CN106708043B - A method of improving Visual Graph under complicated map - Google Patents
A method of improving Visual Graph under complicated map Download PDFInfo
- Publication number
- CN106708043B CN106708043B CN201611144910.2A CN201611144910A CN106708043B CN 106708043 B CN106708043 B CN 106708043B CN 201611144910 A CN201611144910 A CN 201611144910A CN 106708043 B CN106708043 B CN 106708043B
- Authority
- CN
- China
- Prior art keywords
- light
- map
- point
- barrier
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000000007 visual effect Effects 0.000 title claims abstract description 21
- 230000004888 barrier function Effects 0.000 claims abstract description 39
- 230000003287 optical effect Effects 0.000 claims abstract description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000007493 shaping process Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Game Theory and Decision Science (AREA)
- Electromagnetism (AREA)
- Automation & Control Theory (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Processing Or Creating Images (AREA)
Abstract
The method that the invention discloses a kind of to improve Visual Graph under complicated map, is allowed to be applicable not only to the map of convex polygonal obstacle, is also applied for the SLAM map of general complicated landform.Visual Graph is the path planning algorithm proposed in 1979, simulates light along this characteristic of straightline propagation, the angle point of beginning and end and convex polygonal obstacle is connected, constitutes path, but be also only limitted to convex polygonal obstacle.The present invention continues to use main thought, i.e. light is along straightline propagation, emit light from the beginning and end in path, by the reflection of barrier, the path of a connection source and terminal, the function of realizing route planning are finally obtained using optical path as carrier, rather than simply use barrier vertex line as carrier, it is also just not limited only to the barrier of convex polygon in this way, general complicated landform is all suitable for.
Description
Technical field
It is specifically a kind of for ground the present invention relates to a kind of path planning algorithm in intelligent robot motion planning field
The improvement of Visual Graph algorithm, makes it can not only be applied to the map of convex polygonal obstacle under the map of shape complexity
Under, it can also be used under complicated map.
Background technique
Instantly the robot system research for capableing of independent navigation avoidance is abnormal burning hot, and there are many products applications
In practice.Such as the service robot in restaurant, just possess obstacle recognition, the ability of path planning；For another example family's sweeping robot,
Also possess the ability that displacement path is planned in clearing.In terms of public transportation, the application of unmanned plane express delivery delivery
That has carried out is like a raging fire, path planning must be also used in express delivery delivery, so that unmanned plane can be in avoiding obstacles
Under the premise of arrived at the destination with shortest path and complete to deliver.
Path planning refers to the ability how robot decision moves to another point from the certain point of map.It requires first
Robot can obtain the cartographic information of current environment, and can position itself current position, then can just carry out path rule
Draw, position and build figure algorithm it is most practical at present be exactly SLAM algorithm.There are many path planning algorithms at present, such as RRT, PRM
Deng.
Visual Graph is also common path planning algorithm, but it has stringent limitation using to map, it is desirable that
If the barrier convex polygon of map, and the apex coordinate of each barrier is it is known that then connect the top of each barrier
Point, and using these lines as carrier, generate path.But in practical application scene, landform be it is sufficiently complex, in map
Barrier shape is irregular, and its apex coordinate is also unknown, therefore directly to utilize Visual Graph algorithm
It is infeasible.The existing method for solving the problems, such as this is that map is pre-processed first, using morphological method, is such as divided
Water ridge algorithm, Feature Correspondence Algorithm etc., can extract the boundary of the characteristic point or barrier in map, acquired disturbance object it is big
Shape is caused, and each characteristic point is connected with straight line, converts a convex polygon for barrier, reapplies Visual Graph calculation
Method.The calculation amount of this method is not small, and the additional algorithm being related to is more, and efficiency is difficult to estimate, and is transformed into barrier at it
When convex polygon, a degree of expansion or corrosion can be carried out to the edge of barrier, may cause is not barrier originally in map
Hindering the region of object becomes barrier, is that the region of barrier becomes and can pass through originally, finally obtained path may be made illegal.
Summary of the invention
Technology of the invention solves the problems, such as: overcoming the rigid requirement of original Visual Graph to map, proposes one kind
The method that Visual Graph is improved under complicated map, makes it no longer be only limitted to the map of convex polygonal obstacle, in complexity
SLAM map under can also run, and pre-process without to map, the density parameter of node is also easy to adjust, with life
At accurate path.
Technical solution of the invention: a method of improving Visual Graph under complicated map, feature exists
In: Visual Graph can be made to may not only be applied to the map of convex polygonal obstacle, it can also be with to general SLAM map
It is applicable in, its step are as follows:
Step 1: to map is converted, and map binary conversion treatment constructed by grayscale image or SLAM is converted
Map afterwards, this process are known as map binarization；
Step 2: for the map after conversion, beginning and end is given, beginning and end is stored in a sequence list,
And emit light since beginning and end, index path is begun setting up, this process is known as initialization procedure；
Step 3: when light touches barrier, recording the coordinate of the point of impingement, and ask with node existing in sequence list
Distance is taken, gives up the point if less than one threshold value of distance, otherwise retains, which is known as node store decision process；
Step 4: since the node of reservation, re-emitting light, and repeat the process of step 3, this process is known as repeating
Light emission process；
Step 5: when all light collision obstacles all can not generate new node, figure is built in judgement to be terminated；
Step 6: A* pathfinding algorithm is applied on the topological map built up, and can be obtained a connection source and terminal, with
Optical path is the path of carrier, this process is known as pathfinding process.
In the step 1, the method for the binaryzation of map are as follows:
It calls the library opencv to read in given map file, and converts a two-dimentional shaping array for map matrix, i.e.,
Indicate two-dimensional surface space, each of array element represents a pixel of corresponding coordinate on map, if the point is barrier
Hinder object point, then array value is set as 1, if the point is that array value can be set as 0 by point.
In the step 2, emit the method for light are as follows:
(1) for certain point, from 0 degree, i.e., direction starts to emit light every a fixed step-length horizontally to the right, until
Until 360 degree；
(2) for each direction, light is pushed ahead pixel-by-pixel, one pixel of every propulsion, it will detect the point whether be
3 can be entered step and sentenced by point, if can continue to promote if, if the point can not be recorded by indicating to encounter barrier
Disconnected process；
(3) if the light of a direction is apart from too small, then it represents that the direction and barrier very close to, be it is unreasonable,
If therefore light distance is less than a certain threshold value, the light of the direction will be rejected.
In the step 2, the method for storage node are as follows:
Two sequence lists are set, a sequence list allnode stores all nodes, i.e., it is emitted cross light with not yet
Emit all nodes of light, another sequence list open storage not yet emits the node of light.When initialization, by starting point and end
Point is all stored in two sequence lists.
In the step 3, the determination method of node store are as follows:
When light encounters barrier, all nodes in the point of impingement and allnode are sought into distance, if this is apart from small
In a certain threshold value, then give up the point, otherwise the point is added in allnode and open table.
In the step 4, the method that light emits is repeated are as follows:
An element of open gauge outfit is taken out, light emission process shown in step 2 is repeated.
In the step 5, the judgment method that figure terminates is built are as follows:
When the point of impingement of light and the barrier of the transmitting of a certain node with a little at a distance from be respectively less than threshold value when, then the section
Point will not generate new node, hereafter take out a point from open table again and carry out light transmitting, at this time the element of open table
Number will be reduced, and when open table is empty, that is, building figure process terminates.
The advantages of the present invention over the prior art are that:
(1) present invention continue to use the light straightline propagation thinking of primal algorithm, but breach primal algorithm can be only applied to it is convex
The limitation of polygon barrier map.It is using the point of impingement of light and blocking surfaces as node, i.e., similar in complicated map
Emit new light to generate more nodes, throughout the barrier of whole map in the vertex of convex polygon, and from the node
Surface, and path is formed by carrier of optical path, to map itself has no requirement；
(2) present invention is pre-processed without to map, and calculation amount is minimum.With the existing side for improving Visual Graph
Method is compared, and the prior art needs additional designs algorithm to carry out to map to be pre-processed, and is fitted with generating a convex polygon map
Original Visual Graph algorithm is answered, very huge calculation amount is increased.And to map of the present invention has no requirement, i.e.,
It is pre-processed without other algorithm for design to map to generate convex polygonal obstacle map, directly original place figure is grasped
Make, saves a large amount of calculation amounts, improve operational efficiency；
(3) every threshold parameter of the invention is all extremely easily adjusted, and compared with existing technical method, the prior art is needed
Blocking surfaces are expanded or corroded, the shape of barrier is made to become regular uniform, original Visual is adapted to this
Usually there is the illegal situation for passing through barrier in Graph algorithm, resulting path.And the present invention can be with by adjusting threshold parameter
Obtain a more accurate, legal path, without to barrier edge corrosion or expansion, not will lead to the barrier in map
Point is corroded as that can pass through a little, can be expanded to obstacle object point by point, resulting path is accurate and legal.
Detailed description of the invention
Fig. 1 is original Visual Graph algorithm effect；
Fig. 2 is the flow chart of the method for the present invention；
Fig. 3 is effect picture of the present invention.
Specific embodiment
The present invention is generally used in the map of slam algorithm foundation, is actual landform, complex.
As shown in Fig. 2, detailed description are as follows for specific implementation step of the present invention:
Step 1: with slam algorithm or other build nomography obtain current environment cartographic information, with .pgm format
Picture is incoming, calls opencv library function that its binaryzation is obtained the matrix variables Mat of opencv, then convert it into one
Two-dimensional array, value are that 0 or 1,0 expression can pass through, and 1 indicates that, there are barrier, binarization is completed；
Step 2: given beginning and end, if being risen via the position where the location algorithms positioning robot such as SLAM
Point is that robot is currently located a little, and terminal is then target point.Beginning and end is placed in the sequence list of an entitled open first
In, as the node of light to be launched, while by the sequence list of their one entitled allnode of deposit, allnode is for storing up
Deposit the sequence list of all nodes.
Step 3: when open table non-empty, to originate 0 degree of the angle of departure, i.e. horizontal direction one point of taking-up since open table
Right transmitting light, when light encounters barrier not yet, light is pushed ahead pixel-by-pixel, one pixel of every propulsion, all right
Next pixel is detected, and if can continue to promote if, if can not be by indicating to encounter barrier, light stops at this time
Thrust is into and recording the point of impingement coordinate；
Step 4: the point of impingement is detected, if the point of impingement is issued with light is less than a certain threshold value at a distance from point,
It indicates the direction and barrier very and is close to, the light of the direction unreasonable, should give up.If light is reasonable, seek
The Euclidean distance of all elements in the point of impingement and allnode table, when its distance is less than a certain threshold value, then the point is given up, otherwise
Using the point as new preparation transmitting node, while it being stored in the table tail of open table and allnode table, and the node and light are sent out
It penetrates node and establishes connection, a pointer is respectively contained in the structural body for being implemented as two nodes of connection, enables two objects
The pointer coreference for being included, i.e. realization node connection, that is, the side in topological diagram；
Step 5: giving one step angle of launch angle, repeat the process of light transmitting, and light and barrier are touched
Hit the detection for carrying out step 4.The light transmitting of the point terminates if angle reaches 360 degree, step 3 is repeated, again from open
A point is taken out in table, repeats light transmitting；
Step 6: can not generate new node after the 360 degree of light transmitting of a certain light, then from this when open
Begin, the content of open table will be reduced, and when node all in open table all can not create new node, open table will be
Sky shows to build at this time figure completion, has obtained a topological map, and vertex is light launch point, side be node and node it
Between light connection；
Step 7: A* pathfinding algorithm is applied on resulting topological map, the heuristic cost of A* is set as light between node
The distance of line according to the heuristic rule of A*, until terminal, can be obtained the one of connection source and terminal from the off
Item is using optical path as the path of carrier.
It is the Visual Graph path planning algorithm before not improving such as Fig. 1, the map of application can only be as shown in the figure
, barrier is the map of convex polygon, and the vertex of each barrier requires it is known that by beginning and end and obstacle
Connection is established on the vertex of object from each other, then can be constituted the communication path from origin-to-destination to be connected as carrier.Road
The advantages of diameter, is that straightness is good, and turn number is few, thus speed loss when robot operation is small, but since it can only be used
On simple convex polygonal obstacle map, therefore it is difficult to apply in practical problem.
It is that the present invention improves later Visual Graph method effect, the dot in figure indicates light transmitting section such as Fig. 3
Point, filament indicates optical path, and heavy line indicates the path finally obtained.The present invention inherits the advantages of original method, that is, turns round
Number is less, and the speed loss of robot is small, and the disadvantage fatal the present invention overcomes original algorithm, allows to apply
In complicated map, and pretreatment operation is carried out without to map, greatly improves its application prospect in practical problem.
Claims (2)
1. a kind of method for improving Visual Graph under complicated map, it is characterised in that: Visual Graph can be made not
It is applied only for the map of convex polygonal obstacle, general SLAM map can also be applied, its step are as follows:
Step 1: to map is converted, by map binary conversion treatment constructed by grayscale image or SLAM, after being converted
Map, this process are known as map binarization；
Step 2: for the map after conversion, beginning and end is given, beginning and end is stored in a sequence list, and from
Beginning and end starts to emit light, begins setting up index path, this process is known as initialization procedure；
Step 3: when light touches barrier, the coordinate of the point of impingement is recorded, and seek distance with node existing in sequence list,
Give up the point if less than one threshold value of distance, otherwise retains, which is known as node store decision process；
Step 4: since the node of reservation, re-emitting light, and repeat the process of step 3, this process is known as repeating light
Emission process；
Step 5: when all light collision obstacles all can not generate new node, figure is built in judgement to be terminated；
Step 6: applying A* pathfinding algorithm on the topological map built up, can be obtained a connection source and terminal, with optical path
For the path of carrier, this process is known as pathfinding process；
In the step 1, the method for the binaryzation of map are as follows:
It calls the library opencv to read in given map file, and converts a two-dimentional shaping array for map matrix, that is, indicate
Two-dimensional surface space, each of array element represent a pixel of corresponding coordinate on map, if the point is barrier
Point, then be set as 1 for array value, if the point is that array value can be set as 0 by point；
In the step 2, emit the method for light are as follows:
(1) for certain point, from 0 degree, i.e., direction starts to emit light every a fixed step-length horizontally to the right, until 360
Until degree；
(2) for each direction, light is pushed ahead pixel-by-pixel, one pixel of every propulsion, it will detect whether the point is that can lead to
It crosses a little, if can continue to promote if, if can not record the point by indicating to encounter barrier, enter step 3 judgement
Journey；
(3) if the light of a direction is apart from too small, then it represents that the direction and barrier very close to, be it is unreasonable, therefore
If light distance is less than a certain threshold value, the light of the direction will be rejected；
In the step 2, the method for storage node are as follows:
Two sequence lists are set, and a sequence list allnode stores all nodes, i.e., emitted to cross light and not yet emit
All nodes of light, another sequence list open storage not yet emit the node of light；When initialization, all by beginning and end
It is stored in two sequence lists；
In the step 3, the determination method of node store are as follows:
When light encounters barrier, all nodes in the point of impingement and allnode are sought into distance, if this is apart from small Mr. Yu
One threshold value then gives up the point, and otherwise the point is added in allnode and open table；
In the step 5, the judgment method that figure terminates is built are as follows:
When the point of impingement of light and the barrier of the transmitting of a certain node with a little at a distance from be respectively less than threshold value when, then the node is not
New node can be generated, hereafter a point is taken out from open table again and carries out light transmitting, the element number of open table will at this time
It can reduce, when open table is empty, that is, building figure process terminates.
2. the method according to claim 1 for improving Visual Graph under complicated map, it is characterised in that: the step
In rapid 4, the method that light emits is repeated are as follows: an element for taking out open gauge outfit repeats light shown in step 2 and emitted
Journey.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611144910.2A CN106708043B (en) | 2016-12-13 | 2016-12-13 | A method of improving Visual Graph under complicated map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611144910.2A CN106708043B (en) | 2016-12-13 | 2016-12-13 | A method of improving Visual Graph under complicated map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106708043A CN106708043A (en) | 2017-05-24 |
| CN106708043B true CN106708043B (en) | 2019-08-06 |
Family
ID=58936854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611144910.2A Active CN106708043B (en) | 2016-12-13 | 2016-12-13 | A method of improving Visual Graph under complicated map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106708043B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334080B (en) * | 2018-01-18 | 2021-01-05 | 大连理工大学 | Automatic virtual wall generation method for robot navigation |
| CN109799817B (en) * | 2019-01-15 | 2021-12-14 | 智慧航海（青岛）科技有限公司 | Unmanned ship global path planning method based on light reflection characteristics |
| CN113108803B (en) * | 2021-04-12 | 2022-12-16 | 北京佰能盈天科技股份有限公司 | Path planning method and device for double-axis positioning system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101464158A (en) * | 2009-01-15 | 2009-06-24 | 上海交通大学 | Automatic generation method for road network grid digital map based on GPS positioning |
| CN102870430A (en) * | 2010-05-03 | 2013-01-09 | 思科技术公司 | Selecting an optical path for a new connection with the minimum number of optical regenerators |
| US8410920B2 (en) * | 2009-12-04 | 2013-04-02 | Denso Corporation | Proximity notification device, proximity notification program and method for notifying proximity of vehicle |
| CN103679301A (en) * | 2013-12-31 | 2014-03-26 | 西安理工大学 | Complex terrain-based optimal path searching method |
| CN104714555A (en) * | 2015-03-23 | 2015-06-17 | 深圳北航新兴产业技术研究院 | Three-dimensional independent exploration method based on edge |
| CN104737123A (en) * | 2012-10-19 | 2015-06-24 | 哈利伯顿能源服务公司 | Self-defining configuration apparatus, methods, and systems |
| CN105469094A (en) * | 2015-11-28 | 2016-04-06 | 重庆交通大学 | Edge vector line extraction algorithm of binary image of road surface |
| CN105955280A (en) * | 2016-07-19 | 2016-09-21 | Tcl集团股份有限公司 | Mobile robot path planning and obstacle avoidance method and system |
| CN105975975A (en) * | 2016-05-20 | 2016-09-28 | 中国科学技术大学 | Environmental line feature extraction method |
-
2016
- 2016-12-13 CN CN201611144910.2A patent/CN106708043B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101464158A (en) * | 2009-01-15 | 2009-06-24 | 上海交通大学 | Automatic generation method for road network grid digital map based on GPS positioning |
| US8410920B2 (en) * | 2009-12-04 | 2013-04-02 | Denso Corporation | Proximity notification device, proximity notification program and method for notifying proximity of vehicle |
| CN102870430A (en) * | 2010-05-03 | 2013-01-09 | 思科技术公司 | Selecting an optical path for a new connection with the minimum number of optical regenerators |
| CN104737123A (en) * | 2012-10-19 | 2015-06-24 | 哈利伯顿能源服务公司 | Self-defining configuration apparatus, methods, and systems |
| CN103679301A (en) * | 2013-12-31 | 2014-03-26 | 西安理工大学 | Complex terrain-based optimal path searching method |
| CN104714555A (en) * | 2015-03-23 | 2015-06-17 | 深圳北航新兴产业技术研究院 | Three-dimensional independent exploration method based on edge |
| CN105469094A (en) * | 2015-11-28 | 2016-04-06 | 重庆交通大学 | Edge vector line extraction algorithm of binary image of road surface |
| CN105975975A (en) * | 2016-05-20 | 2016-09-28 | 中国科学技术大学 | Environmental line feature extraction method |
| CN105955280A (en) * | 2016-07-19 | 2016-09-21 | Tcl集团股份有限公司 | Mobile robot path planning and obstacle avoidance method and system |
Non-Patent Citations (1)
| Title |
|---|
| Graph-based visual SLAM and visual odometry using an RGB-D camera;JanHartmann;《Proceedings of the 9th International Workshop》;20130630;第288-293页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106708043A (en) | 2017-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bastani et al. | Roadtracer: Automatic extraction of road networks from aerial images | |
| CN110675307B (en) | Implementation method from 3D sparse point cloud to 2D grid graph based on VSLAM | |
| CN110139794B (en) | System, method and non-transitory computer readable storage medium for parking a vehicle | |
| CN106708043B (en) | A method of improving Visual Graph under complicated map | |
| CN111094895B (en) | System and method for robust self-repositioning in pre-constructed visual maps | |
| CN114384920A (en) | Dynamic obstacle avoidance method based on real-time construction of local grid map | |
| CN108334080B (en) | Automatic virtual wall generation method for robot navigation | |
| CN109214348A (en) | A kind of obstacle detection method, device, equipment and storage medium | |
| CN110531770A (en) | One kind being based on improved RRT paths planning method and system | |
| Jaspers et al. | Multi-modal local terrain maps from vision and lidar | |
| CN107016706B (en) | A method of obstacles borders are extracted using Visual Graph algorithm | |
| US20230071794A1 (en) | Method and system for building lane-level map by using 3D point cloud map | |
| US20200064481A1 (en) | Autonomous mobile device, control method and storage medium | |
| CN116448115B (en) | Unmanned ship probability distance map construction method based on navigation radar and photoelectricity | |
| Qin et al. | Deep imitation learning for autonomous navigation in dynamic pedestrian environments | |
| CN106971144B (en) | Method for extracting road center line by applying Visual Graph algorithm | |
| US20200264609A1 (en) | Online agent predictions using semantic maps | |
| CN114063619A (en) | Unmanned ship obstacle detection and breaking method based on carpet type scanning mode | |
| Stein et al. | Enabling topological planning with monocular vision | |
| Berrio et al. | Fusing lidar and semantic image information in octree maps | |
| CN105865457B (en) | Path planning method under a kind of dynamic environment based on Cultural Algorithm | |
| US11830203B2 (en) | Geo-motion and appearance aware data association | |
| Khalil et al. | Integration of motion prediction with end-to-end latent RL for self-driving vehicles | |
| CN111123913B (en) | Double-layer path planning and collaborative obstacle avoidance method for multiple unmanned boats | |
| CN111684457B (en) | State detection method and device and movable platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |