of adjusted control points that minimize an output value of the objective function.
4. The path planning method according to claim 1, wherein the objective function includes a first part, a second part, a third part and a fourth part, the first part is a distance minimum cost from the reference path, the second part is a road centering cost, the third part is a path second order smoothness cost, and the fourth part is a path third order smoothness cost.
5. The path planning method according to claim 1, wherein the boundary constraint includes a boundary range, and the boundary constraint is used to make the control points located in a corresponding boundary range, and the boundary range corresponding to the control points is generated according to a road boundary.
6. The path planning method according to claim 5, wherein the boundary constraints further include a start point constraint and/or an end point constraint, the start point constraint being used to make the start point of the final path located at a preset start point position, and the end point constraint being used to make the end point of the final path located at a preset end point position.
7. A path planning method according to claim 1, wherein the curvature constraints comprise a range of curvatures, the curvature constraints being used to bring the curvature of the path point within the range of curvatures.
8. The path planning method according to claim 7, further comprising:
acquiring the curvature of a reference point corresponding to the path point on the road reference line;
and calculating the curvature of the path point according to the curvature of the reference point and the control point.
9. The path planning method according to claim 1, wherein the generating a final path according to the target control point comprises:
generating a path function according to a preset curve parameter equation and a target control point, wherein the preset curve parameter equation comprises a uniform B spline curve; and
and generating the final path according to the path function.
10. A path planning apparatus, comprising:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a plurality of path points of a reference path generated based on a road reference line;
the first calculation module is used for calculating a plurality of initial control points according to the path points;
an adjusting module, configured to adjust the initial control point based on an objective function, a boundary constraint, and a curvature constraint to generate a target control point;
and the generating module is used for generating a final path according to the target control point.
11. A vehicle, comprising a processor configured to:
acquiring a plurality of path points of a reference path generated based on a road reference line;
calculating a plurality of initial control points according to the path points;
adjusting the initial control points based on an objective function, a boundary constraint and a curvature constraint to generate target control points;
and generating a final path according to the target control point.
12. A computer-readable storage medium containing a computer program which, when executed by a processor, causes the processor to carry out the path planning method of any one of claims 1-9.
CN202110748764.9A 2021-07-02 2021-07-02 Path planning method and device, vehicle and readable storage medium Pending CN113448335A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110748764.9A CN113448335A (en) 2021-07-02 2021-07-02 Path planning method and device, vehicle and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110748764.9A CN113448335A (en) 2021-07-02 2021-07-02 Path planning method and device, vehicle and readable storage medium

Publications (1)

Publication Number Publication Date
CN113448335A true CN113448335A (en) 2021-09-28

Family

ID=77814775

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110748764.9A Pending CN113448335A (en) 2021-07-02 2021-07-02 Path planning method and device, vehicle and readable storage medium

Country Status (1)

Country Link
CN (1) CN113448335A (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113932826A (en) * 2021-10-13 2022-01-14 北京经纬恒润科技股份有限公司 Optimization method and system for vehicle navigation path
CN113985872A (en) * 2021-10-25 2022-01-28 广东嘉腾机器人自动化有限公司 AGV (automatic guided vehicle) goods taking path planning method, device and medium based on visual detection
CN114114930A (en) * 2022-01-28 2022-03-01 清华大学 Method, device, equipment and medium for generating local reference path of automobile
CN114264307A (en) * 2021-12-15 2022-04-01 广州小鹏自动驾驶科技有限公司 Route generation method, apparatus, vehicle and storage medium
CN114296452A (en) * 2021-12-16 2022-04-08 华人运通(上海)自动驾驶科技有限公司 Automatic parking path planning method, apparatus and computer-readable storage medium
CN115077534A (en) * 2022-08-11 2022-09-20 合肥井松智能科技股份有限公司 AGV path planning method based on B spline curve
CN115357032A (en) * 2022-10-20 2022-11-18 上海仙工智能科技有限公司 NURBS-based mobile robot path generation method, system and storage medium
CN117311368A (en) * 2023-11-23 2023-12-29 武汉光昱明晟智能科技有限公司 Automatic pre-marking robot system and operation method thereof
CN117533317A (en) * 2023-12-12 2024-02-09 北京斯年智驾科技有限公司 Tractor reversing path smoothing method, system, device and storage medium
WO2024031959A1 (en) * 2022-08-10 2024-02-15 美的集团(上海)有限公司 Obstacle avoidance robot, control method and control device thereof, and readable storage medium
CN117533317B (en) * 2023-12-12 2024-05-17 北京斯年智驾科技有限公司 Tractor reversing path smoothing method, system, device and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108153310A (en) * 2017-12-22 2018-06-12 南开大学 A kind of Mobile Robot Real-time Motion planing method based on human behavior simulation
US20190086932A1 (en) * 2017-09-18 2019-03-21 Baidu Usa Llc Smooth road reference line for autonomous driving vehicles based on 2d constrained smoothing spline
US20190086925A1 (en) * 2017-09-18 2019-03-21 Baidu Usa Llc Path optimization based on constrained smoothing spline for autonomous driving vehicles
CN111176285A (en) * 2020-01-02 2020-05-19 北京汽车集团有限公司 Method and device for planning travel path, vehicle and readable storage medium
CN111338335A (en) * 2019-12-31 2020-06-26 清华大学 Vehicle local track planning method under structured road scene
CN111547066A (en) * 2020-04-27 2020-08-18 中汽研(天津)汽车信息咨询有限公司 Vehicle trajectory tracking method, device, equipment and storage medium
US20210188286A1 (en) * 2019-12-20 2021-06-24 Baidu Usa Llc A spline curve and spiral curve based reference line smoothing method
CN113050652A (en) * 2021-03-25 2021-06-29 上海海事大学 Trajectory planning method for automatic berthing of intelligent ship

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190086932A1 (en) * 2017-09-18 2019-03-21 Baidu Usa Llc Smooth road reference line for autonomous driving vehicles based on 2d constrained smoothing spline
US20190086925A1 (en) * 2017-09-18 2019-03-21 Baidu Usa Llc Path optimization based on constrained smoothing spline for autonomous driving vehicles
CN109521763A (en) * 2017-09-18 2019-03-26 百度（美国）有限责任公司 The path optimization based on constraint smoothing spline for automatic driving vehicle
CN108153310A (en) * 2017-12-22 2018-06-12 南开大学 A kind of Mobile Robot Real-time Motion planing method based on human behavior simulation
US20210188286A1 (en) * 2019-12-20 2021-06-24 Baidu Usa Llc A spline curve and spiral curve based reference line smoothing method
CN111338335A (en) * 2019-12-31 2020-06-26 清华大学 Vehicle local track planning method under structured road scene
CN111176285A (en) * 2020-01-02 2020-05-19 北京汽车集团有限公司 Method and device for planning travel path, vehicle and readable storage medium
CN111547066A (en) * 2020-04-27 2020-08-18 中汽研(天津)汽车信息咨询有限公司 Vehicle trajectory tracking method, device, equipment and storage medium
CN113050652A (en) * 2021-03-25 2021-06-29 上海海事大学 Trajectory planning method for automatic berthing of intelligent ship

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
曾波等: "六自由度机械臂轨迹规划研究与仿真", 《智能计算机与应用》, vol. 10, no. 11, pages 65 - 69 *

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113932826A (en) * 2021-10-13 2022-01-14 北京经纬恒润科技股份有限公司 Optimization method and system for vehicle navigation path
CN113932826B (en) * 2021-10-13 2024-05-07 北京经纬恒润科技股份有限公司 Optimization method and system for vehicle navigation path
CN113985872A (en) * 2021-10-25 2022-01-28 广东嘉腾机器人自动化有限公司 AGV (automatic guided vehicle) goods taking path planning method, device and medium based on visual detection
CN114264307A (en) * 2021-12-15 2022-04-01 广州小鹏自动驾驶科技有限公司 Route generation method, apparatus, vehicle and storage medium
CN114296452A (en) * 2021-12-16 2022-04-08 华人运通(上海)自动驾驶科技有限公司 Automatic parking path planning method, apparatus and computer-readable storage medium
CN114114930A (en) * 2022-01-28 2022-03-01 清华大学 Method, device, equipment and medium for generating local reference path of automobile
CN114114930B (en) * 2022-01-28 2022-04-19 清华大学 Method, device, equipment and medium for generating local reference path of automobile
WO2024031959A1 (en) * 2022-08-10 2024-02-15 美的集团(上海)有限公司 Obstacle avoidance robot, control method and control device thereof, and readable storage medium
CN115077534B (en) * 2022-08-11 2022-11-15 合肥井松智能科技股份有限公司 AGV path planning method based on B spline curve
CN115077534A (en) * 2022-08-11 2022-09-20 合肥井松智能科技股份有限公司 AGV path planning method based on B spline curve
CN115357032A (en) * 2022-10-20 2022-11-18 上海仙工智能科技有限公司 NURBS-based mobile robot path generation method, system and storage medium
CN115357032B (en) * 2022-10-20 2023-01-31 上海仙工智能科技有限公司 NURBS-based mobile robot path generation method, system and storage medium
CN117311368A (en) * 2023-11-23 2023-12-29 武汉光昱明晟智能科技有限公司 Automatic pre-marking robot system and operation method thereof
CN117311368B (en) * 2023-11-23 2024-04-09 武汉光昱明晟智能科技有限公司 Automatic pre-marking robot system and operation method thereof
CN117533317A (en) * 2023-12-12 2024-02-09 北京斯年智驾科技有限公司 Tractor reversing path smoothing method, system, device and storage medium
CN117533317B (en) * 2023-12-12 2024-05-17 北京斯年智驾科技有限公司 Tractor reversing path smoothing method, system, device and storage medium

Similar Documents

Publication Publication Date Title
CN113448335A (en) Path planning method and device, vehicle and readable storage medium
US20200149906A1 (en) Path planning method, system and device for autonomous driving
CN110657814A (en) Trajectory planning method and device, vehicle and control method and system thereof
CN111177934B (en) Method, apparatus and storage medium for reference path planning
CN116147654B (en) Path planning method based on offline path library
Bertolazzi et al. Efficient re-planning for robotic cars
CN117203108A (en) Lane change based solely on local information
Vailland et al. Cubic bézier local path planner for non-holonomic feasible and comfortable path generation
Da Silva et al. Sparse road network model for autonomous navigation using clothoids
CN114802214A (en) Pure tracking automatic parking control method, performance evaluation tool and readable storage medium
JP6108910B2 (en) Gradient information generation system, method and program
CN111857148B (en) Unstructured road vehicle path planning method
CN113619604A (en) Integrated decision and control method and device for automatic driving automobile and storage medium
CN114115268B (en) Path generation method, device, vehicle and storage medium
WO2023137938A1 (en) Path planning method and apparatus for virtual character, electronic device, and storage medium
CN115534998A (en) Automatic driving integrated decision-making method and device, vehicle and storage medium
CN113753082B (en) Unmanned vehicle track updating method and device, control method and electronic equipment
Daniel et al. Energy constrained trajectory generation for ADAS
CN113850915A (en) Vehicle tracking method based on Autoware
CN114137972B (en) Path generation method, device, vehicle and storage medium
CN113625703A (en) Dynamic path tracking method
CN113568403A (en) Processing method, processing device, vehicle, and storage medium
CN112904837A (en) Data processing method, device and computer readable storage medium
CN114114930B (en) Method, device, equipment and medium for generating local reference path of automobile
Xu Precise path planning and trajectory tracking based on improved A-star algorithm

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination