CN113867344B - Unmanned ship self-adaptive step length path searching method based on terrain complexity - Google Patents
Unmanned ship self-adaptive step length path searching method based on terrain complexity Download PDFInfo
- Publication number
- CN113867344B CN113867344B CN202111098906.8A CN202111098906A CN113867344B CN 113867344 B CN113867344 B CN 113867344B CN 202111098906 A CN202111098906 A CN 202111098906A CN 113867344 B CN113867344 B CN 113867344B
- Authority
- CN
- China
- Prior art keywords
- path
- grid
- area
- obstacle
- environment model
- 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 23
- 230000003068 static effect Effects 0.000 claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 230000004888 barrier function Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005070 sampling Methods 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
- G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles
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)
- Processing Or Creating Images (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned ship self-adaptive step length path searching method based on terrain complexity. Comprises the following steps: acquiring an environment static image and performing binarization pretreatment; then image expansion and rasterization are carried out to establish a map environment model; calculating the terrain complexity of each grid, and screening and subtracting; searching an optimal passing path in a map environment model by using an A-algorithm; and further optimizing the acquired optimal traffic path to obtain a final optimized path. According to the invention, the terrain complexity is calculated according to the map environment model, the map can be automatically segmented for analysis and processing, the calculation of a complete obstacle region is omitted, the calculated amount and the required running memory are reduced, the path is optimized, a plurality of unnecessary inflection points are reduced, the overall path length is shortened, and the path quality is improved.
Description
Technical Field
The invention relates to an artificial intelligence unmanned ship path planning method, in particular to an unmanned ship autonomous path planning and path optimization method, and specifically relates to an unmanned ship self-adaptive step length path searching method based on terrain complexity.
Background
With the continuous development of technology in the field of ocean monitoring in China, unmanned ships have more and more widely applied to automatic path finding algorithms. Through the unmanned ship with automatic navigation and road finding functions, people can realize more frequent and omnibearing offshore monitoring, and survey, sampling, rescue and the like are completed better.
For example, the patent of application number CN 111930121A proposes a hybrid path planning method for an indoor mobile robot, which models the space where the robot is located by using a grid method, generates a random solution by bat algorithm, and then searches for an optimal solution by iteration. However, this method lacks an adaptive strategy to the environment, which is separated by a uniform-sized grid, resulting in a lack of adaptation to the environment.
For example, the patent of application number CN 112378402A combines global path planning with local path planning, and integrates local path planning on the basis of the global path, so that the mobile robot has certain self-adaptive capacity. However, this method also lacks an adaptive strategy to the environment in global path planning, which may lead to poor initial path quality.
In summary, the path planning in the prior art has at least the following drawbacks: in some cases, the step size of the path search is too large, resulting in some possible paths being ignored; in some cases, the step length of the path search is too small, so that too many grids are formed on the map, and the calculated amount of the algorithm and the required running memory are unnecessarily increased, so that the time and the memory consumption required by the algorithm are increased; the obtained path is not optimized, the quality of the path is poor, the generated path has sharp inflection points, unnecessary detour occurs, and the gap between the generated path and the optimal passing path is large.
Disclosure of Invention
In view of the above, the main objective of the present invention is to provide an unmanned ship adaptive step-length path searching method based on terrain complexity, so as to overcome the defects existing in Beijing technology.
The invention comprises the following steps:
step 100, acquiring an environment static image, and performing binarization pretreatment on the environment static image;
step 200, performing image expansion and rasterization on the environment static image subjected to binarization pretreatment, and establishing a map environment model;
step 300, calculating the terrain complexity of each grid in the map environment model and screening and subtracting;
step 400, searching an optimal passing path in a map environment model by utilizing an A-algorithm, and readjusting the step length of the optimal passing path according to the complexity of the current terrain during each iteration;
and 500, further optimizing the acquired optimal traffic path by utilizing the node visibility of the map environment model to obtain a final optimized path.
In the step 100, an electronic chart and a satellite image are acquired, and the electronic chart and the satellite image are correspondingly overlapped to obtain an environment static image; and (3) calibrating a land area and an area with the water depth smaller than 10m in the environment static image as an obstacle area, and calibrating an area with the water depth larger than 10m as a passable area, so as to binarize the environment static image.
In the step 200, the obstacle area is marked as a highlight area, the expansion operation is performed on the environment static image after the binarization pretreatment, the environment static image is rasterized after the expansion operation is completed, a map environment model is built, square grids with the side length of 5-10m are selected for rasterization, and the map environment model is divided into grids with consistent sizes of i x j in rows and columns.
In the step 300, there are a plurality of sub-areas in the obstacle area, each sub-area is separated by the passable area and is not connected, each sub-area is used as an obstacle, and the terrain complexity of all grids is calculated
Wherein k is 1 ，k 2 ，k 3 Taking positive values for the first, second and third proportional coefficients; f (f) 1 Is the local obstacle area ratio; f (f) 2 Representing the relative distance of the obstacles, f when the number of obstacles in the grid is less than or equal to 1 2 Taking 1;f 3 representing the total number of obstacles within the grid; m represents the ordinal number of the grid in the row direction, m= … i, i represents the total number of grids of the map environment model in the row direction, n represents the ordinal number of the grid in the column direction, n= … j, j represents the total number of grids of the map environment model in the column direction;
then, the barrier grids are removed and the grids which are surrounded by the barrier grids and cannot be reached are used as barrier grids with the barrier area ratio reaching 100%.
In step 400, a starting point is selected, from which the terrain complexity of the current grid is basedInputting the path search result into an A-algorithm, adaptively determining a step length to search for an optimal traffic path, wherein the step length refers to the distance between a first node and a last node in the optimal traffic path; when the algorithm A is iterated, the consumed cost in the cost function is taken as the total path length of the paths which have been taken in the paths, the estimated cost in the cost function is calculated by using the Manhattan distance, and the optimal passing path solved by the algorithm A is the optimal passing path P in the map environment model.
In the step 500, the node visibility of the map environment model is utilized to further optimize the optimal passing path P, two nodes which are not directly connected in the optimal passing path P are connected, if the connection line between the two nodes is not overlapped with the optimal passing path P and does not pass through an obstacle, the path of the connection line between the two nodes is used to replace the path of the connection line between the two nodes and a plurality of nodes between the two nodes to operate, and the operation is repeated until the optimal path cannot be further optimized, so as to obtain the final optimized path.
The invention provides a path searching method with self-adaptive step length, which has the following advantages:
according to the map environment model calculation terrain complexity, the map can be automatically segmented for analysis processing, calculation of a complete obstacle area is omitted, the map environment model is divided from large to small, calculation amount and required running memory are reduced, paths are optimized, a plurality of unnecessary inflection points are reduced, overall path length is shortened, and path quality is improved.
Drawings
Fig. 1 is a general flow chart of the method of the present invention.
Fig. 2 is an exemplary diagram of a path search method, wherein fig. 2-1 is an exemplary map. Fig. 2-2 is a graph of terrain complexity parameters. The upper left corner number of each grid represents the local obstacle area ratio f 1 The method comprises the steps of carrying out a first treatment on the surface of the The upper right corner number indicates the relative distance f of the obstacle 2 The lower left corner number indicates the total number of obstacles in the grid f 3 . Fig. 2-3 are final paths after the application of the adaptation step size.
Detailed Description
The invention will be described in further detail with reference to the accompanying drawings and specific examples.
As shown in fig. 1, the method comprises the steps of:
step 100, acquiring an electronic chart and a satellite image, and correspondingly superposing the electronic chart and the satellite image to obtain an environment static image; taking the water level change caused by tidal rise and fall into consideration, marking a land area and an area with the water depth smaller than 10m in an environment static image as barrier areas and marking an area with the water depth larger than 10m as passable areas by taking the water depth of 10m as a reference, thereby binarizing the environment static image;
step 200, calibrating an obstacle area as a highlight area, performing expansion operation on the binarized preprocessed environment static image, enabling an unmanned ship in the environment static image to keep a safe distance from an unvented area, rasterizing the environment static image after the expansion operation is completed, establishing a map environment model, and dividing the map environment model into grids with consistent line numbers i, j, wherein the square grids with side lengths of 5-10m are selected for rasterizing as shown in fig. 2-1;
step 300, calculating the terrain complexity of all grids by taking each sub-area as an obstacle, wherein a plurality of sub-areas exist in the obstacle area, each sub-area is separated by a passable area and is not connected with the passable area
Wherein k is 1 ，k 2 ，k 3 Taking positive values for the first, second and third proportional coefficients; f (f) 1 Is the local obstacle area ratio; f (f) 2 Representing the relative distance of the obstacles, f when the number of obstacles in the grid is less than or equal to 1 2 Taking 1; f (f) 3 Representing the total number of obstacles within the grid; m represents the ordinal number of the grid in the row direction, m= … i, i represents the total number of grids of the map environment model in the row direction, n represents the ordinal number of the grid in the column direction, n= … j, j represents the total number of grids of the map environment model in the column direction;
then, taking a grid with the area ratio of the obstacle reaching 100% as an obstacle grid, removing the obstacle grid and a grid which is surrounded by the obstacle grid and cannot be reached, so that the operation amount can be reduced, and the average distance between the obstacles is obtained by averaging the distances between every two obstacles;
the terrain complexity results for all grids are shown in fig. 2-2.
Step 400, selecting a starting point, starting from the starting point, according to the terrain complexity of the current gridInputting the path search result into an A-algorithm, adaptively determining a step length to search for an optimal traffic path, wherein the step length refers to the distance between a first node and a last node in the optimal traffic path; the algorithm A is iterated, and the cost function is inThe consumed cost is taken as the total length of the paths, the estimated cost in the cost function is calculated by using Manhattan distance, namely the sum of the absolute value of the abscissa of the current point and the absolute value difference of the absolute value of the ordinate of the end point, the optimal passing path solved by using an A-type algorithm is the optimal passing path P in the map environment model, and the nth point in the optimal passing path is marked as P (n).
And 500, further optimizing the optimal passing path P by utilizing the node visibility of the map environment model, connecting two nodes P (n) and P (n+2) which are not directly connected in the optimal passing path P, if the connecting line between the two nodes does not coincide with the optimal passing path P and does not pass through an obstacle, replacing the path of the connecting line between the two nodes with the path of the connecting line between the two nodes and a plurality of nodes between the two nodes to operate, ignoring all the nodes in the middle, repeating the operation until the optimal path cannot be further optimized, and obtaining a final optimized path, as shown in fig. 2-3.
According to the map environment model calculation terrain complexity, the map can be automatically segmented for analysis processing, calculation of a complete obstacle area is omitted, the map environment model is divided from large to small, calculation amount and required running memory are reduced, paths are optimized, a plurality of unnecessary inflection points are reduced, overall path length is shortened, and path quality is improved.
Claims (4)
1. The unmanned ship self-adaptive step length path searching method based on the terrain complexity is characterized by comprising the following steps of:
step 100, acquiring an environment static image, and performing binarization pretreatment on the environment static image;
step 200, performing image expansion and rasterization on the environment static image subjected to binarization pretreatment, and establishing a map environment model;
step 300, calculating the terrain complexity of each grid in the map environment model and screening and subtracting;
in the step 300, there are a plurality of sub-areas in the obstacle area, each sub-area being separated by a passable area and being unconnected, each sub-area being taken asAn obstacle, calculate the terrain complexity of all grids
Wherein k is 1 ,k 2 ,k 3 Taking positive values for the first, second and third proportional coefficients; f (f) 1 Is the local obstacle area ratio; f (f) 2 Representing the relative distance of the obstacles, f when the number of obstacles in the grid is less than or equal to 1 2 Taking 1; f (f) 3 Representing the total number of obstacles within the grid; m represents the ordinal number of the grid in the row direction, m= … i, i represents the total number of grids of the map environment model in the row direction, n represents the ordinal number of the grid in the column direction, n= … j, j represents the total number of grids of the map environment model in the column direction;
then taking a grid with the area ratio of the obstacle reaching 100% as an obstacle grid, and removing the obstacle grid and a grid which is surrounded by the obstacle grid and cannot be reached;
step 400, searching an optimal passing path in a map environment model by utilizing an A-algorithm, and readjusting the step length of the optimal passing path according to the complexity of the current terrain during each iteration;
in step 400, a starting point is selected, from which the terrain complexity of the current grid is basedInputting the path search result into an A-algorithm, adaptively determining a step length to search for an optimal traffic path, wherein the step length refers to the distance between a first node and a last node in the optimal traffic path; when the algorithm A is iterated, the consumed cost in the cost function is taken as the total path length of the walked path in the paths, the estimated cost in the cost function is calculated by using Manhattan distance, and the optimal passing path solved by the algorithm A is the optimal passing path P in the map environment model;
and 500, further optimizing the acquired optimal traffic path by utilizing the node visibility of the map environment model to obtain a final optimized path.
