CN110262488A - Local paths planning method, system and the computer readable storage medium of automatic Pilot - Google Patents
Local paths planning method, system and the computer readable storage medium of automatic Pilot Download PDFInfo
- Publication number
- CN110262488A CN110262488A CN201910528047.8A CN201910528047A CN110262488A CN 110262488 A CN110262488 A CN 110262488A CN 201910528047 A CN201910528047 A CN 201910528047A CN 110262488 A CN110262488 A CN 110262488A
- Authority
- CN
- China
- Prior art keywords
- path
- path curve
- curve
- barrier
- evaluation function
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000005457 optimization Methods 0.000 claims abstract description 15
- 230000010365 information processing Effects 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 93
- 230000004888 barrier function Effects 0.000 claims description 84
- 238000011156 evaluation Methods 0.000 claims description 81
- 230000001953 sensory effect Effects 0.000 claims description 23
- 239000000284 extract Substances 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 235000015170 shellfish Nutrition 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 2
- 238000005070 sampling Methods 0.000 description 5
- 238000004364 calculation method Methods 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
- 238000010586 diagram Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- VIKNJXKGJWUCNN-XGXHKTLJSA-N norethisterone Chemical compound O=C1CC[C@@H]2[C@H]3CC[C@](C)([C@](CC4)(O)C#C)[C@@H]4[C@@H]3CCC2=C1 VIKNJXKGJWUCNN-XGXHKTLJSA-N 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—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
Abstract
The invention discloses a kind of local paths planning method of automatic Pilot, system and computer readable storage mediums, comprising the following steps: the following steps are included: A, information processing: on the basis of global path, generating several sampled points；B, path samples: finding out path curve to be selected, and access path optimizes；If exporting without path curve to be selected without feasible path；C, path optimization: treating routing diametal curve and optimize, and obtains optimal local path curve.The present invention can cook up an optimal local path information, and computational efficiency is high.
Description
Technical field
The invention belongs to automatic Pilot technical fields, and in particular to a kind of local paths planning method of automatic Pilot is
System and computer readable storage medium.
Background technique
With the development of artificial intelligence technology, multi-sensor fusion technology and control decision technology, for automatic Pilot
The demand of automobile is also more more and more intense.According to the usage scenario of autonomous driving vehicle, technical capability etc., L1 to L4 four can be divided into
A grade.Wherein for L3 grade the following are automatic Pilot of having ready conditions, L4 grade is complete automatic Pilot.
Currently, being concentrated mainly on environment sensing and scene cognition to the research of automatic Pilot, vehicle driving acts decision, road
Diameter planning, longitudinal direction of car and the laterally several fields of automatic control.Wherein, path planning is divided into global path planning and local path
Planning.Autonomous driving vehicle according to existing high-precision map use global path planning method, cook up one from starting point to
The path of terminal.Autonomous driving vehicle along this paths when driving, the information thing such as road vehicle, pedestrian, barrier
It is unknown before this, it needs to be provided by sensory perceptual system at this time, and cook up one reasonably using local paths planning method in real time
Path is gone to complete the movement such as overtake other vehicles, follow, detouring, to guarantee the safety traffic of vehicle.
Local paths planning method used by current automatic driving vehicle is mostly with reference to mobile robot local path
Planing method, there are larger gaps with the kinetic characteristic of vehicle, while the calculation amount planned is also larger, it is difficult to meet automatic Pilot
Real-time local paths planning demand of the vehicle on road when driving.
Therefore, it is necessary to develop a kind of local paths planning method of new automatic Pilot, system and computer-readable deposit
Storage media.
Summary of the invention
The object of the present invention is to provide a kind of local paths planning method of automatic Pilot, system and computer-readable storages
Medium can cook up an optimal local path information, and computational efficiency is high.
A kind of local paths planning method of automatic Pilot of the present invention, comprising the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
B1, a first path curve, the generation method of the first path curve are generated at random are as follows:
The sampled point of predetermined number is randomly selected from sampled point generated using equiprobability random function, and passes through shellfish three times
Sai Er curve matching obtains first path curve；
Whether can collide between B2, detection first path curve and barrier, if can collide, enter step B3；
If will not collide, the evaluation function value of the first path curve is calculated according to evaluation function is preset, and enter step B3；
Whether B3, the random number for generating first path curve of judgement reach the first preset times, if not up to, return step
B1 enters step B4 if reaching；
If B4, having and will not collide between one or one or more first path curve and barrier, by evaluation function
It is worth the smallest first path curve as path curve to be selected, and access path optimizes；If all first path curves can be with
It collides between barrier, then output is without feasible path；
C, path optimization:
C1, second path curve, the generation method of second path curve are generated at random are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve；
Whether second path curve and barrier between can collide, if will not collide, according to default evaluation if detecting
Function calculates the evaluation function value of the second path curve；
C2, judge to optimize whether number reaches the second preset times, if not up to, return step C1 is entered step if reaching
C3；
C3, using the smallest second path curve of evaluation function value as optimal local path curve.
Further, the evaluation function are as follows:
F=a*center +b*smooth +c*obstacle；
Wherein, center indicates the distance for deviateing reference path, and smooth indicates that path smooth, obstacle indicate distance barrier
Hindering object distance, a is the weight of center, and 0 < a < 1, b are the weight of smooth, and 0 < b < 1, c are the weight of obstacle, 0
< c < 1.
A kind of local paths planning method of automatic Pilot of the present invention, comprising the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
The random first path curve for generating the first preset quantity, detect between each first path curve and barrier respectively whether
It can collide, if will not collide between first path curve and barrier, calculate first according to evaluation function is preset
The evaluation function value of path curve, and using the smallest first path curve of evaluation function value as path curve to be selected；If all
First path curve can collide with barrier, then output is without feasible path；
Wherein, the generation method of the first path curve are as follows: using equiprobability random function from sampled point generated with
Machine extracts the sampled point of predetermined number, and is fitted by Cubic kolmogorov's differential system, obtains first path curve；
C, path optimization:
C1, second path curve, the generation method of second path curve are generated at random are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve；
Whether second path curve and barrier between can collide, if will not collide, according to default evaluation if detecting
Function calculates the evaluation function value of the second path curve；
C2, judge to optimize whether number reaches the second preset times, if not up to, return step C1 is entered step if reaching
C3；
C3, using the smallest second path curve of evaluation function value as optimal local path curve.
Further, the evaluation function are as follows:
F=a*center +b*smooth +c*obstacle；
Wherein, center indicates the distance for deviateing reference path, and smooth indicates that path smooth, obstacle indicate distance barrier
Hindering object distance, a is the weight of center, and 0 < a < 1, b are the weight of smooth, and 0 < b < 1, c are the weight of obstacle, 0
< c < 1.
A kind of local paths planning method of automatic Pilot of the present invention, comprising the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
The random first path curve for generating the first preset quantity, detect between each first path curve and barrier respectively whether
It can collide, if will not collide between first path curve and barrier, calculate first according to evaluation function is preset
The evaluation function value of path curve, and using the smallest first path curve of evaluation function value as path curve to be selected；If all
First path curve can collide with barrier, then output is without feasible path；
Wherein, the generation method of the first path curve are as follows: using equiprobability random function from sampled point generated with
Machine extracts the sampled point of predetermined number, and is fitted by Cubic kolmogorov's differential system, obtains first path curve；
C, path optimization:
Random the second path curve for generating the second preset quantity, detect between each second path curve and barrier respectively whether
It can collide, if will not collide between the second path curve and barrier, calculate second according to evaluation function is preset
The evaluation function value of path curve, and using the smallest second path curve of evaluation function value as optimal partial path curve；
Wherein, the generation method of second path curve are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve.
Further, the evaluation function are as follows:
F=a*center +b*smooth +c*obstacle；
Wherein, center indicates the distance for deviateing reference path, and smooth indicates that path smooth, obstacle indicate distance barrier
Hindering object distance, a is the weight of center, and 0 < a < 1, b are the weight of smooth, and 0 < b < 1, c are the weight of obstacle, 0
< c < 1.
A kind of local paths planning method of automatic Pilot of the present invention, comprising the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
B1, a first path curve, the generation method of the first path curve are generated at random are as follows:
The sampled point of predetermined number is randomly selected from sampled point generated using equiprobability random function, and passes through shellfish three times
Sai Er curve matching obtains first path curve；
Whether can collide between B2, detection first path curve and barrier, if can collide, enter step B3；
If will not collide, the evaluation function value of the first path curve is calculated according to evaluation function is preset, and enter step B3；
Whether B3, the random number for generating first path curve of judgement reach the first preset times, if not up to, return step
B1 enters step B4 if reaching；
If B4, having and will not collide between one or one or more first path curve and barrier, by evaluation function
It is worth the smallest first path curve as path curve to be selected, and access path optimizes；If all first path curves can be with
It collides between barrier, then output is without feasible path；
C, path optimization:
Random the second path curve for generating the second preset quantity, detect between each second path curve and barrier respectively whether
It can collide, if will not collide between the second path curve and barrier, calculate second according to evaluation function is preset
The evaluation function value of path curve, and using the smallest second path curve of evaluation function value as optimal partial path curve；
Wherein, the generation method of second path curve are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve.
Further, the evaluation function are as follows:
F=a*center +b*smooth +c*obstacle；
Wherein, center indicates the distance for deviateing reference path, and smooth indicates that path smooth, obstacle indicate distance barrier
Hindering object distance, a is the weight of center, and 0 < a < 1, b are the weight of smooth, and 0 < b < 1, c are the weight of obstacle, 0
< c < 1.
A kind of local paths planning system of automatic Pilot of the present invention, comprising:
Sensory perceptual system, for exporting the location information and velocity information of road vehicle, pedestrian and barrier in real time；
Global path planning system, for exporting the global path of current vehicle in real time；
Controller, for receiving the information of sensory perceptual system and the output of global path planning system, which is with perception respectively
System is connected with global path planning system:
The controller is programmed to the step of executing the local paths planning method of automatic Pilot as described in the present invention.
A kind of computer readable storage medium of the present invention, is stored with computer program, and the computer is deposited
The step of storage calls the local paths planning method for executing automatic Pilot as described in the present invention by controller.
The invention has the following advantages that
The position of road vehicle, pedestrian, the barrier for (1) combining the sensory perceptual system at current vehicle traveling moment to provide etc.,
The information such as speed cook up an optimal local path in real time, can complete the movement such as overtake other vehicles, follow, detour, braking.
(2) due to the method using stochastical sampling combination double optimization, number can be fitted just with less path curve
An optimal local path curve can be obtained, computational efficiency is improved.
Detailed description of the invention
Fig. 1 is the schematic diagram of path sampling and path optimization of the invention.
Fig. 2 is the logical flow chart of embodiment one in the present invention；
Fig. 3 is the logical flow chart of embodiment two in the present invention；
Fig. 4 is the logical flow chart of embodiment three in the present invention；
Fig. 5 is the logical flow chart of example IV in the present invention.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings.
Embodiment one
As shown in Fig. 2, in the present embodiment, a kind of local paths planning method of automatic Pilot, comprising the following steps:
A, information processing:
A1, vehicle (H rectangle as shown in figure 1) current location information and velocity information that sensory perceptual system exports in real time are obtained, and
The location information and velocity information of road vehicle, pedestrian and barrier (the A rectangle that the solid line in Fig. 1 indicates).It obtains complete
The global path (Lr curve as shown in figure 1) for the current vehicle that office's path planning system exports in real time.
(a) obstacle information that system docking receives is handled, and is filtered excessive or is crossed Small object, and to barrier profile
It is expanded, obtains A rectangle outer broken lines frame in Fig. 1；
(b) system carries out the processing of reference path to global path information, extracts several distances of current vehicle location direction of advance
Path point and the information such as road left and right sides width；
(c) barrier, path point and the road left and right sides width information obtained according to (a) and (b), screens barrier,
Filter out the barrier outside running region.
A2, on the basis of global path, first along longitudinal (general meter of the LookAheadDist of spacing distance at equal intervals
Calculate formula are as follows: LookAheadDist=VelSpeed*LADTime, wherein VelSpeed be current vehicle speed, unit m/s,
LADTime is to take aim at the time in advance, and general value is 1.5~2.0 determining fore-and-aft distance (directions that vehicle is travelled along road), further according to true
The fore-and-aft distance set is raw at equal intervals (generally take 3~4 at equal intervals) along transverse direction (offset direction of vehicle and path center)
At several sampled points (as shown in figure 1 along the point in Lr transverse direction)；
B, path samples:
B1, at random one first path curve of generation (such as: L1 and L2 in Fig. 1), the generation method of the first path curve
Are as follows:
The sampled point of predetermined number, each laterally sampling are randomly selected from sampled point generated using equiprobability random function
Collecting the sampled point predetermined number N calculation formula closed is N=LaneWidth/SampleWidth, and wherein LaneWidth is road
Can traffic areas width (the generally width of road left and right sides), SampleWidth be the sampling interval distance (generally 0.2m
~0.7m), therefore select the probability f of any sampled point that can be obtained by calculation formula for f=1/N, by each laterally sampling set
Upper selected sampled point is combined, and is fitted by Cubic kolmogorov's differential system, and first path curve is obtained；
Whether can collide between B2, detection first path curve and barrier, if can collide, enter step B3；
If will not collide, the evaluation function value of the first path curve is calculated according to evaluation function is preset, and enter step B3；
Whether B3, the random number for generating first path curve of judgement reach the first preset times (generally 5~20 times), if not
Reach, then return step B1, if reaching, enters step B4；
If B4, having and will not collide between one or one or more first path curve and barrier, by evaluation function
It is worth the smallest first path curve as path curve to be selected (Ls curve as shown in figure 1), and access path optimizes；If all
One path curve can collide between barrier, then output is without feasible path；
C, path optimization:
C1, second path curve, the generation method of second path curve are generated at random are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, if randomly selecting more than one point carries out lateral shift, the lateral shift distance of each point can be identical, also can not be identical；
By the point and unmigrated point after offset, it is fitted by Cubic kolmogorov's differential system, obtains the second path curve；
Whether second path curve and barrier between can collide, if will not collide, according to default evaluation if detecting
Function calculates the evaluation function value of the second path curve；
C2, judge to optimize whether number reaches the second preset times, if not up to, return step C1 is entered step if reaching
C3；
C3, using the smallest second path curve of evaluation function value as optimal local path curve (Ld curve as shown in figure 1).
