CN106682787A - Method for quickly generating generalized Voronoi diagram based on wavefront algorithm - Google Patents
Method for quickly generating generalized Voronoi diagram based on wavefront algorithm Download PDFInfo
- Publication number
- CN106682787A CN106682787A CN201710012511.9A CN201710012511A CN106682787A CN 106682787 A CN106682787 A CN 106682787A CN 201710012511 A CN201710012511 A CN 201710012511A CN 106682787 A CN106682787 A CN 106682787A
- Authority
- CN
- China
- Prior art keywords
- point
- value
- map
- wavefront
- wei nuotu
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000010586 diagram Methods 0.000 title abstract description 17
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000010606 normalization Methods 0.000 claims description 14
- 238000003491 array Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000007493 shaping process Methods 0.000 claims description 3
- 210000000988 bone and bone Anatomy 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 3
- 230000004888 barrier function Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 230000001788 irregular Effects 0.000 description 6
- 230000007797 corrosion Effects 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Classifications
-
- 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
-
- 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
- G05D1/0202—Control of position or course in two dimensions specially adapted to aircraft
-
- 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
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
- G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method for quickly generating generalized Voronoi diagram based on wavefront algorithm; Voronoi diagram method is a space division algorithm established by the Russian mathematician Georgy Fedoseevich Voronoi; the Voronoi diagram method generates a series of diagram blocks by using discrete points as bases, a distance from each diagram block to its corresponding base is shorter than distances from the same to other bases, distances from a point on diagram block boundary to two or more bases are equal, and the diagram is Voronoi diagram in narrow sense; upon path planing problem, generalized Voronoi diagram needs to be established to consider the security of a path planned, to be specific, distances from a node on the Voronoi diagram to two or more obstacles are equal, to also be specific, the node on the Voronoi diagram is a point farthest from obstacles, and the method is also called map skeletonization method. The wavefront algorithm is performed by traversing all blank regions from the edge of an obstacle, points lower than a certain threshold are used as points for the generalized Voronoi diagram after gray gradient calculation is performed, and a standard Voronoi diagram can be generated quickly.
Description
Technical field
The present invention relates to a kind of path planning algorithm in intelligent robot motion planning field, specifically one kind is based on
The method for quickly generating broad sense Wei Nuotu of wavefront algorithms so as to broad sense Wei Nuotu can be generated under standard slam map
And carry out path planning.
Background technology
Instantly the robot system research for being capable of independent navigation avoidance is abnormal burning hot, and has had many products applications
In practice.Such as the service robot in restaurant, just possess obstacle recognition, the ability of path planning；And for example family's sweeping robot,
Also the ability that displacement path is planned in clearing is possessed.In terms of public transportation, the application that unmanned plane express delivery is delivered
That what is carried out is like a raging fire, path planning must be also used on express delivery is delivered, so that unmanned plane can be in avoiding obstacles
On the premise of arrived at most short path and complete deliver.
Path planning refers to how robot decision-making moves to the ability of another point from the certain point of map.Require first
Robot is obtained in that the cartographic information of current environment, and can position the current position of itself, subsequently can just carry out path rule
Draw, it is exactly SLAM algorithms to position and build the algorithm of figure at present most practical.There are many path planning algorithms, such as RRT, PRM at present
Deng.
Voronoi diagram method is that the space segmentation set up by Russia mathematician Georgy Fedoseevich Voronoi is calculated
Method, it generates a series of segments with some discrete points as base, the distance ratio of each segment to its corresponding base to other bases away from
From will be short, and the borderline point of segment is arrived, the distance of two or more bases be equal, and this is referred to as sense stricto Voronoi
Figure.On path planning problem, it is contemplated that the safety in the path planned, it would be desirable to set up the Voronoi diagram of broad sense, i.e.,
It to the distance of two or more barriers is equal that node on Voronoi diagram is, that is, the node on figure is apart from obstacle
The farthest point of thing, this ensures that theres the safety in path, and this method is also called map skeletonizing method.Its advantage is aobvious and easy
See, a safe and reliable path can be obtained, and path more smooths, reasonability is good.
The technology of existing generation Wei Nuotu is broadly divided into arcVRONI and first skeletonizing detects again two kinds of collision,
ArcVRONI is fast although generating Wei Nuotu speed, the Wei Nuotu more standards of generation, but its map request can only by point, line segment and
Circular arc is constituted, for the map that actual slam is generated is not very practical.And detect that the method for collision is the present invention after first skeletonizing
Prototype, the method do not required map, but detection collision expends the time very much, and the Wei Nuotu for generating is nor non-
Normal standard.
The content of the invention
The technology of the present invention solve problem：Overcome the deficiencies in the prior art, there is provided a kind of based on the quick of wavefront algorithms
The method for generating broad sense Wei Nuotu, can quickly generate standard Wei Nuotu on various slam maps.
The technical solution of the present invention：A kind of method for quickly generating broad sense Wei Nuotu based on wavefront algorithms,
Slam maps irregular for barrier edge can quickly generate broad sense Wei Nuotu, and carry out inquiry pathfinding with A* algorithms,
Its step is as follows：
Step 1：The transverse and longitudinal coordinate of the point that all pixels value in the image array IMG after map binary conversion treatment is 1 is stored up
Two arrays Lx are stored to, in Ly；
Step 2：Traversal Lx, adjacent eight point of the point in Ly, and the consecutive points passed through by will being 0 in IMG intermediate values
Transverse and longitudinal coordinate add Lx, in Ly；
Step 3：The skeleton drawing of original place figure is obtained, by skeleton drawing normalization；
Step 4：The Graded Density matrix of the skeleton drawing after normalization, and normalization are calculated, by the gradient after normalization
Point in density matrix less than certain threshold value adds Wei Nuotu；
Step 5：Input starting point and impact point, and inquiry pathfinding is carried out on Wei Nuotu with A* algorithms.
In the step 1, the method for the binaryzation of map is：
The imread functions for calling matlab read in given map file, and are converted in map matrix with im2bw functions
For a two-dimentional shaping array, that is, two dimensional surface space is represented, each element in array represents corresponding coordinate on map
One pixel, if the point is obstacle object point, by array value 1 is set to, if the point by array value by point to be set to 0,
The numerical value of map boundary line point is all set to into 1.
In the step 1, the transverse and longitudinal coordinate of the point that all pixels value in image is 1 is stored into into two arrays Lx, Ly's
Method is：
The find functions in matlab are called, the transverse and longitudinal coordinate for obtaining Lx is stored in into, in Ly.
In the step 3, the method for obtaining original place figure skeleton drawing is：
Traversal Lx, eight adjacent points of the point in Ly have often processed a point, initialize minval values, set initial
Minval values are infinity, if the value in eight points of surrounding a little is bigger than minval, the coordinate of this consecutive points are added into Lx, Ly
In, if eight midranges of surrounding are less than minval, the value of minval is replaced, consecutive points hereafter compare with new minval values work
Compared with after having traveled through consecutive points, the value of origin being assigned to into minval and plus one.Add without new point in Lx, Ly, circulation knot
Beam.Now, each point is given a new value, obtains the skeleton drawing of original place figure.
In the step 3, it is by the normalized method of the skeleton drawing of original place figure：
The maximum for calling the max functions in matlab to find in skeleton drawing, and by the value of each element of skeleton drawing
Divided by this maximum.
In the step 4, the method for obtaining the density gradient matrix of skeleton drawing is：
Call the imgradient functions in matlab
In the step 5, the method by the Graded Density matrix normalization of skeleton drawing is：
The max functions in matlab are called to find the maximum in Graded Density matrix, and by the every of Graded Density matrix
The value of one element is divided by this maximum.
The present invention and advantage be：
(1) Wei Nuotu can be also generated under irregular map.The input of arcvonori compared with prior art must be
By point, line segment and circular arc are constituted, and for irregular map must first carry out polygon projection, effect is bad, and first skeleton is again
Detection impact energy accomplishes to generate Wei Nuotu under irregular map.The present invention is to be based on the basis of map skeletonizing to be tieed up
Promise figure is generated, and it 1 is that the point of barrier adds array to be by all pixels value in step 2, then in step 3 will barrier
The point for hindering the free space at thing edge adds array, is successively corroded to center line of road from barrier edge in step 4, obtains
To the skeleton drawing of map, therefore for the regular degree at barrier edge affects little.
(2) time for generating Wei Nuotu is very short, only need to judge Wei Nuotu to be obtained with the magnitude relationship of threshold value.
Compared with prior art, detection collides process of the needs in skeletonizing for each point in corrosion process is carried out after skeletonizing
Collision detection, expends the time very much.Requirements of the arcvonori to map is higher, and pretreatment map also expends the time very much.And this
Invention only needs to carry out simple threshold decision just to quickly generate Wei Nuotu.The skeletonizing map of map is obtained in step 5
Normalized Graded Density matrix after because value of the point of Wei Nuotu in skeleton drawing is local maximum, positioned at Wei Nuotu
Distribution value of eight points of surrounding in skeleton drawing has eight points around certain symmetry, rather than the point of Wei Nuotu in bone
Value in frame figure must be dull arrangement (or increasing or decreasing, depending in the direction of this spot corrosion), therefore use gradient
After density operator is calculated, the value meeting of point of value of the point in Wei Nuotu in Graded Density matrix compared to Fei Weinuotu
It is very little, can be the decimal of close after being normalized, therefore set a threshold value for example 0.71 to can be obtained by
The coordinate of the point of dimension promise.
(3) every threshold parameter of the invention is all extremely easily adjusted.Compared with prior art, prior art needs over the ground
Figure is expanded so that blocking surfaces become rule, or take a significant amount of time collision detection in skeletonizing process, and this
It is bright to obtain a more accurate, legal path by adjusting threshold parameter, without the need for pretreatment being carried out to map or being carried out
A large amount of collision detections, quickly obtain the Wei Nuotu of more standard.
Description of the drawings
Fig. 1 is the flow chart of the inventive method；
Fig. 2 is design sketch of the present invention on the figure of labyrinth；
Fig. 3 is the Wei Nuotu that very standard can be produced on the more applicable labyrinth figures of Wei Nuotu.
Specific embodiment
The present invention is generally used in the map of slam algorithms foundation, and the more regular effect of obstacles borders is better, such as be confused
Gong Tu.
As shown in figure 1, specific implementation step detailed description of the present invention is as follows：
Step 1：The imread functions for calling matlab read in given map file, and with im2bw functions by map square
Battle array is converted into a two-dimentional shaping array, that is, represent two dimensional surface space, and each element in array represents corresponding on map
One pixel of coordinate, if the point is obstacle object point, by array value 1 is set to, if the point is to pass through point, by array value
0 is set to, the numerical value of map boundary line point is all set to into 1；
Step 2：The transverse and longitudinal coordinate of the point that all pixels value in image is 1 is stored into into two arrays Lx, in Ly；
Step 3：Traversal Lx, eight adjacent points of the point in Ly have often processed a point, initialize minval values, setting
Initial minval values are infinity, if the value in eight points of surrounding a little is bigger than minval, the coordinate of this consecutive points are added
Enter Lx, in Ly, if eight midranges of surrounding are less than minval, replace the value of minval, consecutive points hereafter with it is new
Minval values are made comparisons, and after having traveled through consecutive points, the value of origin is assigned to into minval and plus one.Without new point in Lx, Ly
Add, loop ends.Now, each point is given a new value, obtains the skeleton drawing of original place figure；
Step 4：Their eight adjacent points are begun stepping through from the new point for adding, the value of this point is changed in consecutive points
Minima adds one, and the transverse and longitudinal coordinate of the point that consecutive points intermediate value is 0 is added into Lx, in Ly.Constantly repeat said process until not having
Transverse and longitudinal coordinate a little is added into again Lx, in Ly, after the completion of map be referred to as the skeleton drawing of original place figure, in calling matlab
Max functions find the maximum in skeleton drawing, and the value of each element of skeleton drawing is obtained into normalization divided by this maximum
Skeleton drawing afterwards；
Step 5：The imgradient functions in matlab are called, the Graded Density of the skeleton drawing after normalization is calculated,
The maximum that the max functions in matlab are found in Graded Density matrix is recalled, and each by Graded Density matrix is first
The value of element is divided by this maximum.Graded Density matrix intermediate value adds Wei Nuotu less than the point of certain threshold value.In calling matlab
Imgradient functions, using sobel gradient operators convolutional calculation is carried out, and the gradient for obtaining skeleton drawing after normalization is close
Degree, recalls the maximum that the max functions in matlab are found in Graded Density matrix, and by Graded Density matrix each
The value of element is divided by this maximum.Obtain the density gradient matrix after normalization.Because value of the point of Wei Nuotu in skeleton drawing
It is local maximum, Distribution value of eight around the Wei Nuotu point in skeleton drawing has certain symmetry, Er Feiwei
Value of eight points around the point of promise figure in skeleton drawing must be dull arrangement (or increasing or decreasing, depending in this point
The direction of corrosion), therefore carried out after convolutional calculation using sobel operators, the point in Wei Nuotu is in Graded Density matrix
The value of point of the value compared to Fei Weinuotu can be very little, can be the decimal of close after being normalized, therefore sets
These points are added Wei Nuotu by the coordinate of one threshold value for example 0.71 point that can be obtained by tieing up promise；
Step 6：Input starting point and impact point, and inquiry pathfinding is carried out on Wei Nuotu with A* algorithms.A*'s is heuristic
Cost is set to the distance between Wei Nuotu points, from the off, according to the heuristic rule of A*, to terminal, you can obtain
Obtain path of the point on a Wei Nuotu of connection source and terminal for carrier.
Fig. 2 is design sketch of the algorithm of the present invention on the figure of labyrinth, and black thick line is obstacles borders, and fine rule is Wei Nuotu.
Fig. 3 is design sketch of the present invention on irregular map, and black thick line is obstacles borders, and fine rule is Wei Nuotu, Fig. 2, Fig. 3 explanation
The present invention can produce the Wei Nuotu of very standard on the more applicable labyrinth figures of Wei Nuotu, again can be in irregular map
The Wei Nuotu of upper generation more standard.
Claims (7)
1. a kind of method for quickly generating broad sense Wei Nuotu based on wavefront algorithms, it is characterised in that：For SLAM maps
Broad sense Wei Nuotu is quickly generated, and inquiry pathfinding is carried out with A* algorithms, comprised the following steps that：
Step 1：Map is converted, is determined by the map binary conversion treatment constructed by gray-scale maps or SLAM and by map boundary line
To pass through, the map image matrix IMG after being converted, this process is referred to as map binarization；
Step 2：The transverse and longitudinal coordinate of the point that all pixels value in the image array IMG after map binary conversion treatment is 1 is stored into
Two arrays Lx, in Ly；
Step 3：Traversal Lx, adjacent eight point of the point in Ly, and the horizontal stroke of the consecutive points passed through by will being 0 in IMG intermediate values
Vertical coordinate adds Lx, in Ly；
Step 4：The skeleton drawing of original place figure is obtained, by skeleton drawing normalization；
Step 5：The Graded Density matrix of the skeleton drawing after normalization, and normalization are calculated, by the Graded Density after normalization
Point in matrix less than certain threshold value adds Wei Nuotu；
Step 6：Input starting point and impact point, and inquiry pathfinding is carried out on Wei Nuotu with A* algorithms.
2. a kind of method for quickly generating broad sense Wei Nuotu based on wavefront algorithms according to claim 1, it is special
Levy and be：In the step 1, the method for the binaryzation of map is：
The imread functions for calling matlab read in given map file, and map matrix is converted into into one with im2bw functions
Individual two-dimentional shaping array, that is, represent two dimensional surface space, and each element in array represents of corresponding coordinate on map
Pixel, if the point is obstacle object point, by array value 1 is set to, if array value is set to 0, by ground by the point to pass through point
The numerical value of figure boundary point is all set to 1.
3. a kind of method for quickly generating broad sense Wei Nuotu based on wavefront algorithms according to claim 1, it is special
Levy and be：In the step 2, the transverse and longitudinal coordinate of the point that all pixels value in image is 1 is stored into into two arrays Lx, the side of Ly
Method is：The find functions in matlab are called, the transverse and longitudinal coordinate for obtaining Lx is stored in into, in Ly.
4. a kind of method for quickly generating broad sense Wei Nuotu based on wavefront algorithms according to claim 1, it is special
Levy and be：In the step 4, the method for obtaining original place figure skeleton drawing is：Traversal Lx, eight adjacent points of the point in Ly are often located
A point is managed, minval values have been initialized, it has been infinity to set initial minval values, if the value in eight points of surrounding a little
It is bigger than minval, the coordinate of this consecutive points is added into Lx, in Ly, if eight midranges of surrounding are less than minval, replace
The value of minval, consecutive points hereafter are made comparisons with new minval values, after having traveled through consecutive points, the value of origin are assigned to
Minval adds one, adds without new point in Lx, Ly, loop ends, and now, each point is given individual new
Value, obtains the skeleton drawing of original place figure.
5. a kind of method for quickly generating broad sense Wei Nuotu based on wavefront algorithms according to claim 1, it is special
Levy and be：In the step 4, it is by the normalized method of the skeleton drawing of original place figure：The max functions in matlab are called to find bone
Maximum in frame figure, and by the value of each element of skeleton drawing divided by this maximum.
6. a kind of method for quickly generating broad sense Wei Nuotu based on wavefront algorithms according to claim 1, it is special
Levy and be：In the step 5, the method for obtaining the density gradient matrix of skeleton drawing is to call the imgradient letters in matlab
Number.
7. a kind of method for quickly generating broad sense Wei Nuotu based on wavefront algorithms according to claim 1, it is special
Levy and be：In the step 5, the method by the Graded Density matrix normalization of skeleton drawing is：Call the max functions in matlab
The maximum in Graded Density matrix is found, and by the value of each element of Graded Density matrix divided by this maximum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710012511.9A CN106682787A (en) | 2017-01-09 | 2017-01-09 | Method for quickly generating generalized Voronoi diagram based on wavefront algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710012511.9A CN106682787A (en) | 2017-01-09 | 2017-01-09 | Method for quickly generating generalized Voronoi diagram based on wavefront algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106682787A true CN106682787A (en) | 2017-05-17 |
Family
ID=58849210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710012511.9A Pending CN106682787A (en) | 2017-01-09 | 2017-01-09 | Method for quickly generating generalized Voronoi diagram based on wavefront algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106682787A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423360A (en) * | 2017-06-19 | 2017-12-01 | 广东中冶地理信息股份有限公司 | A kind of labyrinth method for solving based on path center line |
| CN108549388A (en) * | 2018-05-24 | 2018-09-18 | 苏州智伟达机器人科技有限公司 | A kind of method for planning path for mobile robot based on improvement A star strategies |
| CN109357685A (en) * | 2018-11-05 | 2019-02-19 | 飞牛智能科技（南京）有限公司 | Airway net generation method, device and storage medium |
| CN110443774A (en) * | 2019-07-05 | 2019-11-12 | 中国地质大学（武汉） | A kind of city orthography damascene process method and system |
| CN110702126A (en) * | 2018-07-10 | 2020-01-17 | 古野电气株式会社 | Graph generation device and graph generation method |
| CN111323037A (en) * | 2020-02-28 | 2020-06-23 | 武汉科技大学 | Voronoi path planning algorithm for novel framework extraction of mobile robot |
| CN111504321A (en) * | 2020-04-10 | 2020-08-07 | 苏州大学 | Reusable search tree method based on expanded voronoi diagram characteristics |
| CN111507738A (en) * | 2020-05-04 | 2020-08-07 | 武汉积墨包装印刷有限公司 | Ink tracing and recycling process method based on block chain and 5G communication |
| CN112666937A (en) * | 2020-12-07 | 2021-04-16 | 中国科学院深圳先进技术研究院 | Optimal path planning method combined with image framework |
| CN114255241A (en) * | 2021-11-16 | 2022-03-29 | 鹏城实验室 | Region segmentation method, device and equipment for path planning and storage medium |
| CN114485707A (en) * | 2022-01-17 | 2022-05-13 | 武汉科技大学 | Voronoi path planning method based on skeleton key point re-planning |
| CN115265577A (en) * | 2022-09-30 | 2022-11-01 | 北京智行者科技股份有限公司 | Topological relation construction method, system and mobile tool based on Voronoi diagram |
| CN115469662A (en) * | 2022-09-13 | 2022-12-13 | 苏州大学 | Environment exploration method, device and application |
| CN115930969A (en) * | 2023-01-09 | 2023-04-07 | 季华实验室 | Path planning method and device for mobile robot, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140147054A1 (en) * | 2012-11-29 | 2014-05-29 | Yibin TIAN | Topology-preserving downsampling of binary images |
| CN104992443A (en) * | 2015-07-10 | 2015-10-21 | 杭州金人自动控制设备有限公司 | Multipath image separation and extraction method for automated guided forklift |
| CN105913469A (en) * | 2016-04-12 | 2016-08-31 | 西北工业大学 | TF/TA2 track programming method based on skeleton drawing |
| CN106228138A (en) * | 2016-07-26 | 2016-12-14 | 国网重庆市电力公司电力科学研究院 | A kind of Road Detection algorithm of integration region and marginal information |
-
2017
- 2017-01-09 CN CN201710012511.9A patent/CN106682787A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140147054A1 (en) * | 2012-11-29 | 2014-05-29 | Yibin TIAN | Topology-preserving downsampling of binary images |
| CN104992443A (en) * | 2015-07-10 | 2015-10-21 | 杭州金人自动控制设备有限公司 | Multipath image separation and extraction method for automated guided forklift |
| CN105913469A (en) * | 2016-04-12 | 2016-08-31 | 西北工业大学 | TF/TA2 track programming method based on skeleton drawing |
| CN106228138A (en) * | 2016-07-26 | 2016-12-14 | 国网重庆市电力公司电力科学研究院 | A kind of Road Detection algorithm of integration region and marginal information |
Non-Patent Citations (2)
| Title |
|---|
| 李羚 等: ""基于Voronoi图的移动机器人SLAM算法"", 《中南大学学报（自然科学版）》 * |
| 胡玮 等: ""一种Voronoi图的扫描地图矢量化方法"", 《武汉大学学报.信息科学版》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423360A (en) * | 2017-06-19 | 2017-12-01 | 广东中冶地理信息股份有限公司 | A kind of labyrinth method for solving based on path center line |
| CN108549388A (en) * | 2018-05-24 | 2018-09-18 | 苏州智伟达机器人科技有限公司 | A kind of method for planning path for mobile robot based on improvement A star strategies |
| CN110702126A (en) * | 2018-07-10 | 2020-01-17 | 古野电气株式会社 | Graph generation device and graph generation method |
| CN109357685A (en) * | 2018-11-05 | 2019-02-19 | 飞牛智能科技（南京）有限公司 | Airway net generation method, device and storage medium |
| CN110443774A (en) * | 2019-07-05 | 2019-11-12 | 中国地质大学（武汉） | A kind of city orthography damascene process method and system |
| CN111323037A (en) * | 2020-02-28 | 2020-06-23 | 武汉科技大学 | Voronoi path planning algorithm for novel framework extraction of mobile robot |
| CN111504321B (en) * | 2020-04-10 | 2022-03-18 | 苏州大学 | Reusable search tree method based on expanded voronoi diagram characteristics |
| CN111504321A (en) * | 2020-04-10 | 2020-08-07 | 苏州大学 | Reusable search tree method based on expanded voronoi diagram characteristics |
| CN111507738A (en) * | 2020-05-04 | 2020-08-07 | 武汉积墨包装印刷有限公司 | Ink tracing and recycling process method based on block chain and 5G communication |
| CN112666937A (en) * | 2020-12-07 | 2021-04-16 | 中国科学院深圳先进技术研究院 | Optimal path planning method combined with image framework |
| CN114255241A (en) * | 2021-11-16 | 2022-03-29 | 鹏城实验室 | Region segmentation method, device and equipment for path planning and storage medium |
| CN114255241B (en) * | 2021-11-16 | 2023-10-20 | 鹏城实验室 | Region segmentation method, device, equipment and storage medium for path planning |
| CN114485707A (en) * | 2022-01-17 | 2022-05-13 | 武汉科技大学 | Voronoi path planning method based on skeleton key point re-planning |
| CN114485707B (en) * | 2022-01-17 | 2024-04-30 | 武汉科技大学 | Voronoi path planning method based on skeleton key point re-planning |
| CN115469662A (en) * | 2022-09-13 | 2022-12-13 | 苏州大学 | Environment exploration method, device and application |
| CN115265577A (en) * | 2022-09-30 | 2022-11-01 | 北京智行者科技股份有限公司 | Topological relation construction method, system and mobile tool based on Voronoi diagram |
| CN115265577B (en) * | 2022-09-30 | 2023-02-10 | 北京智行者科技股份有限公司 | Topological relation construction method, system and moving tool based on Voronoi diagram |
| CN115930969A (en) * | 2023-01-09 | 2023-04-07 | 季华实验室 | Path planning method and device for mobile robot, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106682787A (en) | Method for quickly generating generalized Voronoi diagram based on wavefront algorithm | |
| CN109541634B (en) | Path planning method and device and mobile device | |
| CN102541057A (en) | Moving robot obstacle avoiding method based on laser range finder | |
| CN103365293B (en) | A kind of robot security's paths planning method based on dynami c block division | |
| Chu et al. | A fast ground segmentation method for 3D point cloud | |
| CN109238298A (en) | A kind of unmanned paths planning method with avoidance | |
| CN105460009B (en) | Automobile control method and device | |
| CN105425795A (en) | Method for planning optimal following path and apparatus | |
| CN107807644A (en) | A kind of farm machinery consumption minimization trajectory path planning method | |
| Huang et al. | Robust lane marking detection under different road conditions | |
| CN105955275A (en) | Robot path programming method and system | |
| CN112115889A (en) | Intelligent vehicle moving target detection method based on vision | |
| CN105652874A (en) | Mobile robot real-time obstacle avoiding method based on general wavefront algorithm | |
| CN104199452A (en) | Mobile robot, mobile robot system as well as mobile and communication method | |
| CN104318611A (en) | Three-dimensional tree re-establishing method based on laser scanning point cloud | |
| Zeng et al. | Lookup: Vision-only real-time precise underground localisation for autonomous mining vehicles | |
| CN112528829B (en) | Visual-based unstructured road centered driving method | |
| CN111815778B (en) | Method for generating navigation path based on ground model | |
| Jianmin et al. | Road and obstacle detection based on multi-layer laser radar in driverless car | |
| CN106971144A (en) | A kind of method that application Visual Graph algorithms extract center line of road | |
| CN102467751A (en) | Rubber band algorithm of three-dimensional virtual scene rapid path planning | |
| Wu et al. | 3D environment detection using multi-view color images and LiDAR point clouds | |
| CN107016706A (en) | A kind of method that application Visual Graph algorithms extract obstacles borders | |
| CN116719341A (en) | Multi-angle route generation method suitable for irregular polygonal field blocks | |
| CN106708043A (en) | Method of improving Visual Graph in complicated map |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170517 |