CN108444488A - Based on etc. steps sample A* algorithms unmanned local paths planning method - Google Patents
Based on etc. steps sample A* algorithms unmanned local paths planning method Download PDFInfo
- Publication number
- CN108444488A CN108444488A CN201810112446.1A CN201810112446A CN108444488A CN 108444488 A CN108444488 A CN 108444488A CN 201810112446 A CN201810112446 A CN 201810112446A CN 108444488 A CN108444488 A CN 108444488A
- Authority
- CN
- China
- Prior art keywords
- node
- point
- lists
- search
- vehicle
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Navigation (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention belongs to unmanned path planning field, the kinematical constraint to meet automobile is limited with actual traffic, the present invention, based on etc. steps sample the unmanned local paths planning methods of A* algorithms, be as follows：Step 1：Define step-size in search and search security domain；Step 2：Determine the starting point and target point of route searching in the grid map of part；Step 3：Establish Open lists and Closed lists；Step 4：Solve the cost function of grid point in Open lists；Step 5：The grid point of cost function value minimum is selected from Open lists；Step 6：All safe adjacent nodes of present node are investigated respectively；Step 7：Processing of the present node without child node in search process；Step 8：The process for repeating step 57 returns to feasible path, or return to search failure until meeting condition.Present invention is mainly applied to unmanned road occasions.
Description
Technical field
The invention belongs to unmanned path planning fields, specifically, are related to a kind of steps sampling and the A* algorithms such as utilizing former
The path search algorithm of reason carries out the local paths planning of automatic driving vehicle.
Background technology
With the development of society, requirement of the people to quality of the life is higher and higher, it is indispensable that automobile becomes human lives
The vehicles, however the increase of automobile quantity and driver's inherently safe consciousness weakness lead to global traffic accident rate
Sharp increase.In face of increasingly serious traffic safety and traffic jam issue, building the task of intelligent transportation system becomes more
In a hurry.Key component of the automatic driving vehicle as structure intelligent transportation system, is paid close attention to by each side in recent years.It is unmanned
The Vehicle Fusion multiple functions such as environment sensing and positioning, decision rule and motion control, to replace the eye of driver, brain and
Hand, have many advantages, such as to be swift in response, driving safety it is reliable.The unmanned skill of some countries such as the U.S., Britain and Germany at present
Art has developed more mature, and the unmanned technology in China is started late, advanced apart from the world in the development of some key technologies
Level also has a certain distance.
The path planning algorithm of automatic driving vehicle mainly inherits the algorithm of robot field, such as A* algorithms, RRT are calculated
Method, Artificial Potential Field Method etc..A* (A-Star) algorithm is to solve the most effective direct search side of shortest path in a kind of static road network
Method, robustness is good, fast to environmental information reaction speed, is widely used in all kinds of robots.A* algorithms are Dijkstra
The improvement of algorithm has the advantages that fast convergence rate, directive property are apparent, search space is small compared with original dijkstra's algorithm.
But traditional basic A* algorithms are due to depending on square grid midpoint to scan for, and its cost function is only path length
Function (cost only related with path length), thus there are path directions to fix, path smooth degree is insufficient, turning angle is big etc. no
Foot, and in the real road emulation and outer curve road simulation for considering lane line limitation, effect is undesirable.Early in 2007
In the city challenge match that U.S. DARPA (advanced research projects agency of the U.S.) is held, the Junior unmanned vehicles of Stanford University's development
The second place of match is achieved using a kind of improved A* algorithms.Some R＆D institutions of China are also by A* algorithms for unmanned
In the path planning of vehicle, for example, China Science ＆ Technology University be propose it is a kind of based on can search for continuous neighborhood A* algorithms nobody
Drive vehicle path planning method.In addition, RRT algorithms are a kind of planing methods of stochastical sampling.It was proposed from 1998, RRT is calculated
Method is widely used in dynamic environment, dimensional state environment and there are kinematics constraints due to its increment type growth characteristics
Environment in.Artificial Potential Field Method is a kind of virtual force method proposed by Khatib, by the motion design of robot at one kind in people
The movement in gravitational field is made, safe and smoother path is cooked up.Since both the above method is not applied in the present invention,
It will not be described below.
Although forefathers have proposed a variety of unmanned path planning algorithms, but algorithm is unsatisfactory for vehicle kinematics about mostly
Beam cannot be directly used to vehicle control, need to carry out a large amount of processing work.
Invention content
Kinematical constraint in order to meet automobile is limited with actual traffic, for the local paths planning of automatic driving vehicle
Make following several respects research：
(1) selection of the cost function under lane line constraint is added；
(2) selection for the cost function that avoidance requires is carried；
(3) consider vehicle actual motion model, carry the A* algorithms of steering constraint；
(4) A* route searchings and the security domain selection of arbitrary point (non-central point) in grid are based on；
(5) path planning of crossroad turn inside diameter.
The present invention by etc. steps sampling thought be introduced into local paths planning strategy, based on etc. steps sample A* algorithms nothing
People drives local paths planning method, is as follows：
Step 1：Define step-size in search and search security domain；
Step-size in search calculation formula is：
Wherein Step indicates that step-size in search, l indicate that grid map precision, v indicate the travel speed of current vehicle, T expressions office
Portion's route update time；
Judged using circular safety domain, the radius r of circular domainsafeIt is defined as：
Here LvehicleFor length of wagon, max () is to be maximized function, in the father node of known current search node
In the case of, need the circular domain of the circular domain for judging current search node and present node and his father's node center point, two
The equal clear in region of circular domain covering is then safety, is danger zone, the cost function of the node if there are barrier
Value is infinity；
Step 2：Determine the starting point and target point of route searching in the grid map of part；
The starting point of route searching is the current location of vehicle, is (0,0) point under vehicle-mounted coordinate system, and headstock is directed toward x
Axis positive direction, therefore position and direction all same of the vehicle in every frame grid map, can be with according to the lane line information in grid map
Judge present road shape, lane line curve can be obtained by quadratic fit, and then obtains current lane center line curve,
Since vehicle is in strict accordance with the increased direction running of x coordinate under vehicle-mounted coordinate system, therefore the target point of route searching is defined as grid
Current lane center line curve x coordinate value maximum position within the scope of trrellis diagram, if there are barrier in the position security realm scope,
It is selected around in the position to meet the point of safe distance as target point apart from barrier；
Step 3：Establish Open lists and Closed lists, Open lists store all generated and the node do not investigated,
The node in path had been investigated and had been added in Closed lists storage, the last one element is current road in Closed lists
Path search node,
Step 4：Solve the cost function of grid point in Open lists；
F (n)=K1g(n)+K2h(n)+K3p(n) (4a)
G (n)=g1Lacc(n)+g2Dacc(n) (4b)
H (n)=h1Lest(n)+h2Dest(n) (4c)
Wherein, f (n) indicates the total cost of grid point, K1、K2And K3For three positive weight coefficients, g (n) indicates that starting point arrives
The accumulated costs of the node, g1And g2For positive weight coefficient, Lacc(n) it is the step-length cost accumulated, Dacc(n) it is turning for accumulation
To cost,
H (n) indicates to estimate cost, h from the node to target point1And h2For positive weight coefficient, Lest(n) it estimates
Step-length cost, Dest(n) it is the steering cost estimated,
P (n) be penalty term, be defined as the fixation cost from father node to the node, due to apart from cost on this
It is not different, therefore the part is only determined by steering angle, α1For positive weight coefficient.θ (n) indicates the movement side of present node
To.
For the direction of motion θ (0)=0 of starting point, accumulated costs g (0)=0, penalty term is p (0)=0, therefore the generation of starting point
Valence function is：
F (0)=K2(h1Lest(0)+h2Dest(0)) (5)
Step 5：The grid point that cost function value minimum is selected from Open lists, labeled as current node, and by its from
Open lists move on in Closed lists；
Step 6：All safe adjacent nodes for investigating present node respectively, if the point does not also exist neither in Open lists
In Closed lists, which is added in Open lists, solves its cost function value, present node is father's section of the point
Point；
Step 7：If present node is without child node in search process, its father node is returned to by present node, and should
Point is deleted from Closed lists, selects the node of cost function value minimum again in Open lists；
Step 8：The process for repeating step 5-7, until meeting condition：
Then it is considered as arrival target point, terminates search, returns to feasible path.If occur in search process Open lists and
Closed lists are sky, then feasible path is not present, and return to search failure.
Step 3 concrete operations flow is as follows：
1. starting point is added in Open lists and Closed lists；
2. the safe grid point adjacent with starting point is added in Open lists, then starting point is father's section of adjacent gate lattice point
Point, is examined
Consider the steering constraint of vehicle, adjacent cells point coordinates (xcur,ycur) be：
Wherein, (xfather,yfather) indicate father node coordinate, θfatehrFor the direction of motion of father node.N determines to choose
Node number, i.e., with fixed differential seat angleSelect 2N+1 adjacent gate lattice point, φmaxIndicate that vehicle maximum front-wheel is inclined
Angle, i indicate node counts, and the positive and negative steering for determining vehicle, when i is positive number, vehicle shows as turning right, when i is negative, vehicle
It shows as.The direction of motion of adjacent gate lattice point is also
As shown in the cost function in step 4, K1、K2、K3、g1、g2、h1、h2And α1It is positive real number, needs to pass through ginseng
Number adjusts determination, in K1=0.8, K2=1.52, K3=0.25, g1=1, g2=1.2, h1=1, h2=0.6, α1Effect when=1.2
Meet actual requirement.
Compared with the prior art, technical characterstic of the invention and effect：
Search node is chosen in the steps sampling such as proposed by the present invention, and the movement side of node is limited when determining adjacent node
To both having met the steering constraint of vehicle, the path searched is also more smooth, and in the case of at the uniform velocity, vehicle control is not necessarily to
Path is fitted.Some improvement A* algorithm common problems that traditional A* algorithms and forefathers propose are saved in path
The distance between point differs, and the direction of search causes the path searched to need a large amount of processing that could be used for vehicle without limitation
Control, such as go node, curve matching etc..
Compared with the prior art, it the accumulated costs in cost function proposed by the invention and estimates cost part and not only wraps
It includes apart from cost, further includes angle cost, and cost function carries penalty term, is defined as present node consolidating to next node
Determine cost, due to being not different on this apart from cost, therefore this is only determined by steering angle.Factors above can be use up can
Energy avoids turning greatly, keeps path more smooth, reduces vehicle mechanical loss.At the end of avoidance, setting for angle cost is estimated
It sets so that path returns to the track that vehicle should travel as quickly as possible.To reduce computation complexity, apart from cost in cost function
Part be all made of manhatton distance, experiments have shown that using the search time used in manhatton distance to be significantly shorter than using Euclidean away from
From search time used.
Since the Searching point of the present invention is not or not grid center, therefore security domain is using previous Square Neighborhood and improper, and
Square Neighborhood with directive safety inspection to being inaccurate, and circle shaped neighborhood region is due to its rotational symmetry, independent of direction, therefore
It is more particularly suitable as safe neighborhood.Safe neighborhood used by the present invention is with current search node and current search node
It is the center of circle with the central point of its father node, what two circles of an a diameter of step-size in search and maximum value in length of wagon were covered
All grid regions ensure that path there is no barrier is passed through, and no matter vehicle touches toward which direction running nothing
Hit danger.
The road conditions such as the invention is turned at the parting of the ways by test, avoidance and S types are curved can obtain quickly can walking along the street
Diameter, gained path be satisfied by vehicle control limitation, in Visual Studio gained search time be respectively less than 30ms.
(Visual Studio are the Integrated Development Environment of windows platform application)
Description of the drawings
Fig. 1 is inventive algorithm overall flow figure.
Fig. 2 defines for vehicle-mounted coordinate system.
Fig. 3 is the crossroad left-hand rotation result figure realized in Visual Studio2013.
Fig. 4 is the crossroad right-hand rotation result figure realized in Visual Studio2013.
Fig. 5 is the avoidance result figure realized in Visual Studio2013.
Fig. 6 is the S type bends road result figure realized in Visual Studio2013.
Specific implementation mode
The present invention by etc. the thought of steps sampling be added in local paths planning strategy, propose a kind of new cost function,
Specific implementation step is as follows：
Step 1：Define step-size in search and search security domain；
It is the distance that vehicle advances in a controlling cycle to define step-size in search, therefore step-size in search calculation formula is：
Wherein Step indicates that step-size in search, l indicate that grid map precision, v indicate the travel speed of current vehicle, T expressions office
Portion's route update time.
There is the possibility of direction change since vehicle advances, to ensure that each node is safety in path, is used
Circular safety domain judges that the radius of circular domain is：
Here LvehicleFor length of wagon, max () is to be maximized function, in the father node of known current search node
In the case of, need the circular domain of the circular domain for judging current search node and present node and his father's node center point, two
The equal clear in region of circular domain covering is then safety, is danger zone, the cost function of the node if there are barrier
Value is infinity.Compared with rectangular safe region of search, the benefit using circular safety region of search is that determination range reduces, and is reduced
The possibility of route searching failure.
Step 2：Determine the starting point and target point of route searching in the grid map of part；
The starting point of route searching is the current location of vehicle, is (0,0) point under vehicle-mounted coordinate system, and headstock is directed toward x
Axis positive direction, position and direction all same of the as shown in Figure 2 therefore vehicle in every frame grid map.According to the lane line in grid map
Information may determine that present road shape, can obtain lane line curve by quadratic fit, and then obtain in current lane
Heart line curve.Since vehicle is in strict accordance with the increased direction running of x coordinate under vehicle-mounted coordinate system, therefore the target point of route searching
It is defined as current lane center line curve x coordinate value maximum position within the scope of grid map, if existing in the position security realm scope
Barrier, then it is selected around in the position to meet the point of safe distance as target point apart from barrier.
Step 3：Establish Open lists and Closed lists, Open lists store all generated and the node do not investigated,
The node in path had been investigated and had been added in Closed lists storage, the last one element is current road in Closed lists
Path search node, concrete operations flow are as follows：
1. starting point is added in Open lists and Closed lists.
2. the safe grid point adjacent with starting point is added in Open lists, then starting point is father's section of adjacent gate lattice point
Point, it is contemplated that the steering constraint of vehicle, adjacent cells point coordinates (xcur,ycur) be：
Wherein, (xfather,yfather) indicate father node coordinate, θfatehrFor the direction of motion of father node.N determines to choose
Node number, i.e., with fixed differential seat angleSelect 2N+1 adjacent gate lattice point, φmaxIndicate that vehicle maximum front-wheel is inclined
Angle, i indicate node counts, and the positive and negative steering for determining vehicle, when i is positive number, vehicle shows as turning right, when i is negative, vehicle
It shows as.The direction of motion of adjacent gate lattice point is also
Step 4：Solve the cost function of grid point in Open lists；
F (n)=K1g(n)+K2h(n)+K3p(n) (4a)
G (n)=g1Lacc(n)+g2Dacc(n) (4b)
H (n)=h1Lest(n)+h2Dest(n) (4c)
Wherein, f (n) indicates the total cost of grid point, K1、K2And K3For three positive weight coefficients.G (n) indicates that starting point arrives
The accumulated costs of the node, g1And g2Step-length cost for positive weight coefficient, accumulation is：
Lacc(n)=1+Lacc(n-1)
The steering cost of accumulation is：
H (n) indicates to estimate cost, h from the node to target point1And h2For positive weight coefficient, the step-length cost estimated
For：
Wherein, (xgoal,ygoal) indicate target point coordinate.
The steering cost estimated is：
Wherein, arctan () is to be maximized function.
P (n) be penalty term, be defined as the fixation cost from father node to the node, due to apart from cost on this
It is not different, therefore the part is only determined by steering angle, α1For positive weight coefficient.θ (n) indicates the movement side of present node
To.
For the direction of motion θ (0)=0 of starting point, accumulated costs g (0)=0, penalty term is p (0)=0, and estimating cost is：
Wherein, (xstart,ystart) indicate starting point coordinate.
Therefore the cost function of starting point is：
F (0)=K2(h1Lest(0)+h2Dest(0)) (5)
Step 5：The grid point that cost function value minimum is selected from Open lists, labeled as current node, and by its from
Open lists move on in Closed lists；
Step 6：All safe adjacent nodes for investigating present node respectively, if the point does not also exist neither in Open lists
In Closed lists, which is added in Open lists, solves its cost function value, present node is father's section of the point
Point；
Step 7：If present node is without child node in search process, its father node is returned to by present node, and should
Point is deleted from Closed lists, selects the node of cost function value minimum again in Open lists；
Step 8：The process for repeating step 5-7, until meeting condition：
Then it is considered as arrival target point, terminates search, returns to feasible path.If occur in search process Open lists and
Closed lists are sky, then feasible path is not present, and return to search failure.
Implementation steps flow chart of the present invention is as shown in Figure 1, the experimental results showed that the algorithm is protected when can meet clear
Lanes are held, more smooth path also can be obtained as shown in Figure 2,3, when crossroad is turned and are accomplished in clear
Track is kept, and as shown in Figure 4,5, can accomplish the avoidance of static-obstacle thing on the basis of meeting Vehicular turn and limiting.Such as step
Shown in cost function in rapid 4, K1、K2、K3、g1、g2、h1、h2And α1It is positive real number, needs to determine by parameter tuning.Ginseng
Several differences can cause the path searched for road conditions of the same race and search time that there is prodigious gap, experimental data to be shown in
K1=0.8, K2=1.52, K3=0.25, g1=1, g2=1.2, h1=1, h2=0.6, α1Effect substantially conforms to reality when=1.2
It is required that.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical solution and advantageous effect
It describes in detail bright, it should be understood that the above is only a specific embodiment of the present invention, is not intended to restrict the invention, it is all
Within the spirit and principles in the present invention, any modification, equivalent substitution, improvement and etc. done should be included in the guarantor of the present invention
Within the scope of shield.
The it is proposed of the A* algorithms document that sees reference is as follows：
P.E.Hart,N.J.Nilsson,and B.Raphael.A formal basis for the heuristic
determination of minimum cost paths in graphs.IEEE Trans.Syst.Sci.and
Cybernetics,SSC-4(2):100-107,1968”。
Claims (3)
1. it is a kind of based on etc. steps sample A* algorithms unmanned local paths planning method, characterized in that be as follows：
Step 1：Define step-size in search and search security domain；
Step-size in search calculation formula is：
Wherein Step indicates that step-size in search, l indicate that grid map precision, v indicate that the travel speed of current vehicle, T indicate local road
Diameter renewal time；
Judged using circular safety domain, the radius r of circular domainsafeIt is defined as：
Here LvehicleFor length of wagon, max () is to be maximized function, in the feelings of the father node of known current search node
Under condition, the circular domain of the circular domain for judging current search node and present node and his father's node center point, two circles are needed
The equal clear in region of domain covering is then safety, is danger zone if there are barrier, and the cost function value of the node is
It is infinitely great；
Step 2：Determine the starting point and target point of route searching in the grid map of part；
The starting point of route searching is the current location of vehicle, is (0,0) point under vehicle-mounted coordinate system, and headstock is being directed toward x-axis just
Direction, therefore position and direction all same of the vehicle in every frame grid map may determine that according to the lane line information in grid map
Go out present road shape, lane line curve can be obtained by quadratic fit, and then obtains current lane center line curve, due to
Vehicle is in strict accordance with the increased direction running of x coordinate under vehicle-mounted coordinate system, therefore the target point of route searching is defined as grid map
Current lane center line curve x coordinate value maximum position in range, if there are barriers in the position security realm scope, at this
Position is selected around to meet the point of safe distance as target point apart from barrier；
Step 3：Establish Open lists and Closed lists, Open lists store all generated and the node do not investigated,
The node in path had been investigated and had been added in Closed lists storage, the last one element is current road in Closed lists
Path search node,
Step 4：Solve the cost function of grid point in Open lists；
F (n)=K1g(n)+K2h(n)+K3p(n) (4a)
G (n)=g1Lacc(n)+g2Dacc(n) (4b)
H (n)=h1Lest(n)+h2Dest(n) (4c)
Wherein, f (n) indicates the total cost of grid point, K1、K2And K3For three positive weight coefficients, g (n) indicates starting point to the section
The accumulated costs of point, g1And g2For positive weight coefficient, Lacc(n) it is the step-length cost accumulated, Dacc(n) it is the steering generation accumulated
Valence,
H (n) indicates to estimate cost, h from the node to target point1And h2For positive weight coefficient, Lest(n) it is the step-length estimated
Cost, Dest(n) it is the steering cost estimated,
P (n) is penalty term, the fixation cost from father node to the node is defined as, due to not having on this apart from cost
Difference, therefore the part is only determined by steering angle, α1For positive weight coefficient.θ (n) indicates the direction of motion of present node.
For the direction of motion θ (0)=0 of starting point, accumulated costs g (0)=0, penalty term is p (0)=0, therefore the cost letter of starting point
Number is：
F (0)=K2(h1Lest(0)+h2Dest(0)) (5)
Step 5：The grid point that cost function value minimum is selected from Open lists, labeled as current node, and by it from Open
List moves on in Closed lists；
Step 6：All safe adjacent nodes for investigating present node respectively, if the point does not also exist neither in Open lists
In Closed lists, which is added in Open lists, solves its cost function value, present node is father's section of the point
Point；
Step 7：If present node is without child node in search process, its father node is returned to by present node, and by the point from
It is deleted in Closed lists, selects the node of cost function value minimum again in Open lists；
Step 8：The process for repeating step 5-7, until meeting condition：
Then be considered as arrival target point, terminate search, if return feasible path occur in search process Open lists and
Closed lists are sky, then feasible path is not present, and return to search failure.
2. as described in claim 1 based on etc. steps sample A* algorithms unmanned local paths planning method, characterized in that
Step 3 concrete operations flow is as follows：
1. starting point is added in Open lists and Closed lists；
2. the safe grid point adjacent with starting point is added in Open lists, then starting point is the father node of adjacent gate lattice point,
In view of the steering constraint of vehicle, adjacent cells point coordinates (xcur,ycur) be：
Wherein, (xfather,yfather) indicate father node coordinate, θfatehrFor the direction of motion of father node.N determines the section chosen
Point number, i.e., with fixed differential seat angleSelect 2N+1 adjacent gate lattice point, φmaxIndicate vehicle maximum front wheel slip angle, i
Indicating node counts, the positive and negative steering for determining vehicle, when i is positive number, vehicle shows as turning right, when i is negative, vehicle performance
To turn left.The direction of motion of adjacent gate lattice point is also
3. as described in claim 1 based on etc. steps sample A* algorithms unmanned local paths planning method, characterized in that
As shown in the cost function in step 4, K1、K2、K3、g1、g2、h1、h2And α1It is positive real number, needs true by parameter tuning
It is fixed, in K1=0.8, K2=1.52, K3=0.25, g1=1, g2=1.2, h1=1, h2=0.6, α1Effect meets reality when=1.2
It is required that.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810112446.1A CN108444488B (en) | 2018-02-05 | 2018-02-05 | Unmanned local path planning method based on equal-step sampling A-x algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810112446.1A CN108444488B (en) | 2018-02-05 | 2018-02-05 | Unmanned local path planning method based on equal-step sampling A-x algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108444488A true CN108444488A (en) | 2018-08-24 |
| CN108444488B CN108444488B (en) | 2021-09-28 |
Family
ID=63191716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810112446.1A Active CN108444488B (en) | 2018-02-05 | 2018-02-05 | Unmanned local path planning method based on equal-step sampling A-x algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108444488B (en) |
Cited By (50)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108896052A (en) * | 2018-09-20 | 2018-11-27 | 鲁东大学 | A kind of mobile robot smooth paths planing method under the environment based on DYNAMIC COMPLEX |
| CN109238270A (en) * | 2018-10-21 | 2019-01-18 | 浙江浙大中控信息技术有限公司 | Intelligent navigation method based on improved A star algorithm |
| CN109374004A (en) * | 2018-11-12 | 2019-02-22 | 智慧航海（青岛）科技有限公司 | A kind of Intelligent unattended ship paths planning method based on IA* algorithm |
| CN109634304A (en) * | 2018-12-13 | 2019-04-16 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Unmanned plane during flying paths planning method, device and storage medium |
| CN109798909A (en) * | 2019-02-01 | 2019-05-24 | 安徽达特智能科技有限公司 | A kind of method of global path planning |
| CN109945882A (en) * | 2019-03-27 | 2019-06-28 | 上海交通大学 | A kind of automatic driving vehicle path planning and control system and method |
| CN109945885A (en) * | 2019-04-16 | 2019-06-28 | 清华大学 | The dynamic barrier obstacle-avoiding route planning calculation method of unmanned motor |
| CN110032187A (en) * | 2019-04-09 | 2019-07-19 | 清华大学 | Unmanned motor static-obstacle obstacle-avoiding route planning calculation method |
| CN110220528A (en) * | 2019-06-10 | 2019-09-10 | 福州大学 | A kind of two-way dynamic path planning method of automatic Pilot unmanned vehicle based on A star algorithm |
| CN110333659A (en) * | 2019-07-15 | 2019-10-15 | 中国人民解放军军事科学院国防科技创新研究院 | A kind of pilotless automobile local paths planning method based on improvement A star search |
| CN110333714A (en) * | 2019-04-09 | 2019-10-15 | 武汉理工大学 | A kind of pilotless automobile paths planning method and device |
| CN110398250A (en) * | 2019-08-13 | 2019-11-01 | 哈尔滨工程大学 | A kind of unmanned boat global path planning method |
| CN110531782A (en) * | 2019-08-23 | 2019-12-03 | 西南交通大学 | Unmanned aerial vehicle flight path paths planning method for community distribution |
| CN110595482A (en) * | 2019-10-28 | 2019-12-20 | 深圳市银星智能科技股份有限公司 | Path planning method and device with obstacle avoidance weight and electronic equipment |
| CN110609547A (en) * | 2019-08-21 | 2019-12-24 | 中山大学 | Mobile robot planning method based on visual map guidance |
| CN110806218A (en) * | 2019-11-29 | 2020-02-18 | 北京京东乾石科技有限公司 | Parking path planning method, device and system |
| CN110836671A (en) * | 2019-11-14 | 2020-02-25 | 北京京邦达贸易有限公司 | Trajectory planning method, trajectory planning device, storage medium, and electronic apparatus |
| CN110908386A (en) * | 2019-12-09 | 2020-03-24 | 中国人民解放军军事科学院国防科技创新研究院 | Layered path planning method for unmanned vehicle |
| CN110967032A (en) * | 2019-12-03 | 2020-04-07 | 清华大学 | Real-time planning method for local driving route of unmanned vehicle in field environment |
| CN111060108A (en) * | 2019-12-31 | 2020-04-24 | 江苏徐工工程机械研究院有限公司 | Path planning method and device and engineering vehicle |
| CN111076736A (en) * | 2020-01-02 | 2020-04-28 | 清华大学 | Vehicle-mounted system based on FPGA design and A star path searching method |
| CN111158366A (en) * | 2019-12-31 | 2020-05-15 | 湖南大学 | Path planning method based on graph search and geometric curve fusion |
| CN111196560A (en) * | 2020-01-03 | 2020-05-26 | 山东大学 | Method and system for dynamically adjusting dangerous area range of bridge crane |
| WO2020102987A1 (en) * | 2018-11-20 | 2020-05-28 | 深圳大学 | Intelligent assisted driving method and system |
| CN111307156A (en) * | 2020-03-09 | 2020-06-19 | 中振同辂(江苏)机器人有限公司 | Coverage path planning method suitable for vehicle-shaped robot |
| CN111427346A (en) * | 2020-03-09 | 2020-07-17 | 中振同辂(江苏)机器人有限公司 | Local path planning and tracking method suitable for vehicle-shaped robot |
| CN111487975A (en) * | 2020-04-30 | 2020-08-04 | 畅加风行(苏州)智能科技有限公司 | Intelligent networking system-based automatic port truck formation method and system |
| CN111679692A (en) * | 2020-08-04 | 2020-09-18 | 上海海事大学 | Unmanned aerial vehicle path planning method based on improved A-star algorithm |
| CN111693050A (en) * | 2020-05-25 | 2020-09-22 | 电子科技大学 | Indoor medium and large robot navigation method based on building information model |
| CN111857148A (en) * | 2020-07-28 | 2020-10-30 | 湖南大学 | Unstructured road vehicle path planning method |
| CN111857112A (en) * | 2019-04-12 | 2020-10-30 | 广州汽车集团股份有限公司 | Automobile local path planning method and electronic equipment |
| CN111897365A (en) * | 2020-08-27 | 2020-11-06 | 中国人民解放军国防科技大学 | Autonomous vehicle three-dimensional path planning method for contour line guide line |
| CN111912407A (en) * | 2019-05-08 | 2020-11-10 | 胡贤良 | Path planning method of multi-robot system |
| CN112612266A (en) * | 2020-12-04 | 2021-04-06 | 湖南大学 | Unstructured road global path planning method and system |
| CN112700668A (en) * | 2020-12-22 | 2021-04-23 | 北京百度网讯科技有限公司 | Remote control method for automatic driving, automatic driving vehicle and cloud equipment |
| CN112764413A (en) * | 2019-10-22 | 2021-05-07 | 广州中国科学院先进技术研究所 | Robot path planning method |
| CN112764418A (en) * | 2020-12-25 | 2021-05-07 | 珠海市一微半导体有限公司 | Clean entrance position determination method based on path finding cost, chip and robot |
| CN112783166A (en) * | 2020-12-30 | 2021-05-11 | 深兰人工智能(深圳)有限公司 | Local trajectory planning method and device, electronic equipment and storage medium |
| CN112923940A (en) * | 2021-01-11 | 2021-06-08 | 珠海格力电器股份有限公司 | Path planning method, device, processing equipment, mobile equipment and storage medium |
| CN113031599A (en) * | 2021-03-02 | 2021-06-25 | 珠海市一微半导体有限公司 | Robot rapid seat finding method with dynamically changed reference point, chip and robot |
| CN113052350A (en) * | 2019-12-26 | 2021-06-29 | 浙江吉利汽车研究院有限公司 | Path planning method and device, electronic equipment and storage medium |
| CN113119995A (en) * | 2021-03-11 | 2021-07-16 | 京东鲲鹏(江苏)科技有限公司 | Path searching method and device, equipment and storage medium |
| CN113124849A (en) * | 2019-12-30 | 2021-07-16 | 广东博智林机器人有限公司 | Indoor path planning method and device, electronic equipment and storage medium |
| CN113286985A (en) * | 2020-09-17 | 2021-08-20 | 华为技术有限公司 | Path planning method and path planning device |
| CN113359757A (en) * | 2021-06-30 | 2021-09-07 | 湖北汽车工业学院 | Improved hybrid A-x algorithm unmanned vehicle path planning and trajectory tracking method |
| CN113479105A (en) * | 2021-07-20 | 2021-10-08 | 钟求明 | Intelligent charging method and intelligent charging station based on automatic driving vehicle |
| CN113532458A (en) * | 2021-06-23 | 2021-10-22 | 厦门大学 | Path searching method based on AStar algorithm |
| CN113804207A (en) * | 2020-09-14 | 2021-12-17 | 北京京东乾石科技有限公司 | Vehicle path planning method, system, equipment and storage medium |
| CN114286383A (en) * | 2021-12-27 | 2022-04-05 | 中国联合网络通信集团有限公司 | Network quality determination method, device and storage medium |
| CN117073688A (en) * | 2023-10-16 | 2023-11-17 | 泉州装备制造研究所 | Coverage path planning method based on multi-layer cost map |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100332436A1 (en) * | 2009-06-29 | 2010-12-30 | International Business Machines Corporation | Multi-pairs shortest path finding method and system |
| CN103679264A (en) * | 2013-12-23 | 2014-03-26 | 山东师范大学 | Crowd evacuation path planning method based on artificial fish swarm algorithm |
| CN105867381A (en) * | 2016-04-25 | 2016-08-17 | 广西大学 | Industrial robot path search optimization algorithm based on probability map |
-
2018
- 2018-02-05 CN CN201810112446.1A patent/CN108444488B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100332436A1 (en) * | 2009-06-29 | 2010-12-30 | International Business Machines Corporation | Multi-pairs shortest path finding method and system |
| CN103679264A (en) * | 2013-12-23 | 2014-03-26 | 山东师范大学 | Crowd evacuation path planning method based on artificial fish swarm algorithm |
| CN105867381A (en) * | 2016-04-25 | 2016-08-17 | 广西大学 | Industrial robot path search optimization algorithm based on probability map |
Non-Patent Citations (5)
| Title |
|---|
| DIDIER DEVAURS 等: "Optimal Path Planning in Complex Cost Spaces With Sampling-Based Algorithms", 《IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING》 * |
| JUAN DU 等: "Research on path planning algorithm based on security patrol robot", 《2016 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION》 * |
| 刘蕾: "室内环境下移动机器人路径规划", 《中国优秀硕士学位论文全文数据库》 * |
| 李冲 等: "基于方向约束的A*算法", 《控制与决策》 * |
| 潘允辉: "基于GIS的无人地面车辆路径规划技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (73)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108896052A (en) * | 2018-09-20 | 2018-11-27 | 鲁东大学 | A kind of mobile robot smooth paths planing method under the environment based on DYNAMIC COMPLEX |
| CN109238270A (en) * | 2018-10-21 | 2019-01-18 | 浙江浙大中控信息技术有限公司 | Intelligent navigation method based on improved A star algorithm |
| CN109374004A (en) * | 2018-11-12 | 2019-02-22 | 智慧航海（青岛）科技有限公司 | A kind of Intelligent unattended ship paths planning method based on IA* algorithm |
| WO2020102987A1 (en) * | 2018-11-20 | 2020-05-28 | 深圳大学 | Intelligent assisted driving method and system |
| CN109634304A (en) * | 2018-12-13 | 2019-04-16 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Unmanned plane during flying paths planning method, device and storage medium |
| CN109634304B (en) * | 2018-12-13 | 2022-07-15 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Unmanned aerial vehicle flight path planning method and device and storage medium |
| CN109798909A (en) * | 2019-02-01 | 2019-05-24 | 安徽达特智能科技有限公司 | A kind of method of global path planning |
| CN109945882A (en) * | 2019-03-27 | 2019-06-28 | 上海交通大学 | A kind of automatic driving vehicle path planning and control system and method |
| CN110032187A (en) * | 2019-04-09 | 2019-07-19 | 清华大学 | Unmanned motor static-obstacle obstacle-avoiding route planning calculation method |
| CN110032187B (en) * | 2019-04-09 | 2020-08-28 | 清华大学 | Unmanned motorcycle static obstacle avoidance path planning calculation method |
| CN110333714A (en) * | 2019-04-09 | 2019-10-15 | 武汉理工大学 | A kind of pilotless automobile paths planning method and device |
| CN110333714B (en) * | 2019-04-09 | 2022-06-10 | 武汉理工大学 | Unmanned vehicle path planning method and device |
