CN103295080A - Three-dimensional path programming method based on elevation diagram and ant colony foraging - Google Patents
Three-dimensional path programming method based on elevation diagram and ant colony foraging Download PDFInfo
- Publication number
- CN103295080A CN103295080A CN2013102351239A CN201310235123A CN103295080A CN 103295080 A CN103295080 A CN 103295080A CN 2013102351239 A CN2013102351239 A CN 2013102351239A CN 201310235123 A CN201310235123 A CN 201310235123A CN 103295080 A CN103295080 A CN 103295080A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- ant
- point
- environment
- grid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention belongs to the technical field of artificial intelligence robots, particularly to a three-dimensional path programming method based on an elevation diagram and ant colony foraging. The three-dimensional path programming method based on the elevation diagram and the ant colony foraging comprises firstly performing three-dimensional model establishing on three-dimensional space through an abstract modeling method, performing smoothing process on the surface of the established three-dimensional model to enable established three-dimensional terrain to be close to the requirement of the true environment as much as possible; secondly performing collection of relevant data information and the like on the established three-dimensional terrain through an elevation modeling method and establishing the elevation diagram three-dimensional environment; and finally combining the ant colony foraging method and the established elevation diagram environment to find an optimal three-dimensional path and proving through a simulation diagram finally. The three-dimensional path programming method based on the elevation diagram and the ant colony foraging solves the problem that the three-dimensional environment in the existing non-structural environment is complex and changeable.
Description
One, technical field:
The invention belongs to the artificial intelligence robot technical field, be specifically related to a kind of three-dimensional path planning method of seeking food based on elevation map and ant group.
Two, background technology:
At the research of the path planning of unmanned car, the modeling in the three dimensions path planning with keep away barrier
Algorithm become problem demanding prompt solution instantly.The great potential that some domestic colleges and universities and research institution notice this field has begun the research of this respect.Developed ATB-1(Autonomous Test Bed-1 during " eight or five "), by Tsing-Hua University, the National University of Defense technology, Zhejiang University, Beijing Institute of Technology, Institutes Of Technology Of Nanjing's joint research and development.Under 863 special supports, Tsing-Hua University has developed the outer intelligent mobile robot experiment porch (THM R-V) of multifunctional room, Shanghai Communications University has developed 211AMCTB and Frontier-ITM mobile platform, the unmanned car platform in " light of spring " ground of Shanghai Tongji University, the unmanned car platform of the red flag HQ-3 of a Chinese vapour and National University of Defense technology's joint research and development.And also have a lot of mechanisms doing a large amount of work aspect the unmanned car and obtaining a lot of scientific payoffss abroad." ripsaw " of AUS HoweandHowe company (Ripsaw-MSI) unmanned car platform for example, U.S. Ka Naiji. Mei Long university development and Application is in (Gladiator) unmanned car platform of U. S. Marine Corps " wrestler ".
Three, summary of the invention:
The invention provides and a kind ofly seek the three-dimensional path planning method of food based on elevation map and ant group, to overcome three-dimensional environment shortcoming complicated and changeable in non-structure environment.
For achieving the above object, the technical solution used in the present invention is: seek the three-dimensional path planning method of food based on elevation map and ant group, it is characterized in that: this method may further comprise the steps:
(1) utilizes the three-dimensional simulated environment of abstract modeling method construct;
(2) three dimensions with structure carries out surperficial smooth treatment;
(3) utilize elevation mathematical modeling method that the dimensional topography of having set up is carried out data acquisition, and form the three-dimensional space environment of elevation map;
(4) the ant group is sought the food method and operate in respectively in elevation map environment and the abstract modeling three-dimensional environment, obtain optimal path.
The concrete steps of described performing step (1) are: under the matlab environment, carry out the three-dimensional environment modeling, at first the summit in the three-dimensional map lower left corner as three-dimensional true origin
O, the point
OIn set up three-dimensional system of coordinate, wherein,
xAxle is the direction that increases along longitude,
yAxle is the direction that increases along latitude,
zAxle is perpendicular to the sea level direction; In this coordinate system with point
OBe the summit, the edge
xDirection of principal axis is got the maximum length of three-dimensional map
ON, the edge
yDirection of principal axis is got the maximum length of three-dimensional map
OO ', the edge
zDirection of principal axis is got three-dimensional maximum length
OP, constructed the cube zone that comprises three-dimensional map
OPMN-O ' P ' M ' N ', this zone is the planning space of three-dimensional path.
The concrete steps of described performing step (2) are: import following steps in the matlab environment:
pause(3)
surfl(x1,y1,z)
shading interp
colormap pink
Smooth treatment can be carried out in the three dimensions surface of structure.
The concrete steps of described performing step (3) are:
One group of data supposing the collection of three-dimensional laser range measurement system are
w i =
w 1,
w 2...,
w n ,
XyBe the three-dimensional rectangular coordinate of arbitrary laser spots, the corresponding variance of data is
σ i 2=
σ 1 2,
σ 2 2...,
σ n 2,
σ i 2Be the variance of corresponding laser spots, before making up the elevation map environment, will
XyThe plane on average is divided into a plurality of grids
C Ij ,
iWith
jExpression grid numbering, and in grid the index of storage 8 grids around it, consider memory space, noise sensitivity and follow-up path planning, lattice dimensions is set to approximate the robot longest edge long;
Laser spots is corresponded in the corresponding grid,
XyThe distribution function of laser spots is approximately normal distribution on the plane:
Wherein,
w i Xy Be laser spots
x,
yCoordinate;
σ i Xy For
xWith
yVariance;
The effective coverage of laser spots is decided to be
xWith
y3 times of standard deviation scopes of direction, laser spots
iTo 8 grids are all influential on every side, namely the parameter of these 8 grids all with laser spots
iRelevant, according to two-dimentional normal distribution formula:
Calculate laser to the influence degree of grid;
If laser spots
Be grid
C Ij hIndividual, point
w i To grid
C Ij Factor of influence be
Wherein, x
+, x
-, y
+And y
-Being the grid scope, is constant, so get in calculating
μ∝
N(
p i Xy ,
σ i Xy ), to grid
C Ij In each
μCarry out normalization and handle, the height value of grid is the weighted mean of all laser spots height in the grid, namely
S μ Factor of influence sum for laser spots in the grid.
The concrete steps of described performing step (4) are:
Step 1: ant begins search, and according to ant group hunting strategy: when ant moves to next point from current point, calculate the selection probability of each point in the viewing area according to heuristic function, heuristic function is
（5）
Ant is at plane ∏
i On current point
p i Select plane ∏
i+ 1
Go up next point
p i+ 1
:
Wherein, τ
a+ 1,
u,
v Be plane ∏
i+ 1
Last point
p(
i+ 1,
u,
v) the pheromones value;
Step 2: pheromones is upgraded: in the three-dimensional environment modeling whole search volume from
Loose and be a series of 3 d-dem point
w i =
w 1,
w 2...,
w n ; described discrete point is sought the node that the food method need be searched for for the ant group, pheromones is stored in the discrete point of model, and each point that looses has the value of a pheromones; the size representative of this dot information element is to the attraction degree of ant, and the each point pheromones is upgraded after every ant process;
The renewal of described pheromones comprises local updating and overall situation renewal two parts,
Described local updating is to increase the ant search not through the probability of point, reaches global search
Purpose, local message is plain to be upgraded along with the search of ant is carried out, pheromones more new formula is
The described overall situation is upgraded and is referred to when ant is finished the search of a paths, with this path
Length is selected shortest path as evaluation of estimate from set of paths, increase the pheromones value of each node of shortest path, and pheromones more new formula is as follows:
（8）
After finishing global path planning, the optimum road that the ant group will select in set of paths
Directly.
Compared with prior art, the advantage and the effect that have of the present invention is as follows:
1, compares and general modeling method, can in different three dimensions path circumstances, find optimal path faster.
2, the three-dimensional environment of complexity can be carried out dimension-reduction treatment, significantly reduce data space and improve arithmetic speed.
Four, description of drawings:
Fig. 1 is the inventive method overview flow chart;
Fig. 2 is the three-dimensional mountain region of the present invention flat road surface illustraton of model;
Fig. 3 is the uneven road surface model figure in the three-dimensional mountain region of the present invention;
Fig. 4 handles figure for the three-dimensional mountain region of the present invention flat road surface smooth surface;
Fig. 5 is the three-dimensional mountain region of the present invention uneven road surface smooth treatment figure;
Fig. 6 is the left view of the three-dimensional mountain region of the present invention elevation map;
Fig. 7 is the aerial view of the three-dimensional mountain region of the present invention elevation map;
Fig. 8 seeks the food method at the path planning figure of three-dimensional mountain region flat road surface for ant group of the present invention;
Fig. 9 seeks the food method at the path planning figure on uneven road surface, three-dimensional mountain region for ant group of the present invention;
Figure 10 seeks the path planning left view of food method in the elevation map environment for ant group of the present invention;
Figure 11 seeks the path planning aerial view of food method in the elevation map environment for ant group of the present invention;
Five, embodiment:
The present invention is described in detail below in conjunction with the drawings and specific embodiments:
The present invention is based on the three-dimensional path planning method that elevation map and ant group seek food may further comprise the steps:
1, utilizes the three-dimensional simulated environment of abstract modeling method construct, (flat road surface and uneven road surface)
Based on experimental requirements, under the matlab environment, carry out the three-dimensional environment modeling, at first the summit in the three-dimensional map lower left corner as three-dimensional true origin
O, the point
OIn set up three-dimensional system of coordinate, wherein,
xAxle is the direction that increases along longitude,
yAxle is the direction that increases along latitude,
zAxle is perpendicular to the sea level direction.In this coordinate system with point
OBe the summit, the edge
xDirection of principal axis is got the maximum length of three-dimensional map
ON, the edge
yDirection of principal axis is got the maximum length of three-dimensional map
OO ', the edge
zDirection of principal axis is got three-dimensional maximum length
OP, so just constructed the cube zone that comprises three-dimensional map
OPMN-O ' P ' M ' N ', this zone is the planning space of three-dimensional path.Setting up a regional span is that 20km*20km carries out simulation modeling, get in this zone minimum point 0 and be sea level altitude, 600m be taken as sea level elevation be this zone in main land level, other some height bases and minimum point difference in height obtain successively, the three-dimensional mountain region of the emulation that forms environment is referring to Fig. 3.We remain unchanged set sea level altitude point and main land planar point in the above regional span of setting up and the zone, in x direction of principal axis 5km ~ 9km scope, change the z axle into 600m perpendicular to sea level altitude, in y direction of principal axis 3km ~ 19km scope, change the z axle into 600m perpendicular to sea level altitude, utilize abstract modeling to form a flat road surface, referring to Fig. 2.
2, the three dimensions of structure is carried out the smooth treatment on surface; (flat road surface and uneven road surface)
In concrete matlab environment, import following steps:
pause(3)
surfl(x1,y1,z)
shading interp
colormap pink
Namely three-dimensional mountain region flat road surface and the uneven road surface grid environment figure that has set up carried out the smooth surface processing, participates in Fig. 4, Fig. 5.
3, utilize elevation mathematical modeling method that the dimensional topography of having set up is carried out data acquisition, and form the three-dimensional space environment of elevation map, referring to Fig. 6 and Fig. 7;
One group of data supposing the collection of three-dimensional laser range measurement system are
w i =
w 1,
w 2...,
w n ,
XyBe the three-dimensional rectangular coordinate of arbitrary laser spots, the corresponding variance of data is
σ i 2=
σ 1 2,
σ 2 2...,
σ n 2,
σ i 2Be the variance of corresponding laser spots, before making up the elevation map environment, will
XyThe plane on average is divided into a plurality of grids
C Ij ,
iWith
jExpression grid numbering, and in grid, stored its index of 8 grids on every side.Consider memory space, noise sensitivity and follow-up path planning, lattice dimensions is set to approximate the robot longest edge long.
Laser spots is corresponded in the corresponding grid,
XyThe distribution function of laser spots is approximately normal distribution on the plane:
Wherein,
w i Xy Be laser spots
x,
yCoordinate;
σ i Xy For
xWith
yVariance.
The effective coverage of laser spots is decided to be
xWith
y3 times of standard deviation scopes of direction, laser spots
iTo 8 grids are all influential on every side, namely the parameter of these 8 grids all with laser spots
iRelevant, according to two-dimentional normal distribution formula:
Calculate laser to the influence degree of grid.
If laser spots
Be grid
C Ij hIndividual, point
w i To grid
C Ij Factor of influence be
Wherein, x
+, x
-, y
+And y
-Being the grid scope, is constant, so get in calculating
μ∝
N(
p i Xy ,
σ i Xy ), to grid
C Ij In each
μCarry out normalization and handle, the height value of grid is the weighted mean of all laser spots height in the grid, namely
（4）
S μ Factor of influence sum for laser spots in the grid.
We are to the three-dimensional mountain region environment on the uneven road surface set up, referring to Fig. 3 number
According to collection, according to above step, form the three-dimensional mountain region figure of elevation map environment at last, referring to Fig. 6, Fig. 7.
4, the ant group is sought the food method and operate in respectively in elevation map environment and the abstract modeling three-dimensional environment, and demonstrate optimal path; Referring to Fig. 8, Fig. 9, Figure 10, Figure 11;
Step 1: ant begins search, and according to ant group hunting strategy: ant is moved from current point
During to next point, calculate the selection probability of each point in the viewing area according to heuristic function, heuristic function is
Ant is at plane ∏
i On current point
p i Select plane ∏
i+ 1
Go up next point
p i+ 1
:
Wherein, τ
a+ 1,
u,
v Be plane ∏
i+ 1
Last point
p(
i+ 1,
u,
v) the pheromones value.
Step 2: pheromones is upgraded: in the three-dimensional environment modeling whole search volume from
Loose and be a series of 3 d-dem point
w i =
w 1,
w 2...,
w n , these discrete points are sought the node that the food method need be searched for for the ant group.Therefore, pheromones is stored in the discrete point of model, each point that looses has the value of a pheromones, and the size representative of this dot information element is to the attraction degree of ant, and the each point pheromones is upgraded after every ant process;
The renewal of pheromones comprises local updating and overall situation renewal two parts, the purpose of local updating
Be to increase the ant search not through the probability of point, reach the purpose of global search.Local message is plain to be upgraded along with the search of ant is carried out, and pheromones more new formula is
The overall situation is upgraded and is referred to when ant is finished the search of a paths, does with the length in this path
Be evaluation of estimate, select shortest path from set of paths, increase the pheromones value of each node of shortest path, pheromones more new formula is as follows:
（8）
After finishing global path planning, the optimum road that the ant group will select in set of paths
Directly.
Claims (5)
1. seek the three-dimensional path planning method of food based on elevation map and ant group, it is characterized in that: this method may further comprise the steps:
(1) utilizes the three-dimensional simulated environment of abstract modeling method construct;
(2) three dimensions with structure carries out surperficial smooth treatment;
(3) utilize elevation mathematical modeling method that the dimensional topography of having set up is carried out data acquisition, and form the three-dimensional space environment of elevation map;
(4) the ant group is sought the food method and operate in respectively in elevation map environment and the abstract modeling three-dimensional environment, obtain optimal path.
2. a kind of three-dimensional path planning method of seeking food based on elevation map and ant group according to claim 1, it is characterized in that: the concrete steps of described performing step (1) are: under the matlab environment, carry out the three-dimensional environment modeling, at first the summit in the three-dimensional map lower left corner as three-dimensional true origin
O, the point
OIn set up three-dimensional system of coordinate, wherein,
xAxle is the direction that increases along longitude,
yAxle is the direction that increases along latitude,
zAxle is perpendicular to the sea level direction; In this coordinate system with point
OBe the summit, the edge
xDirection of principal axis is got the maximum length of three-dimensional map
ON, the edge
yDirection of principal axis is got the maximum length of three-dimensional map
OO ', the edge
zDirection of principal axis is got three-dimensional maximum length
OP, constructed the cube zone that comprises three-dimensional map
OPMN-O ' P ' M ' N ', this zone is the planning space of three-dimensional path.
3. according to claim 1 and 2ly a kind ofly seek the three-dimensional path planning method of food method based on elevation map and ant group, it is characterized in that: the concrete steps of described performing step (2) are: import following steps in the matlab environment:
pause(3)
surfl(x1,y1,z)
shading interp
colormap pink
Smooth treatment can be carried out in the three dimensions surface of structure.
4. according to claim 3ly a kind ofly seek the three-dimensional path planning method of food based on elevation map and ant group, it is characterized in that: the concrete steps of described performing step (3) are:
One group of data supposing the collection of three-dimensional laser range measurement system are
w i =
w 1,
w 2...,
w n ,
XyBe the three-dimensional rectangular coordinate of arbitrary laser spots, the corresponding variance of data is
σ i 2=
σ 1 2,
σ 2 2...,
σ n 2,
σ i 2Be the variance of corresponding laser spots, before making up the elevation map environment, will
XyThe plane on average is divided into a plurality of grids
C Ij ,
iWith
jExpression grid numbering, and in grid the index of storage 8 grids around it, consider memory space, noise sensitivity and follow-up path planning, lattice dimensions is set to approximate the robot longest edge long;
Laser spots is corresponded in the corresponding grid,
XyThe distribution function of laser spots is approximately normal distribution on the plane:
Wherein,
w i Xy Be laser spots
x,
yCoordinate;
σ i Xy For
xWith
yVariance;
The effective coverage of laser spots is decided to be
xWith
y3 times of standard deviation scopes of direction, laser spots
iTo 8 grids are all influential on every side, namely the parameter of these 8 grids all with laser spots
iRelevant, according to two-dimentional normal distribution formula:
Calculate laser to the influence degree of grid;
If laser spots
Be grid
C Ij hIndividual, point
w i To grid
C Ij Factor of influence be
（3）
Wherein, x
+, x
-, y
+And y
-Being the grid scope, is constant, so get in calculating
μ∝
N(
p i Xy ,
σ i Xy ), to grid
C Ij In each
μCarry out normalization and handle, the height value of grid is the weighted mean of all laser spots height in the grid, namely
S μ Factor of influence sum for laser spots in the grid.
5. according to claim 4ly a kind ofly seek the three-dimensional path planning method of food based on elevation map and ant group, it is characterized in that: the concrete steps of described performing step (4) are:
Step 1: ant begins search, and according to ant group hunting strategy: when ant moves to next point from current point, calculate the selection probability of each point in the viewing area according to heuristic function, heuristic function is
Ant is at plane ∏
i On current point
p i Select plane ∏
i+ 1
Go up next point
p i+ 1
:
（6）
Wherein, τ
a+ 1,
u,
v Be plane ∏
i+ 1
Last point
p(
i+ 1,
u,
v) the pheromones value;
Step 2: pheromones is upgraded: in the three-dimensional environment modeling whole search volume from
Loose and be a series of 3 d-dem point
w i =
w 1,
w 2...,
w n ; described discrete point is sought the node that the food method need be searched for for the ant group, pheromones is stored in the discrete point of model, and each point that looses has the value of a pheromones; the size representative of this dot information element is to the attraction degree of ant, and the each point pheromones is upgraded after every ant process;
The renewal of described pheromones comprises local updating and overall situation renewal two parts,
Described local updating is to increase the ant search not through the probability of point, reaches global search
Purpose, local message is plain to be upgraded along with the search of ant is carried out, pheromones more new formula is
The described overall situation is upgraded and is referred to when ant is finished the search of a paths, with this path
Length is selected shortest path as evaluation of estimate from set of paths, increase the pheromones value of each node of shortest path, and pheromones more new formula is as follows:
After finishing global path planning, the optimal path that the ant group will select in set of paths.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013102351239A CN103295080A (en) | 2013-06-14 | 2013-06-14 | Three-dimensional path programming method based on elevation diagram and ant colony foraging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013102351239A CN103295080A (en) | 2013-06-14 | 2013-06-14 | Three-dimensional path programming method based on elevation diagram and ant colony foraging |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103295080A true CN103295080A (en) | 2013-09-11 |
Family
ID=49095900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013102351239A Pending CN103295080A (en) | 2013-06-14 | 2013-06-14 | Three-dimensional path programming method based on elevation diagram and ant colony foraging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103295080A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103472828A (en) * | 2013-09-13 | 2013-12-25 | 桂林电子科技大学 | Mobile robot path planning method based on improvement of ant colony algorithm and particle swarm optimization |
| CN103473956A (en) * | 2013-09-17 | 2013-12-25 | 中国民航大学 | Three-dimensional arrival-departure airline network optimization method based on ant colony algorithm improvement for terminal area |
| CN104199292A (en) * | 2014-08-11 | 2014-12-10 | 大连大学 | Method for planning space manipulator tail end effector avoidance path based on ant colony algorithm |
| CN105116785A (en) * | 2015-06-26 | 2015-12-02 | 北京航空航天大学 | Multi-platform remote robot general control system |
| CN106873599A (en) * | 2017-03-31 | 2017-06-20 | 深圳市靖洲科技有限公司 | Unmanned bicycle paths planning method based on ant group algorithm and polar coordinate transform |
| CN106970620A (en) * | 2017-04-14 | 2017-07-21 | 安徽工程大学 | A kind of robot control method based on monocular vision |
| CN110597276A (en) * | 2018-06-11 | 2019-12-20 | 中国科学院光电研究院 | Remote planning method for unmanned aerial vehicle aerial safety corridor path |
| CN112270752A (en) * | 2020-10-29 | 2021-01-26 | 久瓴(上海)智能科技有限公司 | Agriculture and forestry work path generation method and device, computer equipment and storage medium |
| CN113894787A (en) * | 2021-10-31 | 2022-01-07 | 哈尔滨工业大学 | Heuristic reward function design method used in mechanical arm reinforcement learning motion planning |
-
2013
- 2013-06-14 CN CN2013102351239A patent/CN103295080A/en active Pending
Non-Patent Citations (4)
| Title |
|---|
| 田鑫: "蚁群算法的移动机器人三维路径规划", 《豆丁网HTTP://WWW.DOCIN.COM/P-382576168.HTML》 * |
| 闫飞等: "基于拓扑高程模型的室外三维环境建模与路径规划", 《自动化学报》 * |
| 陈航: "移动机器人三维环境建模与自主运动规划", 《中国优秀硕士学位论文全文数据库 信息科学辑》 * |
| 陈航: "移动机器人三维环境建模与自主运动规划", 《中国优秀硕士学位论文全文数据库 信息科学辑》, no. 07, 15 July 2010 (2010-07-15), pages 140 - 234 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103472828A (en) * | 2013-09-13 | 2013-12-25 | 桂林电子科技大学 | Mobile robot path planning method based on improvement of ant colony algorithm and particle swarm optimization |
| CN103473956A (en) * | 2013-09-17 | 2013-12-25 | 中国民航大学 | Three-dimensional arrival-departure airline network optimization method based on ant colony algorithm improvement for terminal area |
| CN103473956B (en) * | 2013-09-17 | 2015-05-27 | 中国民航大学 | Three-dimensional arrival-departure airline network optimization method based on ant colony algorithm improvement for terminal area |
| CN104199292A (en) * | 2014-08-11 | 2014-12-10 | 大连大学 | Method for planning space manipulator tail end effector avoidance path based on ant colony algorithm |
| CN105116785A (en) * | 2015-06-26 | 2015-12-02 | 北京航空航天大学 | Multi-platform remote robot general control system |
| CN105116785B (en) * | 2015-06-26 | 2018-08-24 | 北京航空航天大学 | A kind of multi-platform tele-robotic general-purpose control system |
| CN106873599A (en) * | 2017-03-31 | 2017-06-20 | 深圳市靖洲科技有限公司 | Unmanned bicycle paths planning method based on ant group algorithm and polar coordinate transform |
| CN106970620A (en) * | 2017-04-14 | 2017-07-21 | 安徽工程大学 | A kind of robot control method based on monocular vision |
| CN110597276A (en) * | 2018-06-11 | 2019-12-20 | 中国科学院光电研究院 | Remote planning method for unmanned aerial vehicle aerial safety corridor path |
| CN112270752A (en) * | 2020-10-29 | 2021-01-26 | 久瓴(上海)智能科技有限公司 | Agriculture and forestry work path generation method and device, computer equipment and storage medium |
| CN113894787A (en) * | 2021-10-31 | 2022-01-07 | 哈尔滨工业大学 | Heuristic reward function design method used in mechanical arm reinforcement learning motion planning |
| CN113894787B (en) * | 2021-10-31 | 2022-06-14 | 哈尔滨工业大学 | Heuristic reward function design method for mechanical arm reinforcement learning motion planning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103295080A (en) | Three-dimensional path programming method based on elevation diagram and ant colony foraging | |
| Yaoming et al. | A newly bio-inspired path planning algorithm for autonomous obstacle avoidance of UAV | |
| CN103994768B (en) | Method and system for seeking for overall situation time optimal path under dynamic time varying environment | |
| CN109814598A (en) | The public airway net design method in unmanned plane low latitude | |
| Sun et al. | AGV path planning based on improved Dijkstra algorithm | |
| CN102901500A (en) | Aircraft optimal path determination method based on mixed probability A star and agent | |
| CN108897312A (en) | Lasting supervised path planing method of more unmanned vehicles to extensive environment | |
| CN113776534B (en) | Unmanned aerial vehicle three-dimensional time-varying airspace navigation method based on three-dimensional subdivision grid | |
| CN108932876B (en) | Express unmanned aerial vehicle flight path planning method introducing black area A and ant colony hybrid algorithm | |
| CN106017472A (en) | Global path planning method, global path planning system and unmanned aerial vehicle | |
| CN104406589B (en) | Flight method of aircraft passing through radar area | |
| CN102496187B (en) | Method for tracking contour line to boundary and fault based on triangular mesh | |
| CN110471426A (en) | Unmanned intelligent vehicle automatic Collision Avoidance method based on quantum wolf pack algorithm | |
| CN109357678A (en) | A kind of multiple no-manned plane paths planning method based on heterogeneousization dove colony optimization algorithm | |
| CN106211256B (en) | A kind of Unmanned Aerial Vehicle Data collection method based on data critical node | |
| CN105067004B (en) | A kind of method for searching path based on landform | |
| CN107478233A (en) | A kind of geological prospecting path planning method and system | |
| CN105608276A (en) | Automatic powder transmission line path selection method and cellular automaton model | |
| CN104200295A (en) | Partition based multi-police-intelligent-agent task allocation method in RCRSS (Robo Cup Rescue Simulation System) | |
| Xu et al. | Iterative construction of low-altitude UAV air route network in urban areas: Case planning and assessment | |
| CN112462805A (en) | 5G networked unmanned aerial vehicle flight path planning method based on improved ant colony algorithm | |
| CN106780586A (en) | A kind of solar energy potential evaluation method based on ground laser point cloud | |
| CN115355922A (en) | Travel path planning method and system based on improved ant colony algorithm | |
| Li et al. | Multi-mechanism swarm optimization for multi-UAV task assignment and path planning in transmission line inspection under multi-wind field | |
| Han et al. | Research on UAV indoor path planning algorithm based on global subdivision grids |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130911 |
|
| RJ01 | Rejection of invention patent application after publication |