CN111679678B - Track planning method and system for transverse and longitudinal separation and computer equipment - Google Patents

Track planning method and system for transverse and longitudinal separation and computer equipment Download PDF

Info

Publication number
CN111679678B
CN111679678B CN202010614679.9A CN202010614679A CN111679678B CN 111679678 B CN111679678 B CN 111679678B CN 202010614679 A CN202010614679 A CN 202010614679A CN 111679678 B CN111679678 B CN 111679678B
Authority
CN
China
Prior art keywords
cost function
candidate curve
weight
curve
candidate
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.)
Active
Application number
CN202010614679.9A
Other languages
Chinese (zh)
Other versions
CN111679678A (en
Inventor
姜赟程
金晓峰
熊焱飞
李泉
王秋旗
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.)
Anhui Haibo Intelligent Technology Co ltd
Original Assignee
Anhui Haibo Intelligent 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 Anhui Haibo Intelligent Technology Co ltd filed Critical Anhui Haibo Intelligent Technology Co ltd
Priority to CN202010614679.9A priority Critical patent/CN111679678B/en
Publication of CN111679678A publication Critical patent/CN111679678A/en
Application granted granted Critical
Publication of CN111679678B publication Critical patent/CN111679678B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • 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
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • 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
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

The invention discloses a track planning method for transverse and longitudinal separation, which is used for respectively planning a path and a speed of a vehicle between an initial position and a target position and comprises the following steps: when path planning is carried out, a candidate curve set is generated by utilizing a plurality of control points selected between an initial position and a target position; constructing a total cost function and a limiting condition, and calculating the value of the total cost function of each candidate curve; dividing an area between the initial position and the target position into a travelable area and an obstacle area according to the position of the obstacle; and when the vehicle enters the obstacle region, sequentially carrying out collision detection on each candidate curve according to the sequence of the total cost function values from small to large, wherein the first candidate curve passing through the collision detection is the optimal track, and the vehicle moves along the optimal track in the obstacle region.

Description

Track planning method and system for transverse and longitudinal separation and computer equipment
Technical Field
The invention relates to the field of unmanned driving, in particular to a track planning method and system with transverse and longitudinal separation and computer equipment.
Background
Most of the trajectory planning methods in the prior art are set for robots, the calculation amount is large, the vehicle dynamics and kinematics are not limited, and the real-time performance is lacked.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method, a system and computer equipment for planning a track with transverse and longitudinal separation.
In order to solve the technical problems, the invention adopts the following technical scheme:
a method for planning a track with transverse and longitudinal separation is used for respectively planning a path and a speed of a vehicle between an initial position and a target position, and comprises the following steps:
the method comprises the following steps: when path planning is carried out, a candidate curve set is generated by utilizing a plurality of control points selected between an initial position and a target position; constructing a total cost function and a limiting condition, and calculating the value of the total cost function of each candidate curve;
step two: dividing an area between the initial position and the target position into a travelable area and an obstacle area according to the position of the obstacle;
step three: and when the vehicle enters the obstacle region, sequentially carrying out collision detection on each candidate curve according to the sequence of the total cost function values from small to large, wherein the first candidate curve passing through the collision detection is the optimal track, and the vehicle moves along the optimal track in the obstacle region.
Specifically, in the step one, vehicle dynamics and kinematics limits, passenger comfort, vehicle safety and curve continuity are comprehensively considered when the total cost function is constructed.
In particular, the total cost function
Figure BDA0002563335430000011
Figure BDA0002563335430000012
Figure BDA0002563335430000013
Wherein the content of the first and second substances,
Figure BDA0002563335430000014
as a cost function of the distance between each two adjacent control points, wsIs the weight of the cost function;
Figure BDA0002563335430000021
as a cost function of the curvature of the candidate curve at each control point, wkIs the weight of the cost function;
Figure BDA0002563335430000022
as a cost function of the first derivative of the candidate curve at each control point,
Figure BDA0002563335430000023
is the weight of the cost function;
Figure BDA0002563335430000024
as a cost function of the second derivative of the candidate curve at each control point,
Figure BDA0002563335430000025
is the weight of the cost function;
Figure BDA0002563335430000026
as a cost function of the third derivative of the candidate curve at each control point,
Figure BDA0002563335430000027
is the weight of the cost function;
Figure BDA0002563335430000028
as a function of the cost of the lateral offset distance between each control point on the candidate curve and the predetermined reference line,
Figure BDA0002563335430000029
is the weight of the cost function;
Figure BDA00025633354300000210
as a cost function of the lateral acceleration of each control point on the candidate curve,
Figure BDA00025633354300000211
is the weight of the cost function;
Figure BDA00025633354300000212
as a cost function of the longitudinal acceleration at each control point on the candidate curve,
Figure BDA00025633354300000213
is the weight of the cost function;
Figure BDA00025633354300000214
as a cost function of the lateral acceleration change rate of each control point on the candidate curve,
Figure BDA00025633354300000215
as a function of the costThe weight of (2);
Figure BDA00025633354300000216
as a cost function of the longitudinal acceleration rate of each control point on the candidate curve,
Figure BDA00025633354300000217
is the weight of the cost function;
Figure BDA00025633354300000218
is the distance, w, between the point on the current trajectory and the corresponding point on the optimal trajectorylIs the weight of the cost function;
Figure BDA00025633354300000219
to run the time-consuming cost function along the candidate curve, wtIs the weight of the cost function.
Specifically, the candidate curve set is a fifth-order polynomial curve set generated by a control point.
In particular, the limiting conditions
Figure BDA00025633354300000220
Lmin≤le≤Lmax|d0|≤Wroad；|de|≤Wroad，C0In the initial position, CeIs the state of the target position, WroadIs the lane width, LminIs the maximum value of the length of the predetermined reference line in the longitudinal direction, LmaxIs the minimum value of the length of the predetermined reference line in the longitudinal direction, wherein d0、deRespectively representing the lateral coordinates of the initial position and the lateral coordinates of the end position of the vehicle in the vehicle coordinate system,
Figure BDA00025633354300000221
respectively representing the lateral component of the initial velocity and the lateral component of the final velocity of the vehicle in the vehicle coordinate system,
Figure BDA00025633354300000222
respectively representing the lateral component of the initial acceleration and the lateral component of the final acceleration of the vehicle in the vehicle coordinate system,/0、leRepresenting the longitudinal component of the initial position and the longitudinal component of the end position of the vehicle, respectively.
Specifically, in the third step, when collision detection is performed on a candidate curve, average sampling is performed on the candidate curve to obtain collision detection points, the distance between any two collision detection points is equal, the distance from each collision detection point to the geometric center of the obstacle is calculated, the minimum distance in the distances is found through a K-D tree data structure, and if the minimum distance is greater than or equal to a set safety threshold, the candidate curve is determined to pass the collision detection; otherwise, performing collision detection on other candidate curves of which the total cost function value is larger than the candidate curve.
Specifically, during speed planning, an ACC controller with an LQG control unit is adopted, the LQG control unit comprises an LQR control unit and a kalman filtering unit, the LQG control unit is used for calculating a wheel rotation angle, and the kalman filtering unit is used for filtering system noise and environmental noise.
A laterally separated trajectory planning system, comprising:
the trajectory generation module is used for generating a candidate curve set by utilizing a plurality of control points selected between an initial position and a target position when path planning is carried out; constructing a total cost function and a limiting condition, and calculating the value of the total cost function of each candidate curve;
the area dividing module is used for dividing an area between the initial position and the target position into a drivable area and an obstacle area according to the position of the obstacle;
and the collision detection module is used for sequentially carrying out collision detection on each candidate curve according to the sequence of the total cost function values from small to large when the vehicle runs along the curve with the lowest total cost function value in the candidate curves in the drivable area and enters the obstacle area, the first candidate curve passing through the collision detection is the optimal track, and the vehicle moves along the optimal track in the obstacle area.
A computer device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, performs the steps of the trajectory planning method.
Compared with the prior art, the invention has the beneficial technical effects that:
according to the method, the path planning is decoupled into the transverse position planning and the longitudinal speed planning, in the transverse path planning, the vehicle moves along the initial optimized track in the drivable area, and then collision detection is carried out after the vehicle enters the obstacle area, so that the calculated amount can be effectively reduced, and the real-time performance of the track planning is ensured.
Drawings
Fig. 1 is a schematic flow chart of the trajectory planning method of the present invention.
Detailed Description
A preferred embodiment of the present invention will be described in detail below with reference to the accompanying drawings.
Most of the trajectory planning methods in the prior art are set for robots, the calculation amount is large, the vehicle dynamics and kinematics are not limited, and the real-time performance is lacked.
As shown in fig. 1, a method for planning a track with a horizontal and vertical separation, which respectively plans a path and a speed of a vehicle between an initial position and a target position, includes the following steps:
s1: when path planning is carried out, a candidate curve set is generated by utilizing a plurality of control points selected between an initial position and a target position; and constructing a total cost function and a limiting condition, and calculating the value of the total cost function of each candidate curve.
Specifically, the candidate curve set is a fifth-order polynomial curve set generated by a control point.
In the field of unmanned driving, for the convenience of control, a cartesian coordinate system is no longer adopted, but a freset coordinate system is adopted under which directions are called lateral and longitudinal directions, and the distance between a vehicle and an obstacle or other vehicles is orthogonally decomposed into a lateral distance and a longitudinal distance.
S2: and dividing the area between the initial position and the target position into a travelable area and an obstacle area according to the position of the obstacle.
The obstacle can be detected in advance, the obstacle can be divided into obstacle areas within 20 meters, and other areas are drivable areas.
Under the condition of being far away from the obstacle, the sampling area is limited to be along the longitudinal direction of the candidate curve, and no obstacle exists, so that the transverse sampling is not needed, namely, the obstacle is not needed to be considered during path planning, so that a large amount of calculation amount caused by the transverse sampling is effectively reduced, when the obstacle exists, namely, when the obstacle is within 20 meters away from the obstacle, the transverse sampling is started, and the optimal curve for avoiding the obstacle is planned.
S3: and when the vehicle enters the obstacle region, sequentially carrying out collision detection on each candidate curve according to the sequence of the total cost function values from small to large, wherein the first candidate curve passing through the collision detection is the optimal track, and the vehicle moves along the optimal track in the obstacle region.
If collision detection is included when the total cost function is calculated, collision detection needs to be carried out on each candidate curve.
Specifically, in the step one, vehicle dynamics and kinematics limits, passenger comfort, vehicle safety and curve continuity are comprehensively considered when the total cost function is constructed.
In particular, the total cost function
Figure BDA0002563335430000041
Figure BDA0002563335430000042
Figure BDA0002563335430000051
Figure BDA0002563335430000052
Wherein the content of the first and second substances,
Figure BDA0002563335430000053
as a cost function of the distance between each two adjacent control points, wsIs the weight of the cost function;
Figure BDA0002563335430000054
as a cost function of the curvature of the candidate curve at each control point, wkIs the weight of the cost function;
Figure BDA0002563335430000055
as a cost function of the first derivative of the candidate curve at each control point,
Figure BDA0002563335430000056
is the weight of the cost function;
Figure BDA0002563335430000057
as a cost function of the second derivative of the candidate curve at each control point,
Figure BDA0002563335430000058
is the weight of the cost function;
Figure BDA0002563335430000059
as a cost function of the third derivative of the candidate curve at each control point,
Figure BDA00025633354300000510
is the weight of the cost function;
Figure BDA00025633354300000511
as a function of the cost of the lateral offset distance between each control point on the candidate curve and the predetermined reference line,
Figure BDA00025633354300000512
is the weight of the cost function;
Figure BDA00025633354300000513
as a cost function of the lateral acceleration of each control point on the candidate curve,
Figure BDA00025633354300000514
is the weight of the cost function;
Figure BDA00025633354300000515
as a cost function of the longitudinal acceleration at each control point on the candidate curve,
Figure BDA00025633354300000516
is the weight of the cost function;
Figure BDA00025633354300000517
as a cost function of the lateral acceleration change rate of each control point on the candidate curve,
Figure BDA00025633354300000518
is the weight of the cost function;
Figure BDA00025633354300000519
as a cost function of the longitudinal acceleration rate of each control point on the candidate curve,
Figure BDA00025633354300000520
is the weight of the cost function;
Figure BDA00025633354300000521
is the distance, w, between the point on the current trajectory and the corresponding point on the optimal trajectorylIs the weight of the cost function;
Figure BDA00025633354300000522
to run the time-consuming cost function along the candidate curve, wtIs the weight of the cost function.
The cost functions fully consider the influence of vehicle dynamics and kinematics limitation, passenger comfort, vehicle safety and curve continuity on path planning, for example, the first derivative, the second derivative and the third derivative of each control point on the candidate curve are calculated, so that the transition of the selected candidate curve is expected to be smoother, and the improvement of the passenger comfort is facilitated.
In particular, the constraint traj is defined as
Figure BDA00025633354300000523
Lmin≤le≤Lmax|d0|≤Wroad；|de|≤Wroad，C0In the initial position, CeIs the state of the target position, WroadIs the lane width, LminIs the maximum value of the length of the predetermined reference line in the longitudinal direction, LmaxIs the minimum value of the length of the predetermined reference line in the longitudinal direction, wherein d0、deRespectively representing the lateral coordinates of the initial position and the lateral coordinates of the end position of the vehicle in the vehicle coordinate system,
Figure BDA00025633354300000524
respectively representing the lateral component of the initial velocity and the lateral component of the final velocity of the vehicle in the vehicle coordinate system,
Figure BDA0002563335430000061
respectively representing the lateral component of the initial acceleration and the lateral component of the final acceleration of the vehicle in the vehicle coordinate system,/0、leRepresenting the longitudinal component of the initial position and the longitudinal component of the end position of the vehicle, respectively.
"symbol means" defined as ";
Figure BDA0002563335430000062
represents passing through the initial position and the target position, and satisfies C0And CeA plot of conditions.
Specifically, in the third step, when collision detection is performed on a candidate curve, average sampling is performed on the candidate curve to obtain collision detection points, the distance between any two collision detection points is equal, the distance from each collision detection point to the geometric center of the obstacle is calculated, the minimum distance in the distances is found through a K-D tree data structure, and if the minimum distance is greater than or equal to a set safety threshold, the candidate curve is determined to pass the collision detection; otherwise, performing collision detection on other candidate curves of which the total cost function value is larger than the candidate curve.
The K-D tree data structure is a data structure for dividing K-dimensional data space and is mainly applied to searching key data in multi-dimensional space
Specifically, during speed planning, an ACC controller with an LQG control unit is adopted, the LQG control unit comprises an LQR control unit and a kalman filtering unit, the LQG control unit is used for calculating a wheel rotation angle, and the kalman filtering unit is used for filtering system noise and environmental noise.
A laterally separated trajectory planning system, comprising:
the trajectory generation module is used for generating a candidate curve set by utilizing a plurality of control points selected between an initial position and a target position when path planning is carried out; constructing a total cost function and a limiting condition, and calculating the value of the total cost function of each candidate curve;
the area dividing module is used for dividing an area between the initial position and the target position into a drivable area and an obstacle area according to the position of the obstacle;
and the collision detection module is used for sequentially carrying out collision detection on each candidate curve according to the sequence of the total cost function values from small to large when the vehicle runs along the curve with the lowest total cost function value in the candidate curves in the drivable area and enters the obstacle area, the first candidate curve passing through the collision detection is the optimal track, and the vehicle moves along the optimal track in the obstacle area.
A computer device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, performs the steps of the trajectory planning method.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein, and any reference signs in the claims are not intended to be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.

Claims (7)

1. A method for planning a track with transverse and longitudinal separation is used for respectively planning a path and a speed of a vehicle between an initial position and a target position, and comprises the following steps:
the method comprises the following steps: when path planning is carried out, a candidate curve set is generated by utilizing a plurality of control points selected between an initial position and a target position; constructing a total cost function and a limiting condition, and calculating the value of the total cost function of each candidate curve;
step two: dividing an area between the initial position and the target position into a travelable area and an obstacle area according to the position of the obstacle;
step three: the vehicle runs along the curve with the lowest total cost function value in the candidate curves in the drivable area, and when the vehicle enters the obstacle area, collision detection is sequentially carried out on each candidate curve according to the sequence of the total cost function values from small to large, the first candidate curve passing through the collision detection is the optimal track, and the vehicle moves along the optimal track in the obstacle area;
in the first step, vehicle dynamics and kinematics limitation, passenger comfort, vehicle safety and curve continuity are comprehensively considered when a total cost function is constructed;
the total cost function
Figure FDA0003502043060000011
Figure FDA0003502043060000012
Wherein the content of the first and second substances,
Figure FDA0003502043060000013
as a cost function of the distance between each two adjacent control points, wsIs the weight of the cost function;
Figure FDA0003502043060000014
as a cost function of the curvature of the candidate curve at each control point, wkIs the weight of the cost function;
Figure FDA0003502043060000015
as a cost function of the first derivative of the candidate curve at each control point,
Figure FDA0003502043060000016
is the weight of the cost function;
Figure FDA0003502043060000017
as a cost function of the second derivative of the candidate curve at each control point,
Figure FDA0003502043060000018
is the weight of the cost function;
Figure FDA0003502043060000019
as a cost function of the third derivative of the candidate curve at each control point,
Figure FDA00035020430600000110
is the weight of the cost function;
Figure FDA00035020430600000111
as a function of the cost of the lateral offset distance between each control point on the candidate curve and the predetermined reference line,
Figure FDA00035020430600000112
is the weight of the cost function;
Figure FDA00035020430600000113
as a cost function of the lateral acceleration of each control point on the candidate curve,
Figure FDA00035020430600000114
is the weight of the cost function;
Figure FDA0003502043060000021
as a cost function of the longitudinal acceleration at each control point on the candidate curve,
Figure FDA0003502043060000022
is the weight of the cost function;
Figure FDA0003502043060000023
as a cost function of the lateral acceleration change rate of each control point on the candidate curve,
Figure FDA0003502043060000024
is the weight of the cost function;
Figure FDA0003502043060000025
as a cost function of the longitudinal acceleration rate of each control point on the candidate curve,
Figure FDA0003502043060000026
is the weight of the cost function;
Figure FDA0003502043060000027
is the distance, w, between the point on the current trajectory and the corresponding point on the optimal trajectorylIs the weight of the cost function;
Figure FDA0003502043060000028
to run the time-consuming cost function along the candidate curve, wtIs the weight of the cost function.
2. The method of claim 1, wherein: the candidate curve set is a fifth-order polynomial curve set generated by the control points.
3. The method of claim 1, wherein: the limiting condition
Figure FDA0003502043060000029
Lmin≤le≤Lmax|d0|≤Wroad；|de|≤Wroad，C0In the initial position, CeIs the state of the target position, WroadIs the lane width, LminIs the maximum value of the length of the predetermined reference line in the longitudinal direction, LmaxIs the minimum value of the length of the predetermined reference line in the longitudinal direction, wherein d0、deRespectively representing the lateral coordinates of the initial position and the lateral coordinates of the end position of the vehicle in the vehicle coordinate system,
Figure FDA00035020430600000210
respectively representing the lateral component of the initial velocity and the lateral component of the final velocity of the vehicle in the vehicle coordinate system,
Figure FDA00035020430600000211
respectively representing the lateral component of the initial acceleration and the lateral component of the final acceleration of the vehicle in the vehicle coordinate system,/0、leRepresenting the longitudinal component of the initial position and the longitudinal component of the end position of the vehicle, respectively.
4. The method of claim 1, wherein: in the third step, when the candidate curve is subjected to collision detection, the candidate curve is subjected to average sampling to obtain collision detection points, the distance between any two collision detection points is equal, the distance from each collision detection point to the geometric center of the obstacle is calculated, the minimum distance in the distances is searched through a K-D tree data structure, and if the minimum distance is greater than or equal to a set safety threshold value, the candidate curve is judged to pass the collision detection; otherwise, performing collision detection on other candidate curves of which the total cost function value is larger than the candidate curve.
5. The method of claim 1, wherein: when speed planning is carried out, an ACC controller with an LQG control unit is adopted, the LQG control unit comprises an LQR control unit and a Kalman filtering unit, the LQG control unit is used for calculating a wheel rotation angle, and the Kalman filtering unit is used for filtering system noise and environment noise.
6. A laterally separated trajectory planning system, comprising:
the trajectory generation module is used for generating a candidate curve set by utilizing a plurality of control points selected between an initial position and a target position when path planning is carried out; constructing a total cost function and a limiting condition, and calculating the value of the total cost function of each candidate curve;
the area dividing module is used for dividing an area between the initial position and the target position into a drivable area and an obstacle area according to the position of the obstacle;
the collision detection module is used for sequentially carrying out collision detection on each candidate curve according to the sequence of the total cost function values from small to large when the vehicle runs along the curve with the lowest total cost function value in the candidate curves in the drivable area and enters the obstacle area, the first candidate curve passing through the collision detection is an optimal track, and the vehicle moves along the optimal track in the obstacle area;
when a total cost function is constructed, vehicle dynamics and kinematics limitation, passenger comfort, vehicle safety and curve continuity are comprehensively considered;
the total cost function
Figure FDA0003502043060000031
Figure FDA0003502043060000032
Wherein the content of the first and second substances,
Figure FDA0003502043060000033
as a cost function of the distance between each two adjacent control points, wsIs the weight of the cost function;
Figure FDA0003502043060000034
as a cost function of the curvature of the candidate curve at each control point, wkIs the weight of the cost function;
Figure FDA0003502043060000035
as a cost function of the first derivative of the candidate curve at each control point,
Figure FDA0003502043060000036
is the weight of the cost function;
Figure FDA0003502043060000037
for the cost of the second derivative of the candidate curve at each control pointThe function of the function is that of the function,
Figure FDA0003502043060000038
is the weight of the cost function;
Figure FDA0003502043060000039
as a cost function of the third derivative of the candidate curve at each control point,
Figure FDA00035020430600000310
is the weight of the cost function;
Figure FDA00035020430600000311
as a function of the cost of the lateral offset distance between each control point on the candidate curve and the predetermined reference line,
Figure FDA00035020430600000312
is the weight of the cost function;
Figure FDA00035020430600000313
as a cost function of the lateral acceleration of each control point on the candidate curve,
Figure FDA00035020430600000314
is the weight of the cost function;
Figure FDA0003502043060000041
as a cost function of the longitudinal acceleration at each control point on the candidate curve,
Figure FDA0003502043060000042
is the weight of the cost function;
Figure FDA0003502043060000043
as a cost function of the lateral acceleration change rate of each control point on the candidate curve,
Figure FDA0003502043060000044
is the weight of the cost function;
Figure FDA0003502043060000045
as a cost function of the longitudinal acceleration rate of each control point on the candidate curve,
Figure FDA0003502043060000046
is the weight of the cost function;
Figure FDA0003502043060000047
is the distance, w, between the point on the current trajectory and the corresponding point on the optimal trajectorylIs the weight of the cost function;
Figure FDA0003502043060000048
to run the time-consuming cost function along the candidate curve, wtIs the weight of the cost function.
7. A computer arrangement, characterized by a memory and a processor, in which a computer program is stored which, when being executed by the processor, carries out the steps of the trajectory planning method according to any one of claims 1-5.
CN202010614679.9A 2020-06-30 2020-06-30 Track planning method and system for transverse and longitudinal separation and computer equipment Active CN111679678B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010614679.9A CN111679678B (en) 2020-06-30 2020-06-30 Track planning method and system for transverse and longitudinal separation and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010614679.9A CN111679678B (en) 2020-06-30 2020-06-30 Track planning method and system for transverse and longitudinal separation and computer equipment

Publications (2)

Publication Number Publication Date
CN111679678A CN111679678A (en) 2020-09-18
CN111679678B true CN111679678B (en) 2022-04-08

Family

ID=72437577

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010614679.9A Active CN111679678B (en) 2020-06-30 2020-06-30 Track planning method and system for transverse and longitudinal separation and computer equipment

Country Status (1)

Country Link
CN (1) CN111679678B (en)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111967374B (en) * 2020-08-14 2021-10-01 安徽海博智能科技有限责任公司 Mine obstacle identification method, system and equipment based on image processing
CN112729328B (en) * 2020-12-25 2023-01-31 际络科技(上海)有限公司 Fuel-saving driving track planning method and device, electronic equipment and storage medium
CN112783161B (en) * 2020-12-29 2023-04-25 广东嘉腾机器人自动化有限公司 AGV obstacle avoidance method based on Bezier curve
CN112677995B (en) * 2021-01-07 2021-12-21 腾讯科技（深圳）有限公司 Vehicle track planning method and device, storage medium and equipment
CN114103938A (en) * 2021-03-23 2022-03-01 京东鲲鹏(江苏)科技有限公司 Method, device and storage medium for controlling longitudinal movement of vehicle
CN113433936B (en) * 2021-06-02 2023-07-25 北京迈格威科技有限公司 Mobile equipment obstacle detouring method and device, mobile equipment and storage medium
CN113238565A (en) * 2021-06-16 2021-08-10 京东鲲鹏(江苏)科技有限公司 Vehicle path planning method and device, vehicle and storage medium
CN113370995B (en) * 2021-07-01 2024-01-09 广州小鹏自动驾驶科技有限公司 Processing method and device of speed curve, electric automobile and electronic equipment
CN115230731A (en) * 2021-09-13 2022-10-25 上海仙途智能科技有限公司 Travel route determination method, travel route determination device, travel route determination terminal, and travel route determination medium
CN115525047B (en) * 2022-03-21 2023-07-25 江苏集萃清联智控科技有限公司 Vehicle local track planning method and system with multi-type obstacle avoidance mode
CN116136417B (en) * 2023-04-14 2023-08-22 北京理工大学 Unmanned vehicle local path planning method facing off-road environment

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107145147B (en) * 2017-04-10 2020-12-15 广州小鹏汽车科技有限公司 Vehicle low-speed automatic driving collision avoidance method and system
US10549749B2 (en) * 2018-03-08 2020-02-04 Baidu Usa Llc Post collision analysis-based vehicle action optimization for autonomous driving vehicles
US11577755B2 (en) * 2018-07-27 2023-02-14 Embotech Ag Method for steering a vehicle and apparatus therefor
CN109557912B (en) * 2018-10-11 2020-07-28 同济大学 Decision planning method for automatically driving special operation vehicle
CN110341711B (en) * 2019-07-06 2021-10-22 深圳数翔科技有限公司 Traveling track generation system and method based on wharf environment
CN111289008B (en) * 2020-04-28 2021-04-13 南京维思科汽车科技有限公司 Local path planning method for unmanned vehicle

Also Published As

Publication number Publication date
CN111679678A (en) 2020-09-18

Similar Documents

Publication Publication Date Title
CN111679678B (en) Track planning method and system for transverse and longitudinal separation and computer equipment
CN110703762B (en) Hybrid path planning method for unmanned surface vehicle in complex environment
CN108569336B (en) Steering control method based on vehicle kinematic model under dynamic constraint
CN111830979B (en) Track optimization method and device
CN112810630B (en) Method and system for planning track of automatic driving vehicle
Liu et al. Real-time longitudinal and lateral state estimation of preceding vehicle based on moving horizon estimation
CN113895463B (en) Path planning method suitable for turning around of automatic driving vehicle
CN110979339A (en) Front road form reconstruction method based on V2V
CN114063615B (en) Reversing navigation control method and system of intelligent pesticide spraying vehicle among ridges in greenhouse
CN116118780A (en) Vehicle obstacle avoidance track planning method, system, vehicle and storage medium
CN113515111B (en) Vehicle obstacle avoidance path planning method and device
CN112327826A (en) Path planning method, device, equipment and medium
CN115900738A (en) Path planning method, device, vehicle and storage medium
US20220121213A1 (en) Hybrid planning method in autonomous vehicle and system thereof
CN113887276A (en) Image-based forward main target detection method
Park et al. Path generation algorithm based on crash point prediction for lane changing of autonomous vehicles
CN116136417B (en) Unmanned vehicle local path planning method facing off-road environment
CN113341999A (en) Forklift path planning method and device based on optimized D-x algorithm
CN111121804B (en) Intelligent vehicle path planning method and system with safety constraint
Feraco et al. A LIDAR-based clustering technique for obstacles and lane boundaries detection in assisted and autonomous driving
CN114537435B (en) Real-time whole vehicle track planning method in automatic driving
Feraco et al. Optimal trajectory generation using an improved probabilistic road map algorithm for autonomous driving
CN115303288A (en) Vehicle control method, control device and camera device
CN111176285B (en) Method and device for planning travel path, vehicle and readable storage medium
CN114084133B (en) Method and related device for determining following target

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
GR01 Patent grant
GR01 Patent grant