| CN111857112A (en) * | 2019-04-12 | 2020-10-30 | 广州汽车集团股份有限公司 | Automobile local path planning method and electronic equipment |
| CN111857112B (en) * | 2019-04-12 | 2023-11-14 | 广州汽车集团股份有限公司 | Automobile local path planning method and electronic equipment |
| CN109945885A (en) * | 2019-04-16 | 2019-06-28 | 清华大学 | The dynamic barrier obstacle-avoiding route planning calculation method of unmanned motor |
| CN111912407B (en) * | 2019-05-08 | 2022-05-17 | 胡贤良 | Path planning method of multi-robot system |
| CN111912407A (en) * | 2019-05-08 | 2020-11-10 | 胡贤良 | Path planning method of multi-robot system |
| CN110220528A (en) * | 2019-06-10 | 2019-09-10 | 福州大学 | A kind of two-way dynamic path planning method of automatic Pilot unmanned vehicle based on A star algorithm |
| CN110333659B (en) * | 2019-07-15 | 2020-04-28 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned vehicle local path planning method based on improved A star search |
| CN110333659A (en) * | 2019-07-15 | 2019-10-15 | 中国人民解放军军事科学院国防科技创新研究院 | A kind of pilotless automobile local paths planning method based on improvement A star search |
| CN110398250B (en) * | 2019-08-13 | 2022-01-11 | 哈尔滨工程大学 | Unmanned ship global path planning method |
| CN110398250A (en) * | 2019-08-13 | 2019-11-01 | 哈尔滨工程大学 | A kind of unmanned boat global path planning method |
| CN110609547A (en) * | 2019-08-21 | 2019-12-24 | 中山大学 | Mobile robot planning method based on visual map guidance |
| CN110531782A (en) * | 2019-08-23 | 2019-12-03 | 西南交通大学 | Unmanned aerial vehicle flight path paths planning method for community distribution |
| CN112764413A (en) * | 2019-10-22 | 2021-05-07 | 广州中国科学院先进技术研究所 | Robot path planning method |
| CN112764413B (en) * | 2019-10-22 | 2024-01-16 | 广州中国科学院先进技术研究所 | Robot path planning method |
| CN110595482A (en) * | 2019-10-28 | 2019-12-20 | 深圳市银星智能科技股份有限公司 | Path planning method and device with obstacle avoidance weight and electronic equipment |
| CN110836671B (en) * | 2019-11-14 | 2021-09-14 | 北京京邦达贸易有限公司 | Trajectory planning method, trajectory planning device, storage medium, and electronic apparatus |
| CN110836671A (en) * | 2019-11-14 | 2020-02-25 | 北京京邦达贸易有限公司 | Trajectory planning method, trajectory planning device, storage medium, and electronic apparatus |
| CN110806218A (en) * | 2019-11-29 | 2020-02-18 | 北京京东乾石科技有限公司 | Parking path planning method, device and system |
| CN110806218B (en) * | 2019-11-29 | 2021-09-07 | 北京京东乾石科技有限公司 | Parking path planning method, device and system |
| CN110967032B (en) * | 2019-12-03 | 2022-01-04 | 清华大学 | Real-time planning method for local driving route of unmanned vehicle in field environment |
| CN110967032A (en) * | 2019-12-03 | 2020-04-07 | 清华大学 | Real-time planning method for local driving route of unmanned vehicle in field environment |
| CN110908386A (en) * | 2019-12-09 | 2020-03-24 | 中国人民解放军军事科学院国防科技创新研究院 | Layered path planning method for unmanned vehicle |
| CN113052350A (en) * | 2019-12-26 | 2021-06-29 | 浙江吉利汽车研究院有限公司 | Path planning method and device, electronic equipment and storage medium |
| CN113124849A (en) * | 2019-12-30 | 2021-07-16 | 广东博智林机器人有限公司 | Indoor path planning method and device, electronic equipment and storage medium |
| CN113124849B (en) * | 2019-12-30 | 2023-11-14 | 广东博智林机器人有限公司 | Indoor path planning method and device, electronic equipment and storage medium |
| CN111158366B (en) * | 2019-12-31 | 2021-11-05 | 湖南大学 | Path planning method based on graph search and geometric curve fusion |
| CN111158366A (en) * | 2019-12-31 | 2020-05-15 | 湖南大学 | Path planning method based on graph search and geometric curve fusion |
| CN111060108A (en) * | 2019-12-31 | 2020-04-24 | 江苏徐工工程机械研究院有限公司 | Path planning method and device and engineering vehicle |
| CN111060108B (en) * | 2019-12-31 | 2021-10-12 | 江苏徐工工程机械研究院有限公司 | Path planning method and device and engineering vehicle |
| CN111076736A (en) * | 2020-01-02 | 2020-04-28 | 清华大学 | Vehicle-mounted system based on FPGA design and A star path searching method |
| CN111076736B (en) * | 2020-01-02 | 2020-10-27 | 清华大学 | Vehicle-mounted system based on FPGA design and A star path searching method |
| CN111196560A (en) * | 2020-01-03 | 2020-05-26 | 山东大学 | Method and system for dynamically adjusting dangerous area range of bridge crane |
| CN111196560B (en) * | 2020-01-03 | 2020-10-20 | 山东大学 | Method and system for dynamically adjusting dangerous area range of bridge crane |
| CN111307156A (en) * | 2020-03-09 | 2020-06-19 | 中振同辂(江苏)机器人有限公司 | Coverage path planning method suitable for vehicle-shaped robot |
| CN111427346A (en) * | 2020-03-09 | 2020-07-17 | 中振同辂(江苏)机器人有限公司 | Local path planning and tracking method suitable for vehicle-shaped robot |
| CN111487975A (en) * | 2020-04-30 | 2020-08-04 | 畅加风行(苏州)智能科技有限公司 | Intelligent networking system-based automatic port truck formation method and system |
| CN111693050A (en) * | 2020-05-25 | 2020-09-22 | 电子科技大学 | Indoor medium and large robot navigation method based on building information model |
| CN111857148B (en) * | 2020-07-28 | 2022-04-29 | 湖南大学 | Unstructured road vehicle path planning method |
| CN111857148A (en) * | 2020-07-28 | 2020-10-30 | 湖南大学 | Unstructured road vehicle path planning method |
| CN111679692A (en) * | 2020-08-04 | 2020-09-18 | 上海海事大学 | Unmanned aerial vehicle path planning method based on improved A-star algorithm |
| CN111897365A (en) * | 2020-08-27 | 2020-11-06 | 中国人民解放军国防科技大学 | Autonomous vehicle three-dimensional path planning method for contour line guide line |
| CN111897365B (en) * | 2020-08-27 | 2022-09-02 | 中国人民解放军国防科技大学 | Autonomous vehicle three-dimensional path planning method for contour line guide line |
| CN113804207A (en) * | 2020-09-14 | 2021-12-17 | 北京京东乾石科技有限公司 | Vehicle path planning method, system, equipment and storage medium |
| CN113286985A (en) * | 2020-09-17 | 2021-08-20 | 华为技术有限公司 | Path planning method and path planning device |
| CN112612266A (en) * | 2020-12-04 | 2021-04-06 | 湖南大学 | Unstructured road global path planning method and system |
| CN112612266B (en) * | 2020-12-04 | 2022-04-01 | 湖南大学 | Unstructured road global path planning method and system |
| CN112700668B (en) * | 2020-12-22 | 2022-08-02 | 北京百度网讯科技有限公司 | Remote control method for automatic driving, automatic driving vehicle and cloud equipment |
| CN112700668A (en) * | 2020-12-22 | 2021-04-23 | 北京百度网讯科技有限公司 | Remote control method for automatic driving, automatic driving vehicle and cloud equipment |
| CN112764418B (en) * | 2020-12-25 | 2024-04-02 | 珠海一微半导体股份有限公司 | Cleaning entrance position determining method based on path searching cost, chip and robot |
| CN112764418A (en) * | 2020-12-25 | 2021-05-07 | 珠海市一微半导体有限公司 | Clean entrance position determination method based on path finding cost, chip and robot |
| CN112783166A (en) * | 2020-12-30 | 2021-05-11 | 深兰人工智能(深圳)有限公司 | Local trajectory planning method and device, electronic equipment and storage medium |
| CN112923940A (en) * | 2021-01-11 | 2021-06-08 | 珠海格力电器股份有限公司 | Path planning method, device, processing equipment, mobile equipment and storage medium |
| CN113031599A (en) * | 2021-03-02 | 2021-06-25 | 珠海市一微半导体有限公司 | Robot rapid seat finding method with dynamically changed reference point, chip and robot |
| CN113031599B (en) * | 2021-03-02 | 2024-05-07 | 珠海一微半导体股份有限公司 | Method for quickly locating robot with dynamically changed reference point, chip and robot |
| CN113119995A (en) * | 2021-03-11 | 2021-07-16 | 京东鲲鹏(江苏)科技有限公司 | Path searching method and device, equipment and storage medium |
| CN113532458A (en) * | 2021-06-23 | 2021-10-22 | 厦门大学 | Path searching method based on AStar algorithm |
| CN113359757A (en) * | 2021-06-30 | 2021-09-07 | 湖北汽车工业学院 | Improved hybrid A-x algorithm unmanned vehicle path planning and trajectory tracking method |
| CN113479105A (en) * | 2021-07-20 | 2021-10-08 | 钟求明 | Intelligent charging method and intelligent charging station based on automatic driving vehicle |
| CN114286383A (en) * | 2021-12-27 | 2022-04-05 | 中国联合网络通信集团有限公司 | Network quality determination method, device and storage medium |
| CN117073688A (en) * | 2023-10-16 | 2023-11-17 | 泉州装备制造研究所 | Coverage path planning method based on multi-layer cost map |
| CN117073688B (en) * | 2023-10-16 | 2024-03-29 | 泉州装备制造研究所 | Coverage path planning method based on multi-layer cost map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108444488B (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108444488A (en) | Based on etc. steps sample A* algorithms unmanned local paths planning method | |
| CN107702716B (en) | Unmanned driving path planning method, system and device | |
| CN108698595B (en) | For controlling the method for vehicle movement and the control system of vehicle | |
| Li et al. | Path planning based on combinaion of improved A-STAR algorithm and DWA algorithm | |
| CN106926844A (en) | A kind of dynamic auto driving lane-change method for planning track based on real time environment information | |
| CN110488802A (en) | A kind of automatic driving vehicle dynamic behaviour decision-making technique netted under connection environment | |
| CN113932823A (en) | Unmanned multi-target-point track parallel planning method based on semantic road map | |
| Thornton et al. | Value sensitive design for autonomous vehicle motion planning | |
| CN112577506B (en) | Automatic driving local path planning method and system | |
| CN109115220B (en) | Method for parking lot system path planning | |
| CN114771563A (en) | Method for realizing planning control of track of automatic driving vehicle | |
| CN113608531A (en) | Unmanned vehicle real-time global path planning method based on dynamic window of safety A-guiding point | |
| CN110488842A (en) | A kind of track of vehicle prediction technique based on two-way kernel ridge regression | |
| WO2022173880A9 (en) | System, method, and computer program product for topological planning in autonomous driving using bounds representations | |
| CN113291318A (en) | Unmanned vehicle blind area turning planning method based on partially observable Markov model | |
| Chen et al. | Path planning for autonomous vehicle based on a two‐layered planning model in complex environment | |
| Yijing et al. | Local path planning of autonomous vehicles based on A* algorithm with equal-step sampling | |
| Zhang et al. | Structured road-oriented motion planning and tracking framework for active collision avoidance of autonomous vehicles | |
| Li et al. | Adaptive sampling-based motion planning with a non-conservatively defensive strategy for autonomous driving | |
| CN115840454B (en) | Multi-vehicle track collaborative planning method and device for unstructured road conflict area | |
| Yu et al. | RDT-RRT: Real-time double-tree rapidly-exploring random tree path planning for autonomous vehicles | |
| Park et al. | Path generation algorithm based on crash point prediction for lane changing of autonomous vehicles | |
| CN115826586B (en) | Path planning method and system integrating global algorithm and local algorithm | |
| CN108896065A (en) | A kind of automobile paths planning method, system, equipment and computer storage medium | |
| Chen et al. | Framework of active obstacle avoidance for autonomous vehicle based on hybrid soft actor-critic algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |