CN113589808A - Global path planning method based on island bridge model - Google Patents
Global path planning method based on island bridge model Download PDFInfo
- Publication number
- CN113589808A CN113589808A CN202110838389.7A CN202110838389A CN113589808A CN 113589808 A CN113589808 A CN 113589808A CN 202110838389 A CN202110838389 A CN 202110838389A CN 113589808 A CN113589808 A CN 113589808A
- Authority
- CN
- China
- Prior art keywords
- island
- map
- path planning
- islands
- bridge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
Images
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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
A global path planning method based on an island bridge model comprises the following steps: 1) loading a current map picture; 2) judging whether the map has a corresponding island number map and a connectivity file, if so, executing step 4); otherwise, execute 3); 3) transmitting the current map picture into a map preprocessing program, and generating a corresponding island number map and a connectivity file; 4) importing the generated island number map and the connectivity file into a path planning program to prepare for starting path planning; 5) inputting the start and end position coordinates into the path planning program, outputting a path planning result, then judging whether to continue path planning, if not, ending the program, otherwise, repeatedly executing the step 5). The invention has high path searching efficiency and no randomness in path retrieval.
Description
Technical Field
The invention relates to the field of robot control, in particular to a novel global path planning method which can be widely applied to the field of autonomous navigation of equipment such as mobile robots and unmanned vehicles.
Background
Path planning refers to that a mobile robot searches an optimal or suboptimal path from a starting state to a target state according to a certain performance index (such as distance, time and the like). Path planning can be divided into global path planning based on prior information and local path planning based on sensor information according to the degree of confidence in the environmental information. In view of whether the acquired obstacle information is static or dynamic, the global path plan belongs to a static plan. The global path planning needs to grasp all environment information and perform path planning according to all information of the environment map.
Although path planning techniques have long achieved a great deal of research, each algorithm has its limitations, such as the inefficiency of the a x algorithm in complex environments of large scale; RRT and its derivative algorithm, there are randomness in the route search, there is search failure situation; the artificial potential field method is easy to generate local minimum values; neural network algorithms require a large number of samples; the intelligent bionic algorithm is low in operation speed and the like.
Disclosure of Invention
In order to overcome the problems of low path planning efficiency, randomness in path retrieval and failure of path planning in a complex environment existing in the conventional path planning, the invention provides a global path planning method based on an island-bridge model, which integrally comprises two parts: a map preprocessing program and a path planning program. When an unknown map is faced, an original map is preprocessed through a map preprocessing program, a topological model of a bridge island is constructed, and a connectivity file and a coding map are generated at the same time. When the map is subsequently planned, the path planning program greatly reduces the retrieval data volume by loading the connectivity file and the coding map. Meanwhile, the algorithm is further accelerated by the operation of disconnecting the peninsula. Further, the invention has the characteristics of high path searching efficiency and no randomness of path retrieval. The method can be widely applied to the field of autonomous navigation and path planning of unmanned vehicles and mobile robots.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a global path planning method based on an island bridge model comprises the following steps:
1) loading a current map picture;
2) judging whether the map has a corresponding island number map and a connectivity file, if so, executing step 4);
otherwise, execute 3);
3) transmitting the current map picture into a map preprocessing program, and generating a corresponding island number map and a connectivity file;
4) importing the generated island number map and the connectivity file into a path planning program to prepare for starting path planning;
5) inputting the start and end position coordinates into the path planning program, outputting a path planning result, then judging whether to continue path planning, if not, ending the program, otherwise, repeatedly executing the step 5).
Further, in the step 3), the map preprocessing procedure includes the following steps:
step 3.1: importing an original map picture;
step 3.2: map binarization processing
The black pixel part in the grid map is represented as an obstacle, the deeper the pixel color is, the higher the probability of the obstacle existing in the grid map is, determining which pixels in the map are the obstacle by setting a threshold value, so that the gray scale image obtained in the step 3.1 is binarized, further determining and obtaining the obstacle in the map, further performing boundary expansion processing on the obtained binarized image, and setting the expansion radius as the radius of the robot for path planning, so that the robot is protected from colliding with the obstacle on the planned path;
step 3.3: image connectivity analysis
Performing connectivity analysis on the expanded binary image in the step 3.2 to obtain passable areas in the map, and simultaneously further representing each connected area in the image by a plurality of simple polygons;
step 3.4: graphic convex polygon subdivision
Carrying out convex polygon subdivision on each simple polygon processed in the step 3.3;
step 3.5: generating island, bridge lists and island group relationships
The convex polygons obtained by subdivision in the step 3.4 are called islands, the common edges among the convex polygons are called bridges, then the islands and the bridges are numbered respectively, the center coordinates of the islands and the bridges or the islands connected with the islands are recorded simultaneously, and the islands and the bridges are recorded in an island list and a bridge list respectively; the islands obtained by subdividing the same simple polygon belong to the same island group, and as the islands in the same island group are obtained by subdividing the same connected domain simple polygon, passable paths must exist among the islands in the same island group; otherwise, no passable path is necessarily existed between the islands of different island groups;
step 3.6: outputting the relevant parameter file
And 3.5, storing the island, bridge list and island group relation generated in the step 3.5 in a file form, creating a hollow image with the same size as the original map image, filling the corresponding pixels at the convex polygonal island positions in the hollow image by using the serial numbers of the corresponding islands to form an island number map, and storing the island number map in an image form.
Still further, in the step 4), the path planning procedure specifically includes the following steps:
step 4.1: importing map parameter files
Before path planning, firstly, importing a related parameter file generated by the map preprocessing program, and further constructing a topological connected structure through an island and bridge list;
step 4.2: inputting start and end coordinates
In the step, the coordinates of the starting point and the end point of the path planning are determined by inputting the coordinates of the starting point and the end point into a program;
step 4.3: obtaining the island number of the beginning and end positions
According to the input coordinates of the starting point and the ending point, the island number corresponding to the starting point and the ending point can be quickly determined by using the coordinates by using an island number map;
step 4.4: and judging whether the starting point and the ending point are the same island group
Through the island numbers of the starting and ending position points obtained in the step 4.3 and the relationship of the island groups to which the starting and ending position points belong, whether the starting and ending points belong to the same island group or not is quickly determined by judging whether the starting and ending point points belong to the same island group, if the starting and ending point can not pass, the information of the non-passing is returned, otherwise, the step 4.5 is carried out;
and 5: severing extraneous peninsulas
If only one bridge is connected with one island, the island is called a peninsula, and the peninsula has the characteristics that: if the initial point and the final point in the path planning are not in the peninsula, the optimal path does not necessarily pass through the peninsula, according to the characteristic, all irrelevant peninsulas can be cut off by iteration before the path planning is started, the subsequent path retrieval is further accelerated, and when the original peninsula is cut off, the connected islands can become new peninsulas;
step 4.6: finding island traffic sequence by using A
In the step, an A algorithm is used for obtaining an optimal bridge passing sequence from the island bridge topological graph model which is left after the irrelevant peninsula is cut off in the step 4.5;
step 4.7: curve of output passage
And (4) sequentially connecting the bridge center coordinates of the optimal bridge passing sequence obtained in the step (4.6) to generate a passing broken line, smoothing the passing broken line by using a Bezier curve, and outputting a passing route planned by an algorithm, thereby finishing the global path planning. And then judging whether to continue path planning or not, if so, returning to the step 4.2 to wait for the next path planning task, and if not, ending the program.
The beneficial effects of the invention are as follows: the method can be applied to the fields of autonomous navigation and path planning of unmanned vehicles and mobile robots. Compared with the existing path planning algorithm, the method has the advantages that the original map is preprocessed, a 'bridge island' topological model is constructed, and the retrieval data volume is greatly reduced. Meanwhile, the algorithm is further accelerated by the operation of disconnecting the peninsula. The method has the main advantage of faster path search speed. Meanwhile, no algorithm randomness exists in the process of path searching, and whether the starting position point and the final position point can pass or not can be judged at the first time. If the starting and ending position points can pass through, a passing path can be generated inevitably.
Drawings
Fig. 1 is a flowchart of a global path planning algorithm based on an island bridge model.
Fig. 2 is a detailed flowchart of a map preprocessing procedure.
Fig. 3 is a specific flowchart of the path planning procedure.
Detailed Description
The invention is further described below with reference to the accompanying drawings:
referring to fig. 1 to 3, a global path planning method based on an island bridge model includes the following steps:
1) loading a current map picture;
2) judging whether the map has a corresponding island number map and a connectivity file, if so, executing step 4);
otherwise, execute 3);
3) transmitting the current map picture into a map preprocessing program, and generating a corresponding island number map and a connectivity file;
4) importing the generated island number map and the connectivity file into a path planning program to prepare for starting path planning;
5) inputting the start and end position coordinates into the path planning program, outputting a path planning result, then judging whether to continue path planning, if not, ending the program, otherwise, repeatedly executing the step 5).
Referring to fig. 2, in step 3), the map preprocessing procedure includes the following steps:
step 3.1: importing original map pictures
Importing a grid map picture of a map into a program in a gray scale graph mode;
step 3 and step 2: map binarization processing
Generally, a black pixel part in a grid map is represented as an obstacle, the darker the pixel color is, the higher the probability that the obstacle exists is, and then, a threshold value can be set to determine which pixels in the map are the obstacle, so that the gray level map obtained in the step 3.1 is binarized to determine and obtain the obstacle in the map; the boundary expansion processing is further carried out on the obtained binary image, and the expansion radius can be generally set as the radius of the robot for path planning, so that the robot is protected from colliding with an obstacle on the planned path;
step 3.3: image connectivity analysis
Performing connectivity analysis on the expanded binary image in the step 3.2 to obtain passable areas in the map, and simultaneously further representing each connected area in the image by a plurality of simple polygons;
step 3.4: graphic convex polygon subdivision
Because the convex polygon has the characteristics that: any two points in the interior (including the boundary) of the convex polygon can be directly communicated by a line segment in the convex polygon, so that the convex polygon is divided by the simple polygons processed in the step 3.3;
step 3.5: generating island, bridge lists and island group relationships
The convex polygons obtained by the subdivision in step 3.4 are called islands, and the edges common between the convex polygons are called bridges. Then numbering each island and each bridge respectively, recording the central coordinates of the islands and the bridges or the islands connected with the islands, and recording the central coordinates and the bridges or the islands in an island list and a bridge list respectively, wherein the islands obtained by subdividing the same simple polygon belong to the same island group; otherwise, no passable path is necessarily existed between the islands of different island groups;
step 3.6: outputting the relevant parameter file
And 3.5, storing the island, bridge list and island group relation generated in the step 3.5 in a file form, creating a hollow image with the same size as the original map image, filling the corresponding pixels at the convex polygonal island positions in the hollow image by using the serial numbers of the corresponding islands to form an island number map, and storing the island number map in an image form.