2. The unmanned ship self-adaptive step path searching method based on terrain complexity according to claim 1, wherein the method comprises the following steps: in the step 100, an electronic chart and a satellite image are acquired, and the electronic chart and the satellite image are correspondingly overlapped to obtain an environment static image; and (3) calibrating a land area and an area with the water depth smaller than 10m in the environment static image as an obstacle area, and calibrating an area with the water depth larger than 10m as a passable area, so as to binarize the environment static image.
3. An unmanned ship self-adaptive step path searching method based on terrain complexity according to claim 1 or 2, wherein the method comprises the following steps: in the step 200, the obstacle area is marked as a highlight area, the expansion operation is performed on the environment static image after the binarization pretreatment, the environment static image is rasterized after the expansion operation is completed, a map environment model is built, square grids with the side length of 5-10m are selected for rasterization, and the map environment model is divided into grids with consistent sizes of i x j in rows and columns.
4. The unmanned ship self-adaptive step path searching method based on terrain complexity according to claim 1, wherein the method comprises the following steps: in the step 500, the node visibility of the map environment model is utilized to further optimize the optimal passing path P, two nodes which are not directly connected in the optimal passing path P are connected, if the connection line between the two nodes is not overlapped with the optimal passing path P and does not pass through an obstacle, the path of the connection line between the two nodes is used to replace the path of the connection line between the two nodes and a plurality of nodes between the two nodes to operate, and the operation is repeated until the optimal path cannot be further optimized, so as to obtain the final optimized path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111098906.8A CN113867344B (en) | 2021-09-18 | 2021-09-18 | Unmanned ship self-adaptive step length path searching method based on terrain complexity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111098906.8A CN113867344B (en) | 2021-09-18 | 2021-09-18 | Unmanned ship self-adaptive step length path searching method based on terrain complexity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113867344A CN113867344A (en) | 2021-12-31 |
| CN113867344B true CN113867344B (en) | 2023-09-05 |
Family
ID=78992790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111098906.8A Active CN113867344B (en) | 2021-09-18 | 2021-09-18 | Unmanned ship self-adaptive step length path searching method based on terrain complexity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113867344B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109164810A (en) * | 2018-09-28 | 2019-01-08 | 昆明理工大学 | It is a kind of based on the adaptive dynamic path planning method of ant colony-clustering algorithm robot |
| CN110083165A (en) * | 2019-05-21 | 2019-08-02 | 大连大学 | A kind of robot paths planning method under complicated narrow environment |
| CN110703762A (en) * | 2019-11-04 | 2020-01-17 | 东南大学 | Hybrid path planning method for unmanned surface vehicle in complex environment |
| CN111551184A (en) * | 2020-03-27 | 2020-08-18 | 上海大学 | Map optimization method and system for SLAM of mobile robot |
| CN112161631A (en) * | 2020-12-01 | 2021-01-01 | 湖北第二师范学院 | Safe path planning method based on large satellite grid map |
| CN112327885A (en) * | 2020-12-01 | 2021-02-05 | 大连海事大学 | Unmanned ship self-adaptive global-local hybrid path planning method |
-
2021
- 2021-09-18 CN CN202111098906.8A patent/CN113867344B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109164810A (en) * | 2018-09-28 | 2019-01-08 | 昆明理工大学 | It is a kind of based on the adaptive dynamic path planning method of ant colony-clustering algorithm robot |
| CN110083165A (en) * | 2019-05-21 | 2019-08-02 | 大连大学 | A kind of robot paths planning method under complicated narrow environment |
| CN110703762A (en) * | 2019-11-04 | 2020-01-17 | 东南大学 | Hybrid path planning method for unmanned surface vehicle in complex environment |
| CN111551184A (en) * | 2020-03-27 | 2020-08-18 | 上海大学 | Map optimization method and system for SLAM of mobile robot |
| CN112161631A (en) * | 2020-12-01 | 2021-01-01 | 湖北第二师范学院 | Safe path planning method based on large satellite grid map |
| CN112327885A (en) * | 2020-12-01 | 2021-02-05 | 大连海事大学 | Unmanned ship self-adaptive global-local hybrid path planning method |
Non-Patent Citations (1)
| Title |
|---|
| 复杂环境下改进APF的机器人路径规划;卢恩超 等;《计算机工程与应用》;20131230;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113867344A (en) | 2021-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256577B (en) | Obstacle clustering method based on multi-line laser radar | |
| CN109829199B (en) | Power line rapid layered extraction method based on LiDAR point cloud | |
| Lee et al. | Perceptual organization of 3D surface points | |
| CN103745441A (en) | Method of filtering airborne LiDAR (Light Detection and Ranging) point cloud | |
| CN114120110A (en) | Multi-granularity calculation method for airborne laser point cloud classification of hybrid scene | |
| Shen et al. | A new algorithm of building boundary extraction based on LIDAR data | |
| CN110580388A (en) | Channel network extraction method based on crowd-sourced trajectory data | |
| CN114463338B (en) | Automatic building laser foot point extraction method based on graph cutting and post-processing | |
| CN1760888A (en) | Method for recognizing change of earth's surface by using satellite SAR carried images at multiple time phases | |
| CN114063616B (en) | Method and device for planning forest path based on three-dimensional laser scanning detection | |
| CN113739707B (en) | Sea ice information extraction method | |
| CN113834547B (en) | River virtual station water level time sequence reconstruction method and system | |
| CN113867344B (en) | Unmanned ship self-adaptive step length path searching method based on terrain complexity | |
| Imran et al. | Delineation of drainage network and estimation of total discharge using digital elevation model (DEM) | |
| Wlodarczyk-Sielicka et al. | Fragmentation of hydrographic big data into subsets during reduction process | |
| CN109784225B (en) | Geographical space mode identification method based on reachable space | |
| CN111080080A (en) | Method and system for estimating risk of geological disaster of villages and small towns | |
| CN115619953A (en) | Rugged terrain-oriented mobile robot terrain mapping method and system | |
| CN115858840A (en) | Scene-based remote sensing image mosaic method | |
| CN114217641B (en) | Unmanned aerial vehicle power transmission and transformation equipment inspection method and system in non-structural environment | |
| Lau et al. | Completing fragmentary river networks via induced terrain | |
| CN114743059A (en) | Automatic classification method for submarine geographic entities by integrating topographic features | |
| Novák et al. | The Potential and Implications of Automated Pre-Processing of LiDAR-Based Digital Elevation Models for Large-Scale Archaeological Landscape Analysis | |
| Moravej et al. | Comparison of automated and manual landform delineation in semi detailed soil survey procedure | |
| CN110084190B (en) | Real-time unstructured road detection method under severe illumination environment based on ANN |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Nie Yong Inventor after: Li Zhenhui Inventor after: Zhang Minjie Inventor after: Lv Xiaowen Inventor after: Sun Xiangwei Inventor after: Tang Jianzhong Inventor after: Chen Zheng Inventor before: Li Zhenhui Inventor before: Zhang Minjie Inventor before: Lv Xiaowen Inventor before: Sun Xiangwei Inventor before: Nie Yong Inventor before: Tang Jianzhong Inventor before: Chen Zheng |
|
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Nie Yong Inventor after: Zhang Minjie Inventor after: Lv Xiaowen Inventor after: Sun Xiangwei Inventor after: Li Zhenhui Inventor after: Tang Jianzhong Inventor after: Chen Zheng Inventor before: Nie Yong Inventor before: Li Zhenhui Inventor before: Zhang Minjie Inventor before: Lv Xiaowen Inventor before: Sun Xiangwei Inventor before: Tang Jianzhong Inventor before: Chen Zheng |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |