CN116400676A - Intelligent collision prevention method for ship motion control - Google Patents
Intelligent collision prevention method for ship motion control Download PDFInfo
- Publication number
- CN116400676A CN116400676A CN202211405010.4A CN202211405010A CN116400676A CN 116400676 A CN116400676 A CN 116400676A CN 202211405010 A CN202211405010 A CN 202211405010A CN 116400676 A CN116400676 A CN 116400676A
- Authority
- CN
- China
- Prior art keywords
- grid
- ship
- path
- obstacle
- target
- 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 54
- 230000002265 prevention Effects 0.000 title claims abstract description 16
- 238000012360 testing method Methods 0.000 claims abstract description 65
- 238000004088 simulation Methods 0.000 claims abstract description 14
- 230000000694 effects Effects 0.000 abstract description 4
- 238000007796 conventional method Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G05D1/0206—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)
- Traffic Control Systems (AREA)
Abstract
The method determines the size of a target grid and the safety radius of the target which are optimal in sailing performance by constructing a test case for simulation test, then performs obstacle expansion and safety treatment according to the safety radius of the target, performs virtual grid division and path search according to the size of the target grid, does not rely on human experience any more to perform the operation, has better intelligent ship collision prevention effect and safety, can achieve balance between collision prevention instantaneity and path optimality, and has better operability and reliability of ship motion control.
Description
Technical Field
The application relates to the technical field of ships, in particular to an intelligent collision prevention method for ship motion control.
Background
With the development of new generation information technology, the fusion of the traditional ship field and artificial intelligence, big data, communication navigation and other technologies is more and more compact, and autonomous ships become new research hotspots, so that people have a continuous growing trend for research and development of autonomous ships. However, achieving fully autonomous operation of a vessel still faces many challenges, such as target detection capability, automatic path generation and path planning techniques, collision avoidance capability, and autonomous decision making systems, among others, where intelligent collision avoidance of the vessel is one of the difficulties.
Disclosure of Invention
Aiming at the problems and the technical requirements, the applicant provides an intelligent collision prevention method for ship motion control, and the technical scheme of the application is as follows:
an intelligent collision prevention method for ship motion control, comprising the following steps:
performing simulation test by constructing test cases to determine the size of a target grid and the safety radius of the target which are optimal in sailing performance;
virtual grid division is carried out on the navigation sea area of the ship according to the determined size of the target grid;
in the navigation sea area with virtual grid division completed, on the basis of collision avoidance of the obstacle according to the target safety radius, path search is carried out by taking the grid as a unit from the current grid of the ship until the collision avoidance decision path is obtained when the current grid of the ship reaches the grid of the navigation terminal point;
and controlling the ship to navigate in the navigation sea according to the collision avoidance decision path until reaching the navigation end point.
The further technical scheme is that the method for searching the path by taking the grid as a unit comprises the following steps:
and selecting the next grid of the current grid from a preset angle interval of the current ship heading on the basis of collision prevention of the obstacle according to the target safety radius.
According to the further technical scheme, the method further comprises the step of performing obstacle expansion on the obstacle in the navigation sea area according to the target safety radius to determine an obstacle coverage area; the method for determining the next grid of any one current grid in the path searching process comprises the following steps:
determining the ship heading of the ship in the current grid, and taking a region which is in a preset angle interval range of the current ship heading and has a distance not exceeding a preset step length from the position of the ship in the current grid as a search feasible region of the current grid;
traversing all neighbor grids of the current grid, and adding the neighbor grids into a feasible neighborhood for any one neighbor grid of the current grid when the neighbor grid is in a searching feasible domain and the neighbor grid does not belong to an obstacle coverage area;
searching a grid with the minimum path cost in the feasible neighborhood as the next grid of the current grid.
The method further comprises the following steps:
after the path search is carried out in the navigation sea area with the virtual grid division to obtain a collision avoidance decision path, detecting whether an obstacle exists in the range of the safety redundancy deviation of the collision avoidance decision path, if so, carrying out path search again in the navigation sea area with the virtual grid division, otherwise, executing the step of controlling the ship to navigate in the navigation sea area according to the collision avoidance decision path.
The method further comprises the following steps:
and constructing a simulation model based on the historical sailing data of the ship to simulate and determine the safety redundancy deviation.
The method further comprises the following steps:
and when the path deviation between the actual navigation path and the collision prevention decision path of the ship is detected to reach the deviation threshold value in the process of controlling the ship to navigate in the navigation sea according to the collision prevention decision path, the current position of the ship is used as a navigation starting point to carry out path searching and correction on the collision prevention decision path again.
The further technical scheme is that the method for determining the size of the target grid and the target safety radius comprises the following steps:
constructing a plurality of test cases, wherein each test case comprises a plurality of obstacle models in a test scene, at least two test cases virtually grid-divide the test scene according to different grid sizes, and at least two test cases collision-prevention the obstacle models according to different safety radiuses;
performing simulation test on the ship based on the constructed multiple test cases, and selecting the grid size used by the test case with optimal sailing performance as a target grid size and the used safety radius as a target safety radius; the sailing performance comprises collision avoidance performance and decision duration of path searching.
The further technical scheme is that the method for constructing the plurality of test cases comprises the following steps:
constructing a test scene sequence, a safety radius sequence and a grid size sequence, wherein the test scene sequence comprises a plurality of test scenes with different obstacle information, the safety radius sequence comprises a plurality of different safety radiuses, and the grid size sequence comprises a plurality of different grid sizes; at least one of a position, a number, a planar contour shape, and a size of an obstacle model included in a test scene having different obstacle information is different;
and combining elements in the three sequences, namely the test scene sequence, the safety radius sequence and the grid size sequence, so as to obtain a plurality of test cases covering all the elements.
The beneficial technical effects of this application are:
the method comprises the steps of determining the size of a target grid and the safety radius of the target which are optimal in sailing performance by constructing a test case for simulation test, then performing obstacle expansion and safety treatment according to the safety radius of the target, and performing virtual grid division and path search according to the size of the target grid without relying on human experience.
In addition, unlike the conventional method of searching collision preventing path in any direction, the method performs grid search in the preset angle interval range, so that on one hand, the real-time performance of collision preventing decision is improved, on the other hand, the turning of the ship is limited within a certain angle range, the feasibility of ship operation is improved, and the method is especially suitable for large and medium-sized ships with poor operability and mobility.
In addition, the ship motion characteristics and automatic deviation correction are considered during path searching, not only is the historical data based on the first release of the collision avoidance decision path verified, but also the actual navigation path and the collision avoidance decision path are compared in the navigation process to timely correct the deviation, so that factors such as ship motion control deviation, perception deviation and the like are brought into decision constraint, and the operability and reliability of ship motion control are greatly improved.
Drawings
Fig. 1 is a method flowchart of an intelligent collision avoidance method according to one embodiment of the present application.
FIG. 2 is a flow chart of a method of generating a collision avoidance decision path in one embodiment of the present application.
FIG. 3 is a schematic diagram of a scenario in which a next grid to the currently located grid is searched in one example.
Fig. 4 is a method flowchart of an intelligent collision avoidance method according to another embodiment of the present application.
Detailed Description
The following describes the embodiments of the present application further with reference to the accompanying drawings.
The application discloses an intelligent collision prevention method for ship motion control, which comprises the following steps, please refer to a flow chart shown in fig. 1:
step S1, performing simulation test by constructing test cases to determine the size of the target grid and the target safety radius which enable the navigation performance to be optimal.
In one embodiment, a plurality of test cases are constructed, each test case comprises a plurality of obstacle models in a test scene, at least two test cases virtually grid-divide the test scene according to different grid sizes, and at least two test cases collision-avoidance the obstacle models according to different safety radiuses. In the present application, collision avoidance of the obstacle model by the ship according to a certain safety radius means that the ship does not travel into an area within the safety radius range around the plane contour of the obstacle model.
One method of constructing multiple test cases is: and constructing a test scene sequence, a safety radius sequence and a grid size sequence. The test scene sequence comprises a plurality of test scenes with different obstacle information, at least one of the positions, the number, the plane outline shapes and the sizes of the obstacle models contained in the test scenes with the different obstacle information are different, and in order to avoid the accidental of the test result, the obstacles in the test scenes are generally randomly generated. The sequence of safety radii comprises a plurality of different safety radii. The grid size sequence includes a plurality of different grid sizes. And combining elements in the three sequences, namely the test scene sequence, the safety radius sequence and the grid size sequence, so as to obtain a plurality of test cases covering all the elements.
And performing simulation test on the ship based on the plurality of test cases obtained by construction, and selecting the grid size used by the test case with the optimal sailing performance as a target grid size and the safety radius used by the test case with the optimal sailing performance as a target safety radius.
The navigation performance comprises collision avoidance performance and decision time of path search, namely the method and the device balance decision time and collision avoidance performance to determine the size of the target grid and the safety radius of the target, so that the effects of excellent collision avoidance performance and high calculation speed are achieved as much as possible. The specific way of evaluating the sailing performance is not limited in the present application.
And S2, virtually meshing the navigation sea area of the ship according to the determined target mesh size. In the conventional method, virtual meshing is generally performed based on conventional experience, and the subsequent path searching process is influenced by meshing results, so that experience-based practice is greatly influenced by subjective experience and has lower accuracy. The size of the target grid which enables the navigation performance to be optimal is determined through a test case simulation test method, and accuracy is higher.
And step S3, in the navigation sea area where virtual meshing is completed, on the basis of collision avoidance of the obstacle according to the target safety radius, path search is performed by taking the mesh as a unit from the current mesh of the ship until the collision avoidance decision path is obtained when the mesh of the navigation terminal is reached.
The ship can sense the obstacle in the navigation sea through a sensing system comprising a radar and a video collector. In order to eliminate the perceived deviation, the obstacle is generally subjected to expansion treatment according to a safety radius, so that the ship can avoid collision on the obstacle according to a certain safety radius. The value of the safety radius can influence the sailing performance, such as shallow draft, small square coefficient, strong maneuverability and maneuverability of small ships with unmanned water surface vessels, and the influence of the selection of the safety radius on the sailing performance is relatively small. The large ship has deeper draft, larger square coefficient, weaker maneuverability and maneuverability, and the value of the safety radius can have larger influence on the sailing performance. At present, the safety radius of the ship during collision avoidance is generally selected through experience, and the value is often inaccurate enough and the sailing performance of the ship is easily affected.
The method for simulating and testing the navigation performance of the obstacle is characterized in that the target safety radius which enables the navigation performance to be optimal is determined through the method for simulating and testing the test case, then the obstacle is inflated according to the determined target safety radius, so that the coverage area of the obstacle in the navigation area is determined, namely, the effect of collision prevention of the obstacle according to the target safety radius is achieved, the accuracy is higher, and the navigation performance can be optimized better.
In another embodiment, the characteristics of poor operability, mobility and the like of the large and medium-sized ships are comprehensively considered, and when the path search is performed by taking the grids as units, the next grid of the current grid is selected from a preset angle interval of the current ship heading on the basis of collision prevention of the obstacle according to the target safety radius. The predetermined angular interval is typically less than 180 °. The defect that grid searching is carried out in any direction in the conventional method is overcome, and the method is improved to the method that grid searching is carried out in a preset angle interval, so that on one hand, the instantaneity of collision avoidance decision is improved, on the other hand, the turning of the ship is limited within a certain angle range, and the feasibility of ship operation is improved.
In one embodiment, the method for determining the next grid of any one current grid in the path searching process includes, please refer to the flowchart shown in fig. 2:
(1) And determining the heading of the ship in the grid where the ship is currently located.
(2) And taking the area which is within the range of the preset angle interval of the current ship heading and has the distance not exceeding the preset step length from the position of the ship in the current grid as the searching feasible area of the current grid. The predetermined step size is custom set, typically equal to the side length of the target mesh size.
(3) Traversing all neighbor grids of the current grid, and adding the neighbor grids into the feasible neighborhood for any one neighbor grid of the current grid when the neighbor grid is in the searching feasible domain and the neighbor grid does not belong to the coverage area of the obstacle. The neighbor mesh of the current mesh is determined based on the idea of an 8-neighbor mesh.
In this step, there may be some cases where some neighbor grids are partially located within the search feasible region and partially located outside the search feasible region, and then it may be determined based on the ratio of the area located within the search feasible region to the whole grid, and when the ratio of the area located within the search feasible region to the whole grid reaches the ratio threshold, the search feasible region is considered to be within the search feasible region, and otherwise, the search feasible region is considered to be not within the search feasible region.
(4) Searching a grid with the minimum path cost in the feasible neighborhood as the next grid of the current grid.
And (3) repeating the steps (1) - (4) until the current grid searching feasible domain contains the grid with the navigation end point, taking the grid with the navigation end point as the next grid of the current grid, and sequentially connecting the grids to generate a collision avoidance decision path.
For example, please refer to the example diagram of mesh division of a local sailing sea area shown in fig. 3, where a ship is currently located in mesh a, the coverage of the obstacle determined after expansion of the obstacle according to the target safety radius includes the mesh shaded in fig. 3, and the heading of the ship is shown by an arrow, and the search feasible area determined according to the predetermined angle interval range θ and the predetermined step size Δ is shown by a fan in fig. 3. The mesh a has a total of 8 neighbor meshes, meshes B, C, D, E, F, G, H and I, respectively. Wherein neither grid E, F, G, H nor I is within the search feasible domain, and is discarded directly. Grid B is within the search feasible but belongs to the obstacle coverage and is therefore also discarded. Meshes C and D are within the search feasible region and do not fall within the coverage of the obstacle, so the feasible neighborhood includes mesh C and mesh D. Then, the mesh C and the mesh D are searched for the mesh that minimizes the path cost as the next mesh of the mesh a.
And S4, controlling the ship to navigate in the navigation sea area according to the collision avoidance decision path until reaching the navigation end point.
In one embodiment, after the collision avoidance decision path is obtained according to step S3, the ship is not directly controlled to navigate according to the collision avoidance decision path, but a verification step is further provided, please combine the flowchart shown in fig. 4, after the collision avoidance decision path is obtained by performing the path search in the navigation sea area with the virtual grid division completed in step S3, whether an obstacle exists in the safety redundancy deviation range of the collision avoidance decision path is detected, if so, the path search is performed again in the navigation sea area with the virtual grid division completed, otherwise, the step of controlling the ship to navigate in the navigation sea area according to the collision avoidance decision path is performed.
In this verification process, the security redundancy bias may be an empirically custom value. Or in another embodiment, to improve accuracy and objectivity, a simulation model is constructed based on historical voyage data of the ship to simulate and determine safety redundancy deviation.
In addition, in the process of controlling the ship to navigate in the navigation sea according to the collision avoidance decision path, the actual navigation path of the ship and the collision avoidance decision path are often not completely overlapped, and certain deviation exists between the two paths, and mainly comprises a perception deviation, a hydrodynamic model deviation and a motion control deviation. The sensing deviation is a deviation caused by inaccurate sensing and mainly comprises relevant elements such as the position, the size and the like of a sensing obstacle. The hydrodynamic model deviation is the deviation caused by the inconsistency of the hydrodynamic model and the real hydrodynamic characteristics of the ship, and is reflected as the deviation between the navigation path of the ship under the real condition and the navigation path in the model simulation. The motion control deviation is embodied as a deviation between a navigation path and a decision path in the ship model simulation. Under the action of the deviation, the actual navigation path of the ship may deviate from the collision avoidance decision path, and when the deviation of the actual navigation path of the ship and the collision avoidance decision path reaches the deviation threshold value, the current position of the ship is used as the navigation starting point to search the path again to correct the collision avoidance decision path, and then the corrected collision avoidance decision path is followed. Otherwise, continuing to track the current collision avoidance decision path until reaching the navigation end point.
What has been described above is only a preferred embodiment of the present application, which is not limited to the above examples. It is to be understood that other modifications and variations which may be directly derived or contemplated by those skilled in the art without departing from the spirit and concepts of the present application are to be considered as being included within the scope of the present application.
Claims (8)
1. An intelligent collision prevention method for ship motion control is characterized by comprising the following steps:
performing simulation test by constructing test cases to determine the size of a target grid and the safety radius of the target which are optimal in sailing performance;
virtual grid division is carried out on the navigation sea area of the ship according to the determined target grid size;
in the navigation sea area with virtual grid division completed, on the basis of collision avoidance of the obstacle according to the target safety radius, carrying out path search by taking the grid as a unit from the current grid of the ship until the current grid reaches the grid of the navigation terminal point, and obtaining a collision avoidance decision path;
and controlling the ship to navigate in the navigation sea area according to the collision avoidance decision path until reaching a navigation end point.
2. The method of claim 1, wherein the method of performing the path search in units of a trellis comprises:
and selecting the next grid of the current grid from a preset angle interval of the current ship heading on the basis of collision prevention of the obstacle according to the target safety radius.
3. The method of claim 2, further comprising performing an obstacle inflation of an obstacle within the voyage sea in accordance with the target safety radius to determine an obstacle coverage area;
the method for determining the next grid of any one current grid in the path searching process comprises the following steps:
determining the ship heading of the ship in the current grid, and taking a region which is in a preset angle interval range of the current ship heading and has a distance not exceeding a preset step length from the position of the ship in the current grid as a search feasible region of the current grid;
traversing all neighbor grids of a current grid, and adding the neighbor grids into a feasible neighborhood when the neighbor grids are in the searching feasible region and the neighbor grids do not belong to an obstacle coverage region for any neighbor grid of the current grid;
searching a grid with the minimum path cost in the feasible neighborhood as the next grid of the current grid.
4. The method according to claim 1, wherein the method further comprises:
after the path search is carried out in the navigation sea area with the virtual grid division to obtain a collision avoidance decision path, detecting whether an obstacle exists in the range of the safety redundancy deviation of the collision avoidance decision path, if so, carrying out path search again in the navigation sea area with the virtual grid division, otherwise, executing the step of controlling the ship to navigate in the navigation sea area according to the collision avoidance decision path.
5. The method according to claim 4, wherein the method further comprises:
and constructing a simulation model based on the historical sailing data of the ship to simulate and determine the safety redundancy deviation.
6. The method according to claim 1, wherein the method further comprises:
and when detecting that the path deviation between the actual navigation path of the ship and the collision avoidance decision path reaches a deviation threshold value in the process of controlling the ship to navigate in the navigation sea according to the collision avoidance decision path, carrying out path searching and correcting on the collision avoidance decision path again by taking the current position of the ship as a navigation starting point.
7. The method of claim 1, wherein determining the target mesh size and the target safety radius comprises:
constructing a plurality of test cases, wherein each test case comprises a plurality of obstacle models in a test scene, at least two test cases virtually grid-divide the test scene according to different grid sizes, and at least two test cases collision-prevention the obstacle models according to different safety radiuses;
performing simulation test on the ship based on the constructed multiple test cases, and selecting the mesh size used by the test case with optimal sailing performance as the target mesh size and the used safety radius as the target safety radius; the sailing performance comprises collision avoidance performance and decision duration of path searching.
8. The method of claim 7, wherein the method of building a plurality of test cases comprises:
constructing a test scene sequence, a safety radius sequence and a grid size sequence, wherein the test scene sequence comprises a plurality of test scenes with different obstacle information, the safety radius sequence comprises a plurality of different safety radiuses, and the grid size sequence comprises a plurality of different grid sizes; at least one of a position, a number, a planar contour shape, and a size of an obstacle model included in a test scene having different obstacle information is different;
and combining elements in the three sequences, namely the test scene sequence, the safety radius sequence and the grid size sequence, so as to obtain a plurality of test cases covering all the elements.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211405010.4A CN116400676B (en) | 2022-11-10 | 2022-11-10 | Intelligent collision prevention method for ship motion control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211405010.4A CN116400676B (en) | 2022-11-10 | 2022-11-10 | Intelligent collision prevention method for ship motion control |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116400676A true CN116400676A (en) | 2023-07-07 |
| CN116400676B CN116400676B (en) | 2024-11-08 |
Family
ID=87006306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211405010.4A Active CN116400676B (en) | 2022-11-10 | 2022-11-10 | Intelligent collision prevention method for ship motion control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116400676B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110703762A (en) * | 2019-11-04 | 2020-01-17 | 东南大学 | Hybrid path planning method for unmanned surface vehicle in complex environment |
| WO2020133118A1 (en) * | 2018-12-27 | 2020-07-02 | Beijing Voyager Technology Co., Ltd. | Systems and methods for path determination |
| WO2020134082A1 (en) * | 2018-12-28 | 2020-07-02 | 歌尔股份有限公司 | Path planning method and apparatus, and mobile device |
| CN111984009A (en) * | 2020-08-04 | 2020-11-24 | 智慧航海（青岛）科技有限公司 | Ship collision avoidance environment modeling method |
| CN112363512A (en) * | 2020-11-25 | 2021-02-12 | 中国船舶科学研究中心 | Intelligent ship collision avoidance path planning method based on heading and speed |
| US20210114622A1 (en) * | 2019-10-17 | 2021-04-22 | Nokia Solutions And Networks Oy | Movement control |
| CN112985406A (en) * | 2021-02-23 | 2021-06-18 | 武汉理工大学 | Ship obstacle avoidance path planning method and device and storage medium |
| CN113066160A (en) * | 2021-03-09 | 2021-07-02 | 浙江大学 | Indoor mobile robot scene data and test case generation method thereof |
| WO2022097335A1 (en) * | 2020-11-04 | 2022-05-12 | 村田機械株式会社 | Autonomous travel path planning method |
| GB202209423D0 (en) * | 2021-08-12 | 2022-08-10 | Univ Xidian | Method for multi-agent dynamic path planning |
| CN115060264A (en) * | 2022-05-23 | 2022-09-16 | 中国船舶重工集团公司第七0七研究所九江分部 | PRM route planning method based on AIS data |
-
2022
- 2022-11-10 CN CN202211405010.4A patent/CN116400676B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020133118A1 (en) * | 2018-12-27 | 2020-07-02 | Beijing Voyager Technology Co., Ltd. | Systems and methods for path determination |
| WO2020134082A1 (en) * | 2018-12-28 | 2020-07-02 | 歌尔股份有限公司 | Path planning method and apparatus, and mobile device |
| US20210114622A1 (en) * | 2019-10-17 | 2021-04-22 | Nokia Solutions And Networks Oy | Movement control |
| CN110703762A (en) * | 2019-11-04 | 2020-01-17 | 东南大学 | Hybrid path planning method for unmanned surface vehicle in complex environment |
| CN111984009A (en) * | 2020-08-04 | 2020-11-24 | 智慧航海（青岛）科技有限公司 | Ship collision avoidance environment modeling method |
| WO2022097335A1 (en) * | 2020-11-04 | 2022-05-12 | 村田機械株式会社 | Autonomous travel path planning method |
| CN112363512A (en) * | 2020-11-25 | 2021-02-12 | 中国船舶科学研究中心 | Intelligent ship collision avoidance path planning method based on heading and speed |
| CN112985406A (en) * | 2021-02-23 | 2021-06-18 | 武汉理工大学 | Ship obstacle avoidance path planning method and device and storage medium |
| CN113066160A (en) * | 2021-03-09 | 2021-07-02 | 浙江大学 | Indoor mobile robot scene data and test case generation method thereof |
| GB202209423D0 (en) * | 2021-08-12 | 2022-08-10 | Univ Xidian | Method for multi-agent dynamic path planning |
| CN115060264A (en) * | 2022-05-23 | 2022-09-16 | 中国船舶重工集团公司第七0七研究所九江分部 | PRM route planning method based on AIS data |
Non-Patent Citations (4)
| Title |
|---|
| YULIN CHENG等: "study of a complete traversal path planning algorithm", 2022 7TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS, 15 August 2022 (2022-08-15) * |
| 张启钱;许卫卫;张洪海;李翰;: "基于IOCAD的无人机避障路径规划", 西北工业大学学报, no. 02, 15 April 2020 (2020-04-15) * |
| 陈卓;金建海;张波;包涛;: "水面无人艇自主导航与控制系统的设计与实现", 中国造船, no. 1, 30 August 2020 (2020-08-30) * |
| 马俊;董良雄;李军;: "一种基于K-means改进蚁群算法的船舶航线设计方法", 中国修船, no. 03, 1 June 2020 (2020-06-01) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116400676B (en) | 2024-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107505939B (en) | A kind of complete coverage path planning method of mobile robot | |
| Liu et al. | Self-adaptive dynamic obstacle avoidance and path planning for USV under complex maritime environment | |
| CN109375625B (en) | Intelligent ship path planning method based on rapid search genetic algorithm | |
| CN109582027B (en) | Improved particle swarm optimization algorithm-based USV cluster collision avoidance planning method | |
| Braginsky et al. | Obstacle avoidance approaches for autonomous underwater vehicle: Simulation and experimental results | |
| CN107422736B (en) | Unmanned ship autonomous return control method | |
| CN114839968B (en) | Path planning method for unmanned surface vehicle | |
| CN113010958B (en) | Simulation system of self-propelled ship and operation method thereof | |
| CN107037809A (en) | A kind of unmanned boat collision prevention method based on improvement ant group algorithm | |
| CN111063218A (en) | Ship collision avoidance decision method | |
| CN113805569B (en) | Countermeasure system, method, terminal and storage medium based on multi-agent technology | |
| CN109784201A (en) | AUV dynamic obstacle avoidance method based on four-dimensional risk assessment | |
| CN110568862A (en) | Unmanned aerial vehicle flight path planning method and device and related equipment | |
| CN104464379B (en) | Sailing plan and radar track correlating method and system based on sectional matching | |
| Maanpää et al. | Multimodal end-to-end learning for autonomous steering in adverse road and weather conditions | |
| CN109556609B (en) | Artificial intelligence-based collision avoidance method and device | |
| CN106292656A (en) | A kind of environmental modeling method and device | |
| CN116400676B (en) | Intelligent collision prevention method for ship motion control | |
| CN113701762B (en) | Unmanned aerial vehicle search route establishing method and device | |
| Wu et al. | A Review of Path Planning Methods for Marine Autonomous Surface Vehicles | |
| Li et al. | An efficient deep reinforcement learning algorithm for Mapless navigation with gap-guided switching strategy | |
| Cao et al. | Unsupervised visual odometry and action integration for pointgoal navigation in indoor environment | |
| CN117539241A (en) | Path planning method integrating global artificial potential field and local reinforcement learning | |
| CN116958529A (en) | Robot remote control method, system and medium | |
| CN112347961B (en) | Intelligent target capturing method and system for unmanned platform in water flow |
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 |