In the present embodiment, the evaluation function are as follows:
F=a*center +b*smooth +c*obstacle；
Wherein, center indicates the distance for deviateing reference path, and smooth indicates that path smooth, obstacle indicate distance barrier
Hindering object distance, a is the weight of center, and 0 < a < 1, b are the weight of smooth, and 0 < b < 1, c are the weight of obstacle, 0
< c < 1.
Carry out speed planning according to local path information, calculate the curvature on local path at each point, according to curvature and
The current speed of vehicle goes the reference velocity of each point on planning local path, and reference velocity is attached in local path information
It exports together.
A kind of local paths planning system of automatic Pilot of the present invention, including sensory perceptual system, global path planning
System and controller, wherein sensory perceptual system for exporting the location information and speed of road vehicle, pedestrian and barrier in real time
Spend information；Global path planning system for exporting the global path of current vehicle in real time；Controller is for receiving sensory perceptual system
With the information of global path planning system output, which connect with sensory perceptual system and global path planning system respectively.Institute
It states controller and is programmed to the step of executing the local paths planning method of automatic Pilot as described in the present invention.
In the present embodiment, sensory perceptual system includes that (totally four, one is mounted on front bumper center to laser radar, before
Side, two are respectively mounted below the reflective mirror of left and right, and towards right and left, one is placed in rear bumper center, towards rear), milli
Metre wave radar (one is mounted on preceding air-inlet grille center lower section, towards front), (totally four, one is mounted on front to camera
At wind glass rearview mirror, towards front, two are respectively mounted below the reflective mirror of left and right, and towards right and left, one is placed in standby
Near case switch, towards rear), differential GPS receiver (receives double antenna and is mounted on roof).
A kind of computer readable storage medium of the present invention, is stored with computer program, and the computer is deposited
The step of storage calls the local paths planning method for executing automatic Pilot as described in the present invention by controller.
Embodiment two
As shown in figure 3, in the present embodiment, a kind of local paths planning method of automatic Pilot, comprising the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
The random first path curve for generating the first preset quantity, detect between each first path curve and barrier respectively whether
It can collide, if will not collide between first path curve and barrier, calculate first according to evaluation function is preset
The evaluation function value of path curve, and using the smallest first path curve of evaluation function value as path curve to be selected；If all
First path curve can collide with barrier, then output is without feasible path；
Wherein, the generation method of the first path curve are as follows: using equiprobability random function from sampled point generated with
Machine extracts the sampled point of predetermined number, and is fitted by Cubic kolmogorov's differential system, obtains first path curve；
C, path optimization:
C1, second path curve, the generation method of second path curve are generated at random are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve；
Whether second path curve and barrier between can collide, if will not collide, according to default evaluation if detecting
Function calculates the evaluation function value of the second path curve；
C2, judge to optimize whether number reaches the second preset times, if not up to, return step C1 is entered step if reaching
C3；
C3, using the smallest second path curve of evaluation function value as optimal local path curve.
Rest part is the same as example 1.
Embodiment three
As shown in figure 4, in the present embodiment, a kind of local paths planning method of automatic Pilot, comprising the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
The random first path curve for generating the first preset quantity, detect between each first path curve and barrier respectively whether
It can collide, if will not collide between first path curve and barrier, calculate first according to evaluation function is preset
The evaluation function value of path curve, and using the smallest first path curve of evaluation function value as path curve to be selected；If all
First path curve can collide with barrier, then output is without feasible path；
Wherein, the generation method of the first path curve are as follows: using equiprobability random function from sampled point generated with
Machine extracts the sampled point of predetermined number, and is fitted by Cubic kolmogorov's differential system, obtains first path curve；
C, path optimization:
Random the second path curve for generating the second preset quantity, detect between each second path curve and barrier respectively whether
It can collide, if will not collide between the second path curve and barrier, calculate second according to evaluation function is preset
The evaluation function value of path curve, and using the smallest second path curve of evaluation function value as optimal partial path curve；
Wherein, the generation method of second path curve are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve.
Rest part is the same as example 1.
Example IV
As shown in figure 5, in the present embodiment, a kind of local paths planning method of automatic Pilot, comprising the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
B1, a first path curve, the generation method of the first path curve are generated at random are as follows:
The sampled point of predetermined number is randomly selected from sampled point generated using equiprobability random function, and passes through shellfish three times
Sai Er curve matching obtains first path curve；
Whether can collide between B2, detection first path curve and barrier, if can collide, enter step B3；
If will not collide, the evaluation function value of the first path curve is calculated according to evaluation function is preset, and enter step B3；
Whether B3, the random number for generating first path curve of judgement reach the first preset times, if not up to, return step
B1 enters step B4 if reaching；
If B4, having and will not collide between one or one or more first path curve and barrier, by evaluation function
It is worth the smallest first path curve as path curve to be selected, and access path optimizes；If all first path curves can be with
It collides between barrier, then output is without feasible path；
C, path optimization:
Random the second path curve for generating the second preset quantity, detect between each second path curve and barrier respectively whether
It can collide, if will not collide between the second path curve and barrier, calculate second according to evaluation function is preset
The evaluation function value of path curve, and using the smallest second path curve of evaluation function value as optimal partial path curve；
Wherein, the generation method of second path curve are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve.
Rest part is the same as example 1.
Claims (10)
1. a kind of local paths planning method of automatic Pilot, which comprises the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
B1, a first path curve, the generation method of the first path curve are generated at random are as follows:
The sampled point of predetermined number is randomly selected from sampled point generated using equiprobability random function, and passes through shellfish three times
Sai Er curve matching obtains first path curve；
Whether can collide between B2, detection first path curve and barrier, if can collide, enter step B3；
If will not collide, the evaluation function value of the first path curve is calculated according to evaluation function is preset, and enter step B3；
Whether B3, the random number for generating first path curve of judgement reach the first preset times, if not up to, return step
B1 enters step B4 if reaching；
If B4, having and will not collide between one or one or more first path curve and barrier, by evaluation function
It is worth the smallest first path curve as path curve to be selected, and access path optimizes；If all first path curves can be with
It collides between barrier, then output is without feasible path；
C, path optimization:
C1, second path curve, the generation method of second path curve are generated at random are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve；
Whether second path curve and barrier between can collide, if will not collide, according to default evaluation if detecting
Function calculates the evaluation function value of the second path curve；
C2, judge to optimize whether number reaches the second preset times, if not up to, return step C1 is entered step if reaching
C3；
C3, using the smallest second path curve of evaluation function value as optimal local path curve.
2. the local paths planning method of automatic Pilot according to claim 1, it is characterised in that: the evaluation function
Are as follows:
F=a*center +b*smooth +c*obstacle；
Wherein, center indicates the distance for deviateing reference path, and smooth indicates that path smooth, obstacle indicate distance barrier
Hindering object distance, a is the weight of center, and 0 < a < 1, b are the weight of smooth, and 0 < b < 1, c are the weight of obstacle, 0
< c < 1.
3. a kind of local paths planning method of automatic Pilot, which comprises the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
The random first path curve for generating the first preset quantity, detect between each first path curve and barrier respectively whether
It can collide, if will not collide between first path curve and barrier, calculate first according to evaluation function is preset
The evaluation function value of path curve, and using the smallest first path curve of evaluation function value as path curve to be selected；If all
First path curve can collide with barrier, then output is without feasible path；
Wherein, the generation method of the first path curve are as follows: using equiprobability random function from sampled point generated with
Machine extracts the sampled point of predetermined number, and is fitted by Cubic kolmogorov's differential system, obtains first path curve；
C, path optimization:
C1, second path curve, the generation method of second path curve are generated at random are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve；
Whether second path curve and barrier between can collide, if will not collide, according to default evaluation if detecting
Function calculates the evaluation function value of the second path curve,
C2, judge to optimize whether number reaches the second preset times, if not up to, return step C1 is entered step if reaching
C3；
C3, using the smallest second path curve of evaluation function value as optimal local path curve.
4. the local paths planning method of automatic Pilot according to claim 3, it is characterised in that: the evaluation function
Are as follows:
F=a*center +b*smooth +c*obstacle；
Wherein, center indicates the distance for deviateing reference path, and smooth indicates that path smooth, obstacle indicate distance barrier
Hindering object distance, a is the weight of center, and 0 < a < 1, b are the weight of smooth, and 0 < b < 1, c are the weight of obstacle, 0
< c < 1.
5. a kind of local paths planning method of automatic Pilot, which comprises the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
The random first path curve for generating the first preset quantity, detect between each first path curve and barrier respectively whether
It can collide, if will not collide between first path curve and barrier, calculate first according to evaluation function is preset
The evaluation function value of path curve, and using the smallest first path curve of evaluation function value as path curve to be selected；If all
First path curve can collide with barrier, then output is without feasible path；
Wherein, the generation method of the first path curve are as follows: using equiprobability random function from sampled point generated with
Machine extracts the sampled point of predetermined number, and is fitted by Cubic kolmogorov's differential system, obtains first path curve；
C, path optimization:
Random the second path curve for generating the second preset quantity, detect between each second path curve and barrier respectively whether
It can collide, if will not collide between the second path curve and barrier, calculate second according to evaluation function is preset
The evaluation function value of path curve, and using the smallest second path curve of evaluation function value as optimal partial path curve；
Wherein, the generation method of second path curve are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve.
6. the local paths planning method of automatic Pilot according to claim 5, it is characterised in that: the evaluation function
Are as follows:
F=a*center +b*smooth +c*obstacle；
Wherein, center indicates the distance for deviateing reference path, and smooth indicates that path smooth, obstacle indicate distance barrier
Hindering object distance, a is the weight of center, and 0 < a < 1, b are the weight of smooth, and 0 < b < 1, c are the weight of obstacle, 0
< c < 1.
7. a kind of local paths planning method of automatic Pilot, which comprises the following steps:
A, information processing:
A1, current vehicle position information and velocity information and road vehicle, pedestrian that sensory perceptual system exports in real time are obtained
With the location information and velocity information of barrier；Obtain the global road for the current vehicle that global path planning system exports in real time
Diameter；
A2, on the basis of global path, first fore-and-aft distance is determined at equal intervals along longitudinal, further according to the fore-and-aft distance edge determined
Laterally generate several sampled points at equal intervals；
B, path samples:
B1, a first path curve, the generation method of the first path curve are generated at random are as follows:
The sampled point of predetermined number is randomly selected from sampled point generated using equiprobability random function, and passes through shellfish three times
Sai Er curve matching obtains first path curve；
Whether can collide between B2, detection first path curve and barrier, if can collide, enter step B3；
If will not collide, the evaluation function value of the first path curve is calculated according to evaluation function is preset, and enter step B3；
Whether B3, the random number for generating first path curve of judgement reach the first preset times, if not up to, return step
B1 enters step B4 if reaching；
If B4, having and will not collide between one or one or more first path curve and barrier, by evaluation function
It is worth the smallest first path curve as path curve to be selected, and access path optimizes；If all first path curves can be with
It collides between barrier, then output is without feasible path；
C, path optimization:
Random the second path curve for generating the second preset quantity, detect between each second path curve and barrier respectively whether
It can collide, if will not collide between the second path curve and barrier, calculate second according to evaluation function is preset
The evaluation function value of path curve, and using the smallest second path curve of evaluation function value as optimal partial path curve；
Wherein, the generation method of second path curve are as follows:
By path curve to be selected it is discrete be multiple points, and randomly select one of point or more than one point to laterally partially
It moves, by the point and unmigrated point after offset, is fitted by Cubic kolmogorov's differential system, obtains the second path curve.
8. the local paths planning method of automatic Pilot according to claim 7, it is characterised in that: the evaluation function
Are as follows:
F=a*center +b*smooth +c*obstacle；
Wherein, center indicates the distance for deviateing reference path, and smooth indicates that path smooth, obstacle indicate distance barrier
Hindering object distance, a is the weight of center, and 0 < a < 1, b are the weight of smooth, and 0 < b < 1, c are the weight of obstacle, 0
< c < 1.
9. a kind of local paths planning system of automatic Pilot, comprising:
Sensory perceptual system, for exporting the location information and velocity information of road vehicle, pedestrian and barrier in real time；
Global path planning system, for exporting the global path of current vehicle in real time；
Controller, for receiving the information of sensory perceptual system and the output of global path planning system, which is with perception respectively
System is connected with global path planning system:
It is characterized by: the controller is programmed to execute the part of automatic Pilot as described in any of the claims 1 to 8
The step of paths planning method.
10. a kind of computer readable storage medium, is stored with computer program, it is characterised in that: the computer storage
The step of local paths planning method for executing automatic Pilot as described in any of the claims 1 to 8 is called by controller.
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 true CN110262488A (en) | 2019-09-20 |
| CN110262488B 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) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111006667A (en) * | 2019-12-09 | 2020-04-14 | 东风商用车有限公司 | Automatic driving track generation system under high-speed scene |
| CN111123952A (en) * | 2019-12-31 | 2020-05-08 | 华为技术有限公司 | Trajectory planning method and device |
| CN111288995A (en) * | 2020-03-12 | 2020-06-16 | 深圳市人工智能与机器人研究院 | Path planning method and path planning device for mobile robot and terminal equipment |
| CN111475573A (en) * | 2020-04-08 | 2020-07-31 | 腾讯科技（深圳）有限公司 | Data synchronization method and device, electronic equipment and storage medium |
| CN111539345A (en) * | 2020-04-27 | 2020-08-14 | 北京百度网讯科技有限公司 | Method, device, equipment and readable storage medium for determining lane change action |
| CN111737636A (en) * | 2020-06-12 | 2020-10-02 | 北京百度网讯科技有限公司 | Path curve generation method and device, computer equipment and storage medium |
| CN112179368A (en) * | 2020-09-27 | 2021-01-05 | 广州小鹏自动驾驶科技有限公司 | Path data processing method and device, vehicle and readable medium |
| CN112783144A (en) * | 2019-10-22 | 2021-05-11 | 舜宇光学（浙江）研究院有限公司 | Path generation method, path planning method, system and equipment |
| CN112918486A (en) * | 2021-02-08 | 2021-06-08 | 北京理工大学 | Space-time behavior decision and trajectory planning system and method |
| CN112964271A (en) * | 2021-03-15 | 2021-06-15 | 西安交通大学 | Multi-scene-oriented automatic driving planning method and system |
| CN113091750A (en) * | 2021-04-12 | 2021-07-09 | 京东数科海益信息科技有限公司 | Local path planning method, device, computer equipment and storage medium |
| CN113483775A (en) * | 2021-06-30 | 2021-10-08 | 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 |
| CN113778102A (en) * | 2021-09-22 | 2021-12-10 | 重庆长安汽车股份有限公司 | AVP global path planning system, method, vehicle and storage medium |
| CN114593742A (en) * | 2020-12-04 | 2022-06-07 | 上海汽车集团股份有限公司 | Local path planning method, device and equipment for intelligent driving vehicle |
| WO2022183790A1 (en) * | 2021-03-02 | 2022-09-09 | 北京旷视机器人技术有限公司 | Path planning method and apparatus, mobile robot, storage medium, and program |
| 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 |
| CN116061975A (en) * | 2023-04-04 | 2023-05-05 | 北京集度科技有限公司 | Vehicle controller, vehicle and vehicle control method |
| CN116136417A (en) * | 2023-04-14 | 2023-05-19 | 北京理工大学 | Unmanned vehicle local path planning method facing off-road environment |
Citations (8)
| 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 |
| US20170320500A1 (en) * | 2016-05-03 | 2017-11-09 | Hyundai Motor Company | Path planning apparatus and method for autonomous 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 |
-
2019
- 2019-06-18 CN CN201910528047.8A patent/CN110262488B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170320500A1 (en) * | 2016-05-03 | 2017-11-09 | Hyundai Motor Company | Path planning apparatus and method for autonomous vehicle |
| 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 |
| US20170364083A1 (en) * | 2016-06-21 | 2017-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Local trajectory planning method and apparatus for smart vehicles |
| 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 |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112783144A (en) * | 2019-10-22 | 2021-05-11 | 舜宇光学（浙江）研究院有限公司 | Path generation method, path planning method, system and equipment |
| 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 |
| CN111006667A (en) * | 2019-12-09 | 2020-04-14 | 东风商用车有限公司 | Automatic driving track generation system under high-speed scene |
| 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 |
| CN111123952A (en) * | 2019-12-31 | 2020-05-08 | 华为技术有限公司 | Trajectory planning method and device |
| CN111288995A (en) * | 2020-03-12 | 2020-06-16 | 深圳市人工智能与机器人研究院 | Path planning method and path planning device for mobile robot and terminal equipment |
| CN111475573A (en) * | 2020-04-08 | 2020-07-31 | 腾讯科技（深圳）有限公司 | Data synchronization method and device, electronic equipment and storage medium |
| CN111539345A (en) * | 2020-04-27 | 2020-08-14 | 北京百度网讯科技有限公司 | Method, device, equipment and readable storage medium for determining lane change action |
| 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 |
| CN111737636A (en) * | 2020-06-12 | 2020-10-02 | 北京百度网讯科技有限公司 | Path curve generation method and device, computer equipment and storage medium |
| 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 |
| CN112179368A (en) * | 2020-09-27 | 2021-01-05 | 广州小鹏自动驾驶科技有限公司 | Path data processing method and device, vehicle and readable 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 |
| CN114593742A (en) * | 2020-12-04 | 2022-06-07 | 上海汽车集团股份有限公司 | Local path planning method, device and equipment for intelligent driving vehicle |
| CN112918486A (en) * | 2021-02-08 | 2021-06-08 | 北京理工大学 | Space-time behavior decision and trajectory planning system and method |
| CN112918486B (en) * | 2021-02-08 | 2022-06-03 | 北京理工大学 | Space-time behavior decision and trajectory planning system and method |
| WO2022183790A1 (en) * | 2021-03-02 | 2022-09-09 | 北京旷视机器人技术有限公司 | Path planning method and apparatus, mobile robot, storage medium, and program |
| CN112964271A (en) * | 2021-03-15 | 2021-06-15 | 西安交通大学 | Multi-scene-oriented automatic driving planning method and system |
| CN113091750A (en) * | 2021-04-12 | 2021-07-09 | 京东数科海益信息科技有限公司 | Local path planning method, device, computer equipment and storage medium |
| CN113483775A (en) * | 2021-06-30 | 2021-10-08 | 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 |
| CN113778102A (en) * | 2021-09-22 | 2021-12-10 | 重庆长安汽车股份有限公司 | AVP global path planning system, method, vehicle and 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 |
| 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 |
| CN116061975A (en) * | 2023-04-04 | 2023-05-05 | 北京集度科技有限公司 | Vehicle controller, vehicle and vehicle control method |
| CN116136417A (en) * | 2023-04-14 | 2023-05-19 | 北京理工大学 | Unmanned vehicle local path planning method facing off-road environment |
| CN116136417B (en) * | 2023-04-14 | 2023-08-22 | 北京理工大学 | Unmanned vehicle local path planning method facing off-road environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110262488B (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262488A (en) | Local paths planning method, system and the computer readable storage medium of automatic Pilot | |
| US11275382B2 (en) | Autonomous driving system | |
| US11155258B2 (en) | System and method for radar cross traffic tracking and maneuver risk estimation | |
| CN112204633B (en) | Probabilistic object tracking and prediction framework | |
| CN114234998B (en) | Unmanned multi-target point track parallel planning method based on semantic road map | |
| Cosgun et al. | Towards full automated drive in urban environments: A demonstration in gomentum station, california | |
| US9079587B1 (en) | Autonomous control in a dense vehicle environment | |
| CN105892464A (en) | Special car automatic driving system based on fixed routes and driving method for same | |
| CN110816540B (en) | Traffic jam determining method, device and system and vehicle | |
| CN104897168A (en) | Intelligent vehicle path search method and system based on road risk assessment | |
| CN105809130A (en) | Binocular depth perception-based vehicle travelable area calculation method | |
| Kim et al. | Probabilistic threat assessment with environment description and rule-based multi-traffic prediction for integrated risk management system | |
| CN104933856A (en) | Real-time evaluation system and method for road conditions | |
| CN112265542B (en) | Automatic driving meeting scene processing method and device and vehicle | |
| Kim et al. | Automated complex urban driving based on enhanced environment representation with GPS/map, radar, lidar and vision | |
| Kim et al. | Design of integrated risk management-based dynamic driving control of automated vehicles | |
| US11358606B2 (en) | Method for operating a motor vehicle for improving working conditions of evaluation units in the motor vehicle, control system for performing a method of this kind, and motor vehicle having a control system of this kind | |
| CN113085852A (en) | Behavior early warning method and device for automatic driving vehicle and cloud equipment | |
| CN109709944A (en) | A kind of generation method in enter the station method and its path of entering the station of automatic Pilot bus | |
| CN115140096A (en) | Spline curve and polynomial curve-based automatic driving track planning method | |
| CN112394725A (en) | Predictive and reactive view-based planning for autonomous driving | |
| CN106371436A (en) | Driverless automobile obstacle avoidance method and system | |
| CN113581181B (en) | Intelligent vehicle overtaking track planning method | |
| WO2022154986A1 (en) | Methods and systems for safe out-of-lane driving | |
| CN113432615A (en) | Detection method and system based on multi-sensor fusion drivable area and vehicle |
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 |