Referring to fig. 3, in the step 4), the path planning procedure includes the following steps:
step 4.1: importing map parameter files
Before path planning, firstly, importing a related parameter file generated by the map preprocessing program, and further constructing a topological connected structure through an island and bridge list;
step 4.2: inputting start and end coordinates
In the step, the coordinates of the starting point and the end point of the path planning are determined by inputting the coordinates of the starting point and the end point into a program;
and step 3: obtaining the island number of the beginning and end positions
According to the input coordinates of the starting point and the ending point, the island number corresponding to the starting point and the ending point can be quickly determined by using the coordinates by using an island number map;
step 4.4: and judging whether the starting point and the ending point are the same island group
Through the island numbers of the starting and ending position points obtained in the step 4.3 and the relationship of the island groups to which the starting and ending position points belong, whether the starting and ending points belong to the same island group or not is quickly determined by judging whether the starting and ending point points belong to the same island group, if the starting and ending point can not pass, the information of the non-passing is returned, otherwise, the step 4.5 is carried out;
and 5: severing extraneous peninsulas
If only one bridge is connected with one island, the island is called a peninsula, and the peninsula has the characteristics that: if the initial point and the final point in the path planning are not in the peninsula, the optimal path does not necessarily pass through the peninsula, according to the characteristic, all irrelevant peninsulas can be cut off by iteration before the path planning is started, the subsequent path retrieval is further accelerated, and when the original peninsula is cut off, the connected islands can become new peninsulas;
step 4.6: finding island traffic sequence by using A
In the step, an A algorithm is used for obtaining an optimal bridge passing sequence from the island bridge topological graph model which is left after the irrelevant peninsula is cut off in the step 4.5;
step 4.7: curve of output passage
And (4) sequentially connecting the bridge center coordinates of the optimal bridge passing sequence obtained in the step (4.6) to generate a passing broken line, and then smoothing the passing broken line by using a Bezier curve so as to output a passing route planned by an algorithm. And finishing the global path planning, then judging whether to continue the path planning, if so, returning to the step 4.2 to wait for the next path planning task, and otherwise, ending the program.
The embodiments described in this specification are merely illustrative of implementations of the inventive concepts, which are intended for purposes of illustration only. The scope of the present invention should not be construed as being limited to the particular forms set forth in the examples, but rather as being defined by the claims and the equivalents thereof which can occur to those skilled in the art upon consideration of the present inventive concept.
Claims (3)
1. A global path planning method based on an island bridge model is characterized by comprising the following steps:
1) loading a current map picture;
2) judging whether the map has a corresponding island number map and a connectivity file, if so, executing step 4); otherwise, execute 3);
3) transmitting the current map picture into a map preprocessing program, and generating a corresponding island number map and a connectivity file;
4) importing the generated island number map and the connectivity file into a path planning program to prepare for starting path planning;
5) inputting the start and end position coordinates into the path planning program, outputting a path planning result, then judging whether to continue path planning, if not, ending the program, otherwise, repeatedly executing the step 5).
2. The global path planning method based on island bridge model according to claim 1, wherein in step 3), the map preprocessing procedure comprises the following steps:
step 3.1: importing an original map picture;
step 3.2: map binarization processing
The black pixel part in the grid map is represented as an obstacle, the deeper the pixel color is, the higher the probability of the obstacle existing in the grid map is, determining which pixels in the map are the obstacle by setting a threshold value, so that the gray scale image obtained in the step 3.1 is binarized, further determining and obtaining the obstacle in the map, further performing boundary expansion processing on the obtained binarized image, and setting the expansion radius as the radius of the robot for path planning, so that the robot is protected from colliding with the obstacle on the planned path;
step 3.3: image connectivity analysis
Performing connectivity analysis on the expanded binary image in the step 3.2 to obtain passable areas in the map, and simultaneously further representing each connected area in the image by a plurality of simple polygons;
step 3.4: graphic convex polygon subdivision
Carrying out convex polygon subdivision on each simple polygon processed in the step 3.3;
step 3.5: generating island, bridge lists and island group relationships
The convex polygons obtained by subdivision in the step 3.4 are called islands, the common edges among the convex polygons are called bridges, then the islands and the bridges are numbered respectively, the center coordinates of the islands and the bridges or the islands connected with the islands are recorded simultaneously, and the islands and the bridges are recorded in an island list and a bridge list respectively; the islands obtained by subdividing the same simple polygon belong to the same island group, and as the islands in the same island group are obtained by subdividing the same connected domain simple polygon, passable paths must exist among the islands in the same island group; otherwise, no passable path is necessarily existed between the islands of different island groups;
step 3.6: outputting the relevant parameter file
And 3.5, storing the island, bridge list and island group relation generated in the step 3.5 in a file form, creating a hollow image with the same size as the original map image, filling the corresponding pixels at the convex polygonal island positions in the hollow image by using the serial numbers of the corresponding islands to form an island number map, and storing the island number map in an image form.
3. The global path planning method based on the island-bridge model according to claim 1 or 2, wherein in the step 4), the path planning program specifically includes the following steps:
step 4.1: importing map parameter files
Before path planning, firstly, importing a related parameter file generated by the map preprocessing program, and further constructing a topological connected structure through an island and bridge list;
step 4.2: inputting start and end coordinates
In the step, the coordinates of the starting point and the end point of the path planning are determined by inputting the coordinates of the starting point and the end point into a program;
step 4.3: obtaining the island number of the beginning and end positions
According to the input coordinates of the starting point and the ending point, the island number corresponding to the starting point and the ending point can be quickly determined by using the coordinates by using an island number map;
step 4.4: and judging whether the starting point and the ending point are the same island group
Through the island numbers of the starting and ending position points obtained in the step 4.3 and the relationship of the island groups to which the starting and ending position points belong, whether the starting and ending points belong to the same island group or not is quickly determined by judging whether the starting and ending point points belong to the same island group, if the starting and ending point can not pass, the information of the non-passing is returned, otherwise, the step 4.5 is carried out;
and 5: severing extraneous peninsulas
If only one bridge is connected with one island, the island is called a peninsula, and the peninsula has the characteristics that: if the initial point and the final point in the path planning are not in the peninsula, the optimal path does not necessarily pass through the peninsula, according to the characteristic, all irrelevant peninsulas can be cut off by iteration before the path planning is started, the subsequent path retrieval is further accelerated, and when the original peninsula is cut off, the connected islands can become new peninsulas;
step 4.6: finding island traffic sequence by using A
In the step, an A algorithm is used for obtaining an optimal bridge passing sequence from the island bridge topological graph model which is left after the irrelevant peninsula is cut off in the step 4.5;
step 4.7: curve of output passage
And (3) sequentially connecting the bridge center coordinates of the optimal bridge passing sequence obtained in the step (4.6) to generate a passing broken line, smoothing the passing broken line by using a Bezier curve, and further outputting a passing route planned by an algorithm, thereby completing the global path planning, then judging whether to continue the path planning, if so, returning to the step (4.2) to wait for the next path planning task, otherwise, ending the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110838389.7A CN113589808B (en) | 2021-07-23 | 2021-07-23 | Global path planning method based on island bridge model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110838389.7A CN113589808B (en) | 2021-07-23 | 2021-07-23 | Global path planning method based on island bridge model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113589808A true CN113589808A (en) | 2021-11-02 |
| CN113589808B CN113589808B (en) | 2024-05-03 |
Family
ID=78249311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110838389.7A Active CN113589808B (en) | 2021-07-23 | 2021-07-23 | Global path planning method based on island bridge model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113589808B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005032196A (en) * | 2003-07-11 | 2005-02-03 | Japan Science & Technology Agency | System for planning path for moving robot |
| CN101833699A (en) * | 2009-03-12 | 2010-09-15 | 北京博懋易通科技有限公司 | Heuristic route segment path-finding method for ship route design |
| CN104407824A (en) * | 2014-11-04 | 2015-03-11 | 浙江工业大学 | Printing method of movable printer |
| CN106584860A (en) * | 2016-12-04 | 2017-04-26 | 福建农林大学 | Fast path planning method for island-holding lamellar area in 3D printing |
| CN110887502A (en) * | 2019-11-18 | 2020-03-17 | 广西华蓝岩土工程有限公司 | Must-pass node shortest path searching method |
| CN112033404A (en) * | 2020-07-31 | 2020-12-04 | 重庆智行者信息科技有限公司 | Multi-communication-region full-coverage cleaning path planning method for unmanned sweeper |
| CN112674010A (en) * | 2020-12-17 | 2021-04-20 | 无锡卡尔曼导航技术有限公司 | Operation method for cultivating unmanned ship |
-
2021
- 2021-07-23 CN CN202110838389.7A patent/CN113589808B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005032196A (en) * | 2003-07-11 | 2005-02-03 | Japan Science & Technology Agency | System for planning path for moving robot |
| CN101833699A (en) * | 2009-03-12 | 2010-09-15 | 北京博懋易通科技有限公司 | Heuristic route segment path-finding method for ship route design |
| CN104407824A (en) * | 2014-11-04 | 2015-03-11 | 浙江工业大学 | Printing method of movable printer |
| CN106584860A (en) * | 2016-12-04 | 2017-04-26 | 福建农林大学 | Fast path planning method for island-holding lamellar area in 3D printing |
| CN110887502A (en) * | 2019-11-18 | 2020-03-17 | 广西华蓝岩土工程有限公司 | Must-pass node shortest path searching method |
| CN112033404A (en) * | 2020-07-31 | 2020-12-04 | 重庆智行者信息科技有限公司 | Multi-communication-region full-coverage cleaning path planning method for unmanned sweeper |
| CN112674010A (en) * | 2020-12-17 | 2021-04-20 | 无锡卡尔曼导航技术有限公司 | Operation method for cultivating unmanned ship |
Non-Patent Citations (2)
| Title |
|---|
| JONATHAN D. GAMMELL 等: "Informed Sampling for Asymptotically Optimal Path Planning", IEEE TRANSACTIONS ON ROBOTICS, vol. 34, no. 4, 31 August 2018 (2018-08-31), XP011688852, DOI: 10.1109/TRO.2018.2830331 * |
| 张波菲 等: "基于Maklink图和布谷鸟搜索算法的施工水域路径规划", 上海海事大学学报, 30 September 2020 (2020-09-30) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113589808B (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11709058B2 (en) | Path planning method and device and mobile device | |
| Bastani et al. | Roadtracer: Automatic extraction of road networks from aerial images | |
| CN114440916B (en) | Navigation method, device, equipment and storage medium | |
| KR102305230B1 (en) | Method and device for improving accuracy of boundary information from image | |
| CN112683275A (en) | Path planning method of grid map | |
| CN113971723B (en) | Method, device, equipment and storage medium for constructing three-dimensional map in high-precision map | |
| Quin et al. | Approaches for efficiently detecting frontier cells in robotics exploration | |
| CN113325389A (en) | Unmanned vehicle laser radar positioning method, system and storage medium | |
| CN115560771A (en) | Sampling-based path planning method and device and automatic driving equipment | |
| Portugal et al. | Extracting Topological Information from Grid Maps for Robot Navigation. | |
| CN112428271B (en) | Robot real-time motion planning method based on multi-mode information feature tree | |
| CN107016706B (en) | A method of obstacles borders are extracted using Visual Graph algorithm | |
| CN115830578B (en) | Article inspection method and device and electronic equipment | |
| CN112269848A (en) | Crowdsourcing trajectory data fusion method and device | |
| CN113589808B (en) | Global path planning method based on island bridge model | |
| CN116523970A (en) | Dynamic three-dimensional target tracking method and device based on secondary implicit matching | |
| CN116772846A (en) | Unmanned aerial vehicle track planning method, unmanned aerial vehicle track planning device, unmanned aerial vehicle track planning equipment and unmanned aerial vehicle track planning medium | |
| CN115049997A (en) | Method and device for generating edge lane line, electronic device and storage medium | |
| CN114495049A (en) | Method and device for identifying lane line | |
| Yun et al. | Using self-organizing map for road network extraction from ikonos imagery | |
| CN111435086B (en) | Navigation method and device based on splicing map | |
| CN110705695A (en) | Method, device, equipment and storage medium for searching model structure | |
| Portugal et al. | Retrieving topological information for mobile robots provided with grid maps | |
| Ai et al. | A displacement method based on field analysis | |
| CN116343070B (en) | Intelligent interpretation method for aerial survey image ground object elements |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |