CN110262488B - Automatic driving local path planning method, system and computer readable storage medium - Google Patents
Automatic driving local path planning method, system and computer readable storage medium Download PDFInfo
- Publication number
- CN110262488B CN110262488B CN201910528047.8A CN201910528047A CN110262488B CN 110262488 B CN110262488 B CN 110262488B CN 201910528047 A CN201910528047 A CN 201910528047A CN 110262488 B CN110262488 B CN 110262488B
- Authority
- CN
- China
- Prior art keywords
- path
- curve
- obstacle
- evaluation function
- curves
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000005070 sampling Methods 0.000 claims abstract description 58
- 238000005457 optimization Methods 0.000 claims abstract description 28
- 230000010365 information processing Effects 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 93
- 238000011156 evaluation Methods 0.000 claims description 77
- 230000004888 barrier function Effects 0.000 claims description 30
- 230000008447 perception Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
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
- G05D1/02—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
-
- 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
- G05D1/0225—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving docking at a fixed facility, e.g. base station or loading bay
-
- 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- 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
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a local path planning method, a system and a computer readable storage medium for automatic driving, which comprises the following steps: the method comprises the following steps: A. and (3) information processing: generating a plurality of sampling points by taking the global path as a reference; B. path sampling: finding out a curve of a path to be selected, and entering path optimization; if no path curve to be selected exists, outputting a no-feasible path; C. path optimization: and optimizing the path to be selected to obtain an optimal local path curve. The invention can plan an optimal local path information and has high calculation efficiency.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to a local path planning method and system for automatic driving and a computer readable storage medium.
Background
With the development of artificial intelligence technology, multi-sensor fusion technology and control decision technology, the demand for automatically driving automobiles is more and more strong. The automatic driving automobile can be divided into four grades of L1 to L4 according to the use scene, technical capability and the like of the automatic driving automobile. Wherein conditional autonomous driving is below the L3 rating and full autonomous driving is at the L4 rating.
At present, research on automatic driving mainly focuses on several fields of environment perception and scene cognition, vehicle driving action decision, path planning and vehicle longitudinal and transverse automatic control. The path planning is divided into global path planning and local path planning. The automatic driving automobile plans a path from a starting point to a terminal point by utilizing a global path planning method according to the existing high-precision map. When the automatic driving automobile runs along the path, information of vehicles, pedestrians, obstacles and the like on the road is unknown in advance, at the moment, the information needs to be given by a sensing system, a reasonable path is planned by using a local path planning method in real time, and actions such as overtaking, following, bypassing and the like are finished so as to ensure the safe running of the vehicle.
The local path planning method adopted by the current automatic driving vehicle mostly refers to the local path planning method of a mobile robot, has a large difference with the motion characteristic of the vehicle, and has a large calculation amount for planning, so that the real-time local path planning requirement of the automatic driving vehicle when the automatic driving vehicle runs on a road is difficult to meet.
Therefore, there is a need to develop a new automatic driving local path planning method, system and computer readable storage medium.
Disclosure of Invention
The invention aims to provide an automatic driving local path planning method, an automatic driving local path planning system and a computer readable storage medium, which can plan an optimal local path information and have high calculation efficiency.
The invention relates to an automatic driving local path planning method, which comprises the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
b1, randomly generating a first path curve, wherein the generation method of the first path curve is as follows:
randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
b2, detecting whether the first path curve and the obstacle collide, and if so, entering the step B3; if no collision occurs, calculating an evaluation function value of the first path curve according to a preset evaluation function, and entering the step B3;
b3, judging whether the frequency of randomly generating the first path curve reaches a first preset frequency, if not, returning to the step B1, and if so, entering the step B4;
b4, if one or more first path curves and the obstacle cannot collide, taking the first path curve with the minimum evaluation function value as a candidate path curve, and performing path optimization; if all the first path curves collide with the barrier, outputting no feasible path;
C. path optimization:
c1, randomly generating a second path curve, wherein the generation method of the second path curve is as follows:
dispersing a curve of a path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted through a Bezier curve for three times to obtain a second path curve;
detecting whether the second path curve and the barrier collide, and if not, calculating an evaluation function value of the second path curve according to a preset evaluation function;
c2, judging whether the optimization times reach a second preset time, if not, returning to the step C1, and if so, entering the step C3;
and C3, taking the second path curve with the minimum evaluation function value as the optimal local path curve.
Further, the evaluation function is:
F=a*center +b*smooth +c*obstacle；
wherein center represents the distance deviating from the reference path, smooth represents the path smoothness, obstacle represents the distance from the obstacle, a is the weight of center, 0 & lt a & lt 1, b is the weight of smooth, 0 & lt b & lt 1, c is the weight of obstacle, and 0 & lt c & lt 1.
The invention relates to an automatic driving local path planning method, which comprises the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
randomly generating a first preset number of first path curves, respectively detecting whether the first path curves collide with the barrier, if the first path curves do not collide with the barrier, calculating an evaluation function value of the first path curves according to a preset evaluation function, and taking the first path curve with the minimum evaluation function value as a path curve to be selected; if all the first path curves collide with the barrier, outputting no feasible path;
the generation method of the first path curve comprises the following steps: randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
C. path optimization:
c1, randomly generating a second path curve, wherein the generation method of the second path curve is as follows:
dispersing a curve of a path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted through a Bezier curve for three times to obtain a second path curve;
detecting whether the second path curve and the barrier collide, and if not, calculating an evaluation function value of the second path curve according to a preset evaluation function;
c2, judging whether the optimization times reach a second preset time, if not, returning to the step C1, and if so, entering the step C3;
and C3, taking the second path curve with the minimum evaluation function value as the optimal local path curve.
Further, the evaluation function is:
F=a*center +b*smooth +c*obstacle；
wherein center represents the distance deviating from the reference path, smooth represents the path smoothness, obstacle represents the distance from the obstacle, a is the weight of center, 0 & lt a & lt 1, b is the weight of smooth, 0 & lt b & lt 1, c is the weight of obstacle, and 0 & lt c & lt 1.
The invention relates to an automatic driving local path planning method, which comprises the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
randomly generating a first preset number of first path curves, respectively detecting whether the first path curves collide with the barrier, if the first path curves do not collide with the barrier, calculating an evaluation function value of the first path curves according to a preset evaluation function, and taking the first path curve with the minimum evaluation function value as a path curve to be selected; if all the first path curves collide with the barrier, outputting no feasible path;
the generation method of the first path curve comprises the following steps: randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
C. path optimization:
randomly generating a second preset number of second path curves, respectively detecting whether the second path curves collide with the obstacles, if not, calculating an evaluation function value of the second path curves according to a preset evaluation function, and taking the second path curve with the minimum evaluation function value as an optimal local path curve;
the generation method of the second path curve comprises the following steps:
and dispersing the curve of the path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted by a Bezier curve for three times to obtain a second path curve.
Further, the evaluation function is:
F=a*center +b*smooth +c*obstacle；
wherein center represents the distance deviating from the reference path, smooth represents the path smoothness, obstacle represents the distance from the obstacle, a is the weight of center, 0 & lt a & lt 1, b is the weight of smooth, 0 & lt b & lt 1, c is the weight of obstacle, and 0 & lt c & lt 1.
The invention relates to an automatic driving local path planning method, which comprises the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
b1, randomly generating a first path curve, wherein the generation method of the first path curve is as follows:
randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
b2, detecting whether the first path curve and the obstacle collide, and if so, entering the step B3; if no collision occurs, calculating an evaluation function value of the first path curve according to a preset evaluation function, and entering the step B3;
b3, judging whether the frequency of randomly generating the first path curve reaches a first preset frequency, if not, returning to the step B1, and if so, entering the step B4;
b4, if one or more first path curves and the obstacle cannot collide, taking the first path curve with the minimum evaluation function value as a candidate path curve, and performing path optimization; if all the first path curves collide with the barrier, outputting no feasible path;
C. path optimization:
randomly generating a second preset number of second path curves, respectively detecting whether the second path curves collide with the obstacles, if not, calculating an evaluation function value of the second path curves according to a preset evaluation function, and taking the second path curve with the minimum evaluation function value as an optimal local path curve;
the generation method of the second path curve comprises the following steps:
and dispersing the curve of the path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted by a Bezier curve for three times to obtain a second path curve.
Further, the evaluation function is:
F=a*center +b*smooth +c*obstacle；
wherein center represents the distance deviating from the reference path, smooth represents the path smoothness, obstacle represents the distance from the obstacle, a is the weight of center, 0 & lt a & lt 1, b is the weight of smooth, 0 & lt b & lt 1, c is the weight of obstacle, and 0 & lt c & lt 1.
The invention relates to an automatic driving local path planning system, which comprises:
the sensing system is used for outputting position information and speed information of vehicles, pedestrians and obstacles on a road in real time;
the global path planning system is used for outputting a global path of the current vehicle in real time;
the controller is used for receiving information output by the perception system and the global path planning system, and is respectively connected with the perception system and the global path planning system:
the controller is programmed to perform the steps of the method of local path planning for autonomous driving according to the invention.
A computer-readable storage medium according to the present invention has stored therein a computer program, the computer program storing steps that are invoked by a controller to perform a method of local path planning for autopilot according to the present invention.
The invention has the following advantages:
(1) and an optimal local path is planned in real time by combining the information such as the positions and the speeds of the vehicles, pedestrians, obstacles and the like on the road, which is given by a sensing system at the current driving moment of the vehicles, so that the actions such as overtaking, following, bypassing, braking and the like can be completed.
(2) Due to the adoption of the random sampling and quadratic optimization method, an optimal local path curve can be obtained by using fewer path curve fitting times, and the calculation efficiency is improved.
Drawings
Fig. 1 is a schematic diagram of path sampling and path optimization of the present invention.
FIG. 2 is a logic flow diagram of a first embodiment of the present invention;
FIG. 3 is a logic flow diagram of a second embodiment of the present invention;
FIG. 4 is a logic flow diagram of a third embodiment of the present invention;
FIG. 5 is a logic flow diagram of a fourth embodiment of the present invention.
Detailed Description
The invention will be further explained with reference to the drawings.
Example one
As shown in fig. 2, in this embodiment, the method for planning the local path of the automatic driving includes the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle (such as the H rectangle in figure 1) output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle (the A rectangle indicated by the solid line in figure 1) on the road. And acquiring a global path (such as an Lr curve in FIG. 1) of the current vehicle, which is output by the global path planning system in real time.
(a) The system processes the received obstacle information, filters out large or small targets, and expands the obstacle outline to obtain a dotted line frame outside the rectangle A in FIG. 1;
(b) the system carries out reference path processing on the global path information and extracts path points at a plurality of distances in the advancing direction of the current vehicle position, the width of the left side and the right side of a road and other information;
(c) and (c) screening the obstacles according to the obstacles, the path points and the width information of the left and right sides of the road obtained in the step (a) and the step (b), namely filtering the obstacles outside the driving area.
A2, taking a global path as a reference, firstly, equally spacing along the longitudinal direction (the general calculation formula of the lookaheadDist of the spacing distance is that: lookaheadDist = VelSpeed LADTime, wherein VelSpeed is the current vehicle speed, the unit is m/s, LADTime is the preview time, the value is generally 1.5-2.0, the longitudinal distance (the direction of the vehicle running along the path) is determined, and then, according to the determined longitudinal distance, equally spacing (generally 3-4 equal spacing) along the transverse direction (the offset direction of the vehicle and the center of the path) is generated into a plurality of sampling points (such as the points along the Lr transverse direction in the figure 1);
B. path sampling:
b1, randomly generating a first path curve (such as L1 and L2 in FIG. 1), wherein the generation method of the first path curve is as follows:
randomly extracting a preset number of sampling points from the generated sampling points by using an equiprobable random function, wherein the preset number N of the sampling points in each transverse sampling set has a calculation formula of N = LaneWidth/SampleWidth, wherein LaneWidth is the width of a passable area of a road (generally the width of the left side and the right side of the road), and SampleWidth is a sampling interval distance (generally 0.2 m-0.7 m), so that the probability f of selecting any sampling point can be obtained by the calculation formula of f =1/N, combining the selected sampling points in each transverse sampling set, and obtaining a first path curve through cubic Bezier curve fitting;
b2, detecting whether the first path curve and the obstacle collide, and if so, entering the step B3; if no collision occurs, calculating an evaluation function value of the first path curve according to a preset evaluation function, and entering the step B3;
b3, judging whether the frequency of randomly generating the first path curve reaches a first preset frequency (generally 5-20 times), if not, returning to the step B1, and if so, entering the step B4;
b4, if there is one or more first path curves and the obstacle will not collide, taking the first path curve with the minimum evaluation function value as the candidate path curve (such as Ls curve in fig. 1), and entering path optimization; if all the first path curves collide with the barrier, outputting no feasible path;
C. path optimization:
c1, randomly generating a second path curve, wherein the generation method of the second path curve is as follows:
dispersing the curve of the path to be selected into a plurality of points, randomly selecting one point or more than one point to shift in the transverse direction, and if more than one point is randomly selected to shift in the transverse direction, the transverse shift distances of the points can be the same or different; fitting the shifted points and the non-shifted points through a Bezier curve for three times to obtain a second path curve;
detecting whether the second path curve and the barrier collide, and if not, calculating an evaluation function value of the second path curve according to a preset evaluation function;
c2, judging whether the optimization times reach a second preset time, if not, returning to the step C1, and if so, entering the step C3;
and C3, taking the second path curve with the minimum evaluation function value as an optimal local path curve (such as the Ld curve in figure 1).
In this embodiment, the evaluation function is:
F=a*center +b*smooth +c*obstacle；
wherein center represents the distance deviating from the reference path, smooth represents the path smoothness, obstacle represents the distance from the obstacle, a is the weight of center, 0 & lt a & lt 1, b is the weight of smooth, 0 & lt b & lt 1, c is the weight of obstacle, and 0 & lt c & lt 1.
And planning the speed according to the local path information, calculating the curvature of each point on the local path, planning the reference speed of each point on the local path according to the curvature and the current speed of the vehicle, and adding the reference speed to the local path information for outputting together.
The invention relates to an automatic driving local path planning system which comprises a sensing system, a global path planning system and a controller, wherein the sensing system is used for outputting position information and speed information of vehicles, pedestrians and obstacles on a road in real time; the global path planning system is used for outputting a global path of the current vehicle in real time; the controller is used for receiving information output by the perception system and the global path planning system, and is respectively connected with the perception system and the global path planning system. The controller is programmed to perform the steps of the method of local path planning for autonomous driving according to the invention.
In this embodiment, the sensing system includes lidar (four in total, one mounted in the center of the front bumper and facing forward, two mounted below the left and right reflectors and facing left and right, and one mounted in the center of the rear bumper and facing rearward), millimeter wave radar (one mounted below the center of the front grille and facing forward), cameras (four in total, one mounted at the front windshield mirror and facing forward, two mounted below the left and right reflectors and facing left and right, and one mounted near the trunk switch and facing rearward), and a differential GPS receiver (receiving dual antenna mounted on the roof).
A computer-readable storage medium according to the present invention has stored therein a computer program, the computer program storing steps that are invoked by a controller to perform a method of local path planning for autopilot according to the present invention.
Example two
As shown in fig. 3, in this embodiment, the method for planning the local path of the automatic driving includes the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
randomly generating a first preset number of first path curves, respectively detecting whether the first path curves collide with the barrier, if the first path curves do not collide with the barrier, calculating an evaluation function value of the first path curves according to a preset evaluation function, and taking the first path curve with the minimum evaluation function value as a path curve to be selected; if all the first path curves collide with the barrier, outputting no feasible path;
the generation method of the first path curve comprises the following steps: randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
C. path optimization:
c1, randomly generating a second path curve, wherein the generation method of the second path curve is as follows:
dispersing a curve of a path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted through a Bezier curve for three times to obtain a second path curve;
detecting whether the second path curve and the barrier collide, and if not, calculating an evaluation function value of the second path curve according to a preset evaluation function;
c2, judging whether the optimization times reach a second preset time, if not, returning to the step C1, and if so, entering the step C3;
and C3, taking the second path curve with the minimum evaluation function value as the optimal local path curve.
The rest is the same as the first embodiment.
EXAMPLE III
As shown in fig. 4, in this embodiment, the method for planning the local path of the automatic driving includes the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
randomly generating a first preset number of first path curves, respectively detecting whether the first path curves collide with the barrier, if the first path curves do not collide with the barrier, calculating an evaluation function value of the first path curves according to a preset evaluation function, and taking the first path curve with the minimum evaluation function value as a path curve to be selected; if all the first path curves collide with the barrier, outputting no feasible path;
the generation method of the first path curve comprises the following steps: randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
C. path optimization:
randomly generating a second preset number of second path curves, respectively detecting whether the second path curves collide with the obstacles, if not, calculating an evaluation function value of the second path curves according to a preset evaluation function, and taking the second path curve with the minimum evaluation function value as an optimal local path curve;
the generation method of the second path curve comprises the following steps:
and dispersing the curve of the path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted by a Bezier curve for three times to obtain a second path curve.
The rest is the same as the first embodiment.
Example four
As shown in fig. 5, in this embodiment, the method for planning the local path of the automatic driving includes the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
b1, randomly generating a first path curve, wherein the generation method of the first path curve is as follows:
randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
b2, detecting whether the first path curve and the obstacle collide, and if so, entering the step B3; if no collision occurs, calculating an evaluation function value of the first path curve according to a preset evaluation function, and entering the step B3;
b3, judging whether the frequency of randomly generating the first path curve reaches a first preset frequency, if not, returning to the step B1, and if so, entering the step B4;
b4, if one or more first path curves and the obstacle cannot collide, taking the first path curve with the minimum evaluation function value as a candidate path curve, and performing path optimization; if all the first path curves collide with the barrier, outputting no feasible path;
C. path optimization:
randomly generating a second preset number of second path curves, respectively detecting whether the second path curves collide with the obstacles, if not, calculating an evaluation function value of the second path curves according to a preset evaluation function, and taking the second path curve with the minimum evaluation function value as an optimal local path curve;
the generation method of the second path curve comprises the following steps:
and dispersing the curve of the path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted by a Bezier curve for three times to obtain a second path curve.
The rest is the same as the first embodiment.
Claims (10)
1. An automatic driving local path planning method is characterized by comprising the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
b1, randomly generating a first path curve, wherein the generation method of the first path curve is as follows:
randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
b2, detecting whether the first path curve and the obstacle collide, and if so, entering the step B3; if no collision occurs, calculating an evaluation function value of the first path curve according to a preset evaluation function, and entering the step B3;
b3, judging whether the frequency of randomly generating the first path curve reaches a first preset frequency, if not, returning to the step B1, and if so, entering the step B4;
b4, if one or more first path curves and the obstacle cannot collide, taking the first path curve with the minimum evaluation function value as a candidate path curve, and performing path optimization; if all the first path curves collide with the barrier, outputting no feasible path;
C. path optimization:
c1, randomly generating a second path curve, wherein the generation method of the second path curve is as follows:
dispersing a curve of a path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted through a Bezier curve for three times to obtain a second path curve;
detecting whether the second path curve and the barrier collide, and if not, calculating an evaluation function value of the second path curve according to a preset evaluation function;
c2, judging whether the optimization times reach a second preset time, if not, returning to the step C1, and if so, entering the step C3;
and C3, taking the second path curve with the minimum evaluation function value as the optimal local path curve.
2. The autonomous driving local path planning method according to claim 1, characterized in that: the merit function is:
F=a*center +b*smooth +c*obstacle；
wherein center represents the distance deviating from the reference path, smooth represents the path smoothness, obstacle represents the distance from the obstacle, a is the weight of center, 0 & lt a & lt 1, b is the weight of smooth, 0 & lt b & lt 1, c is the weight of obstacle, and 0 & lt c & lt 1.
3. An automatic driving local path planning method is characterized by comprising the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
randomly generating a first preset number of first path curves, respectively detecting whether the first path curves collide with the barrier, if the first path curves do not collide with the barrier, calculating an evaluation function value of the first path curves according to a preset evaluation function, and taking the first path curve with the minimum evaluation function value as a path curve to be selected; if all the first path curves collide with the barrier, outputting no feasible path;
the generation method of the first path curve comprises the following steps: randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
C. path optimization:
c1, randomly generating a second path curve, wherein the generation method of the second path curve is as follows:
dispersing a curve of a path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted through a Bezier curve for three times to obtain a second path curve;
detecting whether the second path curve and the barrier collide, if not, calculating an evaluation function value of the second path curve according to a preset evaluation function,
c2, judging whether the optimization times reach a second preset time, if not, returning to the step C1, and if so, entering the step C3;
and C3, taking the second path curve with the minimum evaluation function value as the optimal local path curve.
4. The autonomous-driven local path planning method according to claim 3, characterized in that: the merit function is:
F=a*center +b*smooth +c*obstacle；
wherein center represents the distance deviating from the reference path, smooth represents the path smoothness, obstacle represents the distance from the obstacle, a is the weight of center, 0 & lt a & lt 1, b is the weight of smooth, 0 & lt b & lt 1, c is the weight of obstacle, and 0 & lt c & lt 1.
5. An automatic driving local path planning method is characterized by comprising the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
randomly generating a first preset number of first path curves, respectively detecting whether the first path curves collide with the barrier, if the first path curves do not collide with the barrier, calculating an evaluation function value of the first path curves according to a preset evaluation function, and taking the first path curve with the minimum evaluation function value as a path curve to be selected; if all the first path curves collide with the barrier, outputting no feasible path;
the generation method of the first path curve comprises the following steps: randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
C. path optimization:
randomly generating a second preset number of second path curves, respectively detecting whether the second path curves collide with the obstacles, if not, calculating an evaluation function value of the second path curves according to a preset evaluation function, and taking the second path curve with the minimum evaluation function value as an optimal local path curve;
the generation method of the second path curve comprises the following steps:
and dispersing the curve of the path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted by a Bezier curve for three times to obtain a second path curve.
6. The autonomous-driven local path planning method according to claim 5, characterized in that: the merit function is:
F=a*center +b*smooth +c*obstacle；
wherein center represents the distance deviating from the reference path, smooth represents the path smoothness, obstacle represents the distance from the obstacle, a is the weight of center, 0 & lt a & lt 1, b is the weight of smooth, 0 & lt b & lt 1, c is the weight of obstacle, and 0 & lt c & lt 1.
7. An automatic driving local path planning method is characterized by comprising the following steps:
A. and (3) information processing:
a1, acquiring the current position information and speed information of the vehicle output by the sensing system in real time, and the position information and speed information of the vehicle, the pedestrian and the obstacle on the road; acquiring a global path of a current vehicle output by a global path planning system in real time;
a2, taking the global path as a reference, determining longitudinal distances at equal intervals along the longitudinal direction, and generating a plurality of sampling points at equal intervals along the transverse direction according to the determined longitudinal distances;
B. path sampling:
b1, randomly generating a first path curve, wherein the generation method of the first path curve is as follows:
randomly extracting a preset number of sampling points from the generated sampling points by using an equal probability random function, and obtaining a first path curve through three times of Bezier curve fitting;
b2, detecting whether the first path curve and the obstacle collide, and if so, entering the step B3; if no collision occurs, calculating an evaluation function value of the first path curve according to a preset evaluation function, and entering the step B3;
b3, judging whether the frequency of randomly generating the first path curve reaches a first preset frequency, if not, returning to the step B1, and if so, entering the step B4;
b4, if one or more first path curves and the obstacle cannot collide, taking the first path curve with the minimum evaluation function value as a candidate path curve, and performing path optimization; if all the first path curves collide with the barrier, outputting no feasible path;
C. path optimization:
randomly generating a second preset number of second path curves, respectively detecting whether the second path curves collide with the obstacles, if not, calculating an evaluation function value of the second path curves according to a preset evaluation function, and taking the second path curve with the minimum evaluation function value as an optimal local path curve;
the generation method of the second path curve comprises the following steps:
and dispersing the curve of the path to be selected into a plurality of points, randomly selecting one point or more than one point from the plurality of points to shift in the transverse direction, and fitting the shifted point and the point which is not shifted by a Bezier curve for three times to obtain a second path curve.
8. The autonomous-driven local path planning method of claim 7, wherein: the merit function is:
F=a*center +b*smooth +c*obstacle；
wherein center represents the distance deviating from the reference path, smooth represents the path smoothness, obstacle represents the distance from the obstacle, a is the weight of center, 0 & lt a & lt 1, b is the weight of smooth, 0 & lt b & lt 1, c is the weight of obstacle, and 0 & lt c & lt 1.
9. An autonomous local path planning system comprising:
the sensing system is used for outputting position information and speed information of vehicles, pedestrians and obstacles on a road in real time;
the global path planning system is used for outputting a global path of the current vehicle in real time;
the controller is used for receiving information output by the perception system and the global path planning system, and is respectively connected with the perception system and the global path planning system:
the method is characterized in that: the controller is programmed to perform the steps of the autonomous driving local path planning method according to any of claims 1 to 8.
10. A computer-readable storage medium having stored therein a computer program, characterized in that: the computer stores steps that are invoked by the controller to perform the method of automatically driven local path planning according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910528047.8A CN110262488B (en) | 2019-06-18 | 2019-06-18 | Automatic driving local path planning method, system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910528047.8A CN110262488B (en) | 2019-06-18 | 2019-06-18 | Automatic driving local path planning method, system and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110262488A CN110262488A (en) | 2019-09-20 |
| CN110262488B true CN110262488B (en) | 2021-11-30 |
Family
ID=67919124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910528047.8A Active CN110262488B (en) | 2019-06-18 | 2019-06-18 | Automatic driving local path planning method, system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110262488B (en) |
Families Citing this family (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112783144B (en) * | 2019-10-22 | 2023-09-29 | 舜宇光学（浙江）研究院有限公司 | Path generation method, path planning method, system and equipment thereof |
| CN111006667B (en) * | 2019-12-09 | 2021-07-06 | 东风商用车有限公司 | Automatic driving track generation system under high-speed scene |
| CN111123952B (en) * | 2019-12-31 | 2021-12-31 | 华为技术有限公司 | Trajectory planning method and device |
| CN111288995B (en) * | 2020-03-12 | 2022-05-13 | 深圳市人工智能与机器人研究院 | Route planning method and route planning device of mobile robot and terminal equipment |
| CN111475573B (en) * | 2020-04-08 | 2023-02-28 | 腾讯科技（深圳）有限公司 | Data synchronization method and device, electronic equipment and storage medium |
| CN111539345B (en) * | 2020-04-27 | 2023-09-26 | 阿波罗智能技术(北京)有限公司 | Method, apparatus, device and readable storage medium for determining track changing action |
| CN111737636B (en) * | 2020-06-12 | 2024-02-02 | 北京百度网讯科技有限公司 | Path curve generation method, device, computer equipment and storage medium |
| CN112179368B (en) * | 2020-09-27 | 2022-12-13 | 广州小鹏自动驾驶科技有限公司 | Path data processing method and device, vehicle and readable medium |
| CN114593742B (en) * | 2020-12-04 | 2024-04-19 | 上海汽车集团股份有限公司 | Local path planning method, device and equipment for intelligent driving vehicle |
| CN112918486B (en) * | 2021-02-08 | 2022-06-03 | 北京理工大学 | Space-time behavior decision and trajectory planning system and method |
| CN113050627A (en) * | 2021-03-02 | 2021-06-29 | 北京旷视机器人技术有限公司 | Path planning method and device, mobile robot and computer storage medium |
| CN112964271B (en) * | 2021-03-15 | 2023-03-31 | 西安交通大学 | Multi-scene-oriented automatic driving planning method and system |
| CN113091750B (en) * | 2021-04-12 | 2023-04-07 | 京东科技信息技术有限公司 | Local path planning method, device, computer equipment and storage medium |
| CN113483775B (en) * | 2021-06-30 | 2024-06-14 | 上海商汤临港智能科技有限公司 | Path prediction method and device, electronic equipment and computer readable storage medium |
| CN113721608A (en) * | 2021-08-16 | 2021-11-30 | 河南牧原智能科技有限公司 | Robot local path planning method and system and readable storage medium |
| CN113778102B (en) * | 2021-09-22 | 2023-05-12 | 重庆长安汽车股份有限公司 | AVP global path planning system, method, vehicle and storage medium |
| CN114248761B (en) * | 2021-12-10 | 2024-06-04 | 重庆长安汽车股份有限公司 | Target track discretization method, parking path tracking error optimization method and system |
| CN114995421B (en) * | 2022-05-31 | 2024-06-18 | 重庆长安汽车股份有限公司 | Automatic driving obstacle avoidance method, device, electronic equipment, storage medium and program product |
| CN115230694A (en) * | 2022-09-20 | 2022-10-25 | 毫末智行科技有限公司 | Obstacle recognition method and device for automatic driving vehicle and vehicle |
| CN116013074A (en) * | 2023-01-05 | 2023-04-25 | 北京清丰智行科技有限公司 | Intelligent travel system based on car Lu Yun cooperation in park |
| CN116061975B (en) * | 2023-04-04 | 2023-06-16 | 北京集度科技有限公司 | Vehicle controller, vehicle and vehicle control method |
| CN116136417B (en) * | 2023-04-14 | 2023-08-22 | 北京理工大学 | Unmanned vehicle local path planning method facing off-road environment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106114507A (en) * | 2016-06-21 | 2016-11-16 | 百度在线网络技术（北京）有限公司 | Local path planning method and device for intelligent vehicle |
| CN106598055A (en) * | 2017-01-19 | 2017-04-26 | 北京智行者科技有限公司 | Intelligent vehicle local path planning method, device thereof, and vehicle |
| CN107608344A (en) * | 2017-08-21 | 2018-01-19 | 上海蔚来汽车有限公司 | Vehicle motion control method, apparatus and relevant device based on trajectory planning |
| CN107992050A (en) * | 2017-12-20 | 2018-05-04 | 广州汽车集团股份有限公司 | Pilotless automobile local path motion planning method and device |
| CN108088456A (en) * | 2017-12-21 | 2018-05-29 | 北京工业大学 | A kind of automatic driving vehicle local paths planning method with time consistency |
| CN108445885A (en) * | 2018-04-20 | 2018-08-24 | 鹤山东风新能源科技有限公司 | A kind of automated driving system and its control method based on pure electric vehicle logistic car |
| CN109253735A (en) * | 2018-11-30 | 2019-01-22 | 奇瑞汽车股份有限公司 | Paths planning method, device and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101795250B1 (en) * | 2016-05-03 | 2017-11-07 | 현대자동차주식회사 | Path planning apparatus and method for autonomous vehicle |
-
2019
- 2019-06-18 CN CN201910528047.8A patent/CN110262488B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106114507A (en) * | 2016-06-21 | 2016-11-16 | 百度在线网络技术（北京）有限公司 | Local path planning method and device for intelligent vehicle |
| CN106598055A (en) * | 2017-01-19 | 2017-04-26 | 北京智行者科技有限公司 | Intelligent vehicle local path planning method, device thereof, and vehicle |
| CN107608344A (en) * | 2017-08-21 | 2018-01-19 | 上海蔚来汽车有限公司 | Vehicle motion control method, apparatus and relevant device based on trajectory planning |
| CN107992050A (en) * | 2017-12-20 | 2018-05-04 | 广州汽车集团股份有限公司 | Pilotless automobile local path motion planning method and device |
| CN108088456A (en) * | 2017-12-21 | 2018-05-29 | 北京工业大学 | A kind of automatic driving vehicle local paths planning method with time consistency |
| CN108445885A (en) * | 2018-04-20 | 2018-08-24 | 鹤山东风新能源科技有限公司 | A kind of automated driving system and its control method based on pure electric vehicle logistic car |
| CN109253735A (en) * | 2018-11-30 | 2019-01-22 | 奇瑞汽车股份有限公司 | Paths planning method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110262488A (en) | 2019-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262488B (en) | Automatic driving local path planning method, system and computer readable storage medium | |
| US12005904B2 (en) | Autonomous driving system | |
| US11155258B2 (en) | System and method for radar cross traffic tracking and maneuver risk estimation | |
| US10688991B2 (en) | Systems and methods for unprotected maneuver mitigation in autonomous vehicles | |
| CN107848531B (en) | Vehicle control device, vehicle control method, and medium storing vehicle control program | |
| Darms et al. | Obstacle detection and tracking for the urban challenge | |
| US20180074506A1 (en) | Systems and methods for mapping roadway-interfering objects in autonomous vehicles | |
| CN101622156B (en) | Perimeter monitor | |
| CN113490863A (en) | Radar-assisted three-dimensional depth reconstruction of a single image | |
| US20190339393A1 (en) | Method and apparatus crosstalk and multipath noise reduction in a lidar system | |
| US11433897B2 (en) | Method and apparatus for determination of optimal cruising lane in an assisted driving system | |
| US10162357B2 (en) | Distributed computing among vehicles | |
| Moras et al. | A lidar perception scheme for intelligent vehicle navigation | |
| CN111699404A (en) | Driving auxiliary target acquisition method and device, radar, driving system and vehicle | |
| CN112660128A (en) | Apparatus for determining lane change path of autonomous vehicle and method thereof | |
| CN115775378A (en) | Vehicle-road cooperative target detection method based on multi-sensor fusion | |
| CN112506177A (en) | Behavior control apparatus and behavior control method for autonomous vehicle | |
| CN111650934A (en) | Method for planning local path of automatic driving system | |
| US20220414386A1 (en) | Method for detecting lane line using lidar sensor and lane detection device for performing the method | |
| JP2019094880A (en) | Vehicle control device, vehicle control method, and program | |
| CN115359332A (en) | Data fusion method and device based on vehicle-road cooperation, electronic equipment and system | |
| CN114954442A (en) | Vehicle control method and system and vehicle | |
| JP7291015B2 (en) | Surrounding object recognition method and surrounding object recognition device | |
| Sathiyan et al. | A comprehensive review on cruise control for intelligent vehicles | |
| TWI841695B (en) | Method, on-board computer and non-transitory computer-readable medium for radar-aided single image three-dimensional depth reconstruction |
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 |