CN116400679A - Ship formation algorithm combining rapid travel leveling method and virtual obstacle potential field method - Google Patents
Ship formation algorithm combining rapid travel leveling method and virtual obstacle potential field method Download PDFInfo
- Publication number
- CN116400679A CN116400679A CN202310166496.9A CN202310166496A CN116400679A CN 116400679 A CN116400679 A CN 116400679A CN 202310166496 A CN202310166496 A CN 202310166496A CN 116400679 A CN116400679 A CN 116400679A
- Authority
- CN
- China
- Prior art keywords
- ship
- obstacle
- virtual
- follower
- potential field
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 230000015572 biosynthetic process Effects 0.000 title claims abstract description 38
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000010586 diagram Methods 0.000 claims description 8
- 238000002474 experimental method Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 2
- 238000005755 formation reaction Methods 0.000 abstract description 33
- 230000003068 static effect Effects 0.000 abstract description 3
- 230000002265 prevention Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 230000007998 vessel formation Effects 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
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 invention provides a ship formation algorithm combining a fast traveling leveling method and a virtual obstacle potential field method, which adopts the fast traveling leveling method to conduct global static path planning, then realizes the path tracking of a follower ship to a leader ship through a leader-following formation control method, finally adopts an improved virtual obstacle potential field method to conduct local collision avoidance, and improves the situation that the ship possibly enters a local minimum point position through a mode of adding a virtual obstacle; the experimental result shows that the algorithm plans a route with the advantages of time, smoothness and safety for a leader in the ship, and forms stable formations rapidly; compared with the Dijkstra algorithm and the A algorithm, the operation speed is obviously improved; the ship can be prevented from being bumped timely when encountering obstacles at collision risk, and the problem that the traditional artificial potential field method cannot solve is solved and is separated from a local minimum point is solved.
Description
Technical Field
The invention relates to a ship formation algorithm capable of effectively establishing a formation structure and guaranteeing the safety of all ships, in particular to a ship formation algorithm combining a rapid traveling leveling method and a virtual obstacle potential field method, and belongs to the technical field of intelligent and safe navigation of ships.
Background
The ship formation has important significance for maintaining the stability of the coordination operation of multiple ships. The leader-follower formation control method is popular with students because of the advantages of simple principle and easy realization. In order to realize the coordination operation of the offshore multi-ship by the method, the route planning needs to be carried out for the leader in the team in advance. The Dijkstra algorithm and the a-x algorithm in the currently commonly used global path planning algorithm are algorithms for solving the optimal path, but the Dijkstra algorithm and the a-x algorithm have the following defects: firstly, the Dijkstra algorithm is simple in principle, but the calculation flow is too complex and occupies more memory, and is only suitable for path planning in a smaller scale; the a algorithm operates faster than the Dijkstra algorithm, but is very dependent on heuristic functions, which results in a huge calculation of the algorithm. Secondly, since the main objective of the two is to plan the shortest route, the safety during navigation cannot be ensured.
And when the route tracking of the follower ship to the leader ship is realized by the leader-follow formation control method, static obstacles may appear in the sailing route, so that an algorithm is urgently needed to solve the problem that the follower may collide in the tracking process. In the traditional collision prevention method, the artificial potential field method has the advantages of strong real-time performance, simple mathematical calculation, smoother planned path, easy programming and the like, so that the artificial potential field method is widely used for solving the problem of local collision prevention, but the artificial potential field method can be involved in the situation that a ship is stagnated due to a local minimum point.
Disclosure of Invention
The invention discloses a ship formation algorithm combining a rapid travelling flattening method and a virtual obstacle potential field method, which is an algorithm for effectively establishing a formation structure and ensuring the safety of all ships by combining a leading-following formation control method with a path planning method of the rapid travelling flattening method and a local collision prevention method of the virtual obstacle potential field method.
The technical scheme of the ship formation algorithm combining the rapid travelling flattening method and the virtual obstacle potential field method is as follows:
1) Path planning based on fast travel flattening method
The fast travel flattening method comprises the following steps:
step1: modeling a navigation environment and converting the environment into a binary grid map; marking the cells belonging to the obstacle and the cells corresponding to the passable area respectively;
step2: the fast-marching flattening method takes each unit marked as an obstacle in a map as a wave source, and simultaneously expands a plurality of waves, wherein the result value of each unit in the map represents the time when the waves need to reach the nearest obstacle, and is proportional to the distance from the obstacle; the potential diagram obtained in the step is a velocity potential and is marked as W (x), each grid in the velocity potential diagram has a value which indicates the distance between the grid and the nearest barrier, and the value range is 0-1;
step3: the target point is treated as a unique wave source on the basis of the potential map W (x) to ensure a global minimum, and the wave is spread on the map until the initial point is reached. For each cell in the feasible region, extracting the expansion speed of the wave from the velocity potential diagram W (x) calculated in the previous step;
step4: finally, starting from the starting point of the ship, gradient descent is carried out on the whole arrival time map, and the whole arrival time map is moved to a target point (the global minimum value of the result map) of the ship, so that a path comprehensively considering the arrival time, smoothness and safety is obtained;
2) Capacity control based on Laplace matrix
Considering a lead-following multi-vessel queuing system, wherein each vessel in the system can be regarded as a node in the network, and the information transfer links between vessels can be regarded as edges connecting different nodes; thus, the multi-vessel system and its communication network can be modeled as one graph; in the formation, the ship formation system is constructed as a directed graph, as shown in fig. 1, in which the direction of the arrow represents the direction of information transfer, due to the presence of the information flow.
The directed graph is represented by g= { V, E }, where v= { V 1 ,v 2 ,...,v n And N vertices in the figure, i.e. N vessels in the system,
then the set of edges made up of vertices is represented. The laplace matrix L is defined as: l=d-a, where D is the entry matrix of the graph, and the elements on its diagonal are the sum of the entries of the nodes; a is the weight matrix of the graph, if the vertex v is the head of the edge E, then element a in the A matrix ij =1, otherwise a ij ＝0。
The weight matrix of the system can be obtained by the method as follows:
the input degree matrix is as follows:
the Laplace matrix is:
definition x= [ x ] 1 ,x 2 ,...x 5 ] T For the current coordinate value of each ship, eta is the expected relative position of two adjacent points.
Whereby for each edge on the topology graph is available:
point x j Relative to point x i The difference from the expected value is: e, e ij ＝x i -x j -η
Point x j The differences with respect to all point distance expectations are:
where α is the relative position gain factor.
To enable the follower to track the leader track we need to get e j The value of (2) is reduced to 0, so that the speed of each follower will be subjected to e j By eliminating the influence of this error amount, the stability of the formation is achieved.
3) Local obstacle avoidance based on virtual obstacle potential field method
During the course of the track of the leader path by the follower in the convoy, if a situation that is too close to the obstacle occurs on the tracked path, collision risk is likely to occur. It is therefore necessary that each follower be able to independently implement a local collision avoidance to cope with this situation. The traditional artificial potential field method has the advantages of strong real-time performance, simple mathematical calculation, smoother planned path, easy programming and the like, so that the traditional artificial potential field method is widely used for solving the problem of local collision prevention, but the traditional artificial potential field method can be involved in the situation that a ship is stagnated due to a local minimum point. In order to solve the problem, a virtual obstacle potential field method is proposed, when a ship of a follower enters a position of a local minimum point, a virtual obstacle is added by judging the distribution of the obstacle, at the moment, the resultant force born by the ship is changed through the added virtual obstacle, and the virtual obstacle provides additional escape force for the ship to escape from the local minimum point. And the existence of the repulsive force can avoid the ship from sinking into the tiny point again.
Assuming that the real-time coordinate position of the ship is P= (x, y), the position of the target point is P g ＝(x g ,y g ) Then the gravitational field function is:
where the coefficient k is the gain coefficient of the gravitational field, and a suitable value is chosen experimentally.
The gradient relation between the gravitational force and the gravitational field can be known, and the expression of the gravitational force is as follows:
F a ＝-grad(U a )＝-k(P-P g ) (5)
the mathematical expression of the repulsive field is:
wherein the coefficient beta is the gain coefficient of the repulsive field, ρ is the distance from the ship to the obstacle, ρ 0 Is the radius of the repulsive force field, and the repulsive force beyond the range is zero.
The expression of the repulsive force is:
when a ship enters a position of a local minimum point, a virtual obstacle is introduced, and the virtual repulsive force field function is as follows:
wherein beta 'is a virtual repulsive force potential field constant larger than zero, ρ' is the distance between the ship and the virtual obstacle, ρ 0 ' is the distance of influence of the virtual obstacle on the vessel.
The virtual repulsive force is as follows:
the resultant force expression is thus:
the application steps of the virtual obstacle potential field method in the formation navigation of the ship are as follows:
step1: inputting parameters such as the current position, the sailing speed, the direction and the like of each ship;
step2: determining whether the ship of the follower enters the influence range of the obstacle, if so, calculating repulsive force and attractive force, otherwise, continuing sailing;
step3: when the follower has been affected by the obstacle, it is judged whether or not the resultant force received is 0. If the virtual obstacle is 0, adding the virtual obstacle, then recalculating resultant force, and judging the movement direction; if not 0, the direction of motion is calculated directly. Repeating this step until it leaves the area of influence of the obstacle;
step4: and when the ship of the follower breaks away from the collision risk, continuing to navigate according to the original track.
The invention has the positive effects that: a ship formation algorithm combining a fast travel leveling method with a virtual obstacle potential field method is provided. Firstly, carrying out global static path planning by adopting a fast traveling flat method, then realizing path tracking of a follower ship to a leader ship by adopting a leader-following formation control method, and finally, carrying out local collision prevention by adopting an improved virtual obstacle potential field method, and improving the situation that the ship possibly enters a local minimum point position by adding a virtual obstacle; the experimental result shows that the algorithm plans a route with the advantages of time, smoothness and safety for a leader in the ship, and forms stable formations rapidly; for an nxn grid, the overall computational complexity of the method is O (NlogN), the overall computational complexity of Dijkstra and a algorithms is O (N) 2 ) Compared with the Dijkstra algorithm and the A-type algorithm, the method has obvious improvement in running speed; the ship can be prevented from being bumped timely when encountering obstacles at collision risk, and the problem that the traditional artificial potential field method cannot solve is solved and is separated from a local minimum point is solved.
Drawings
FIG. 1 is a diagram of a marine vessel formation system;
FIG. 2 is an initial map constructed;
FIG. 3 is a graph of velocity profiles obtained using the fast-marching flattening method;
FIG. 4 is a roadmap using the fast-marching flattening method;
FIG. 5 is a voyage route map of a formation using the present invention;
fig. 6 is an initial map in experimental example 2;
FIG. 7 is an error graph in Experimental example 2;
FIG. 8 is a navigation trajectory of Experimental example 2;
FIG. 9 is a graph of the error of follower-3 in experimental example 2;
FIG. 10 is a graph showing the error of follower-2 in experimental example 2;
fig. 11 is a collision avoidance route map of experimental example 2 in which virtual obstacles are introduced;
fig. 12 is an initial map in experimental example 3;
FIG. 13 is an error graph in Experimental example 3;
fig. 14 is a collision avoidance line chart in experimental example 3.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the invention in any way, and any modifications or alterations to the invention, which would be readily apparent to a person of ordinary skill in the art, without departing from the technical solutions of the invention, are intended to fall within the scope of the claims of the invention.
Example 1
In fig. 2, an initial map is generated by MATLAB, the size of the map is 200x 200 pixels, and the path planning step of the fast-travel flat method is first entered:
step1: converting the environment into a binary mesh map, wherein black areas represent obstacles, such as land or islands, and white areas represent free space;
step2: iterating all units regarded as obstacles on a propagation surface in the graph to obtain a velocity potential graph as shown in fig. 3, wherein values in the grid represent the distance between the units and the nearest obstacle, the range of values is 0-1, and points with low values represent that the current position is possibly too close to the obstacle, so that the ship can navigate in a region with high values;
step3: iterating again from the end point on the propagation surface in the graph on the basis of the velocity potential graph W (x), and obtaining an arrival time map;
step4: gradient descent is carried out on the whole arrival time map to obtain a path comprehensively considering the arrival time, smoothness and safety aspects, as shown in fig. 4;
then combining the rapid travelling flattening method with the formation control based on the Laplace matrix, and providing that the formation advances to the end point in a formation with an included angle of 60 degrees between two wings so that a follower keeps sailing in unison with a leader, and entering a formation control step based on the Laplace matrix;
step1: calculating an incidence matrix, a weight matrix and a Laplace matrix of the multi-ship formation system diagram;
step2: calculating the sum of relative error values of each ship relative to other ships;
step3: stabilizing the formation by eliminating the error; the path curve in fig. 5 can be finally obtained.
Therefore, the method can realize the stability and consistency of formation.
Example 2
When the leader is tracked by using the leader following method, if the situation that the follower is too close to the obstacle occurs on the tracked path, the follower is likely to have collision risk, so the problem of local collision avoidance needs to be solved.
Initial information of the leader and each follower is given as shown in table 1.
TABLE 1 Ship initial information
The preset obstacle is shown by a cross in fig. 6, coordinates of the obstacle points are (0.4, 0.8), (-0.5, 1) and (3.1, 3.4), the collision radius of the obstacle is 50 meters, and the influence distance is 200 meters. The leader is represented by a red circle, the follower is represented by another circle, the leader runs along a pre-planned path, in this experiment it is specified to run towards the target point (5, 5), the remaining followers track the leader movement in a pre-set formation (two wings at 60 ° angle, the distance between adjacent vessels on the same side is 0.2 km).
As can be seen from the relative error plot (fig. 7) and the voyage route plot (fig. 8), the follower was tracking the leader's trajectory for the first 2 minutes and 30 seconds.
As shown in fig. 9, at 2.7min, the follower-3 senses the existence of the obstacle, and enters a collision avoidance state at this time, and enters a local obstacle avoidance step of the virtual obstacle potential field method:
step1: inputting parameters such as the current position, the sailing speed, the direction and the like of the ship and perceived obstacle information;
step2: calculating the attraction and repulsion force of the ship in real time according to formulas (4), (5), (6) and (7);
step3: judging whether the resultant force is 0, wherein the figure shows that the resultant force of the ship is not 0 all the time because the obstacle and the path tracking point are not on the same straight line, calculating the motion direction at the moment through the real-time resultant force, and repeating the steps until the obstacle leaves the influence range of the obstacle;
step4: and continuing sailing according to the original track when the ship of the follower breaks away from the collision risk in 3.2 min.
As also shown in FIG. 10, follower-2 felt the presence of an obstacle at 4.6min and completed the collision avoidance operation at 5.2 min.
During the following voyage, as shown in fig. 11, at about 12min, follower-4 is in the same line with the obstacle and the path tracking point, and at this time, enters the local obstacle avoidance Step3 of the virtual obstacle potential field method: at this time, a virtual obstacle is introduced in the left direction thereof, which is indicated by a red cross in the figure, the resultant force and the moving direction of the ship are changed by adding a virtual repulsive force, and this step is repeated until it leaves the influence range of the obstacle; step4: and continuing sailing according to the original track when the ship of the follower breaks away from the collision risk at 12.4 min. Eventually, at about 14 minutes, all followers reach the preset position, after which a stable structure with the leader can be maintained.
Example 3
The experiment verifies the effectiveness of the path tracking method when the path of the leader is tracked by the follower and the situation of multiple obstacles appears on the tracked path.
Initial information of the leader and each follower is given as shown in table 2.
As shown in fig. 12, the leader is represented by a black circle, the follower is represented by a circle of other colors, and the preset obstacle is represented by a cross.
TABLE 2 Ship initial information
The leader was driven along a pre-planned path, in this experiment defined as driving towards the target point (9, 9), and the remaining followers tracked the leader movement in a pre-set formation (two wings at 60 ° angle, two adjacent vessels on the same side 0.5km apart).
As can be seen from the relative error graph (fig. 13) and the navigation line graph (fig. 14), the follower enters the multi-obstacle region at about 7.5min, and enters the collision prevention state. And finally, recovering the stable formation at about 17 min.
Experimental example 1
The following experiment proves that the result of the invention is accurate;
it can be seen through example 1 that the route planned using the fast travel square law takes time, smoothness and safety into consideration at the same time, so that the route planned by the present invention is more advantageous for navigation of the ship. While the run time using the present invention was 3 minutes 40 seconds, the run time using the a algorithm was 16 minutes 24 seconds, and the present invention reduced the run time by 12 minutes 44 seconds.
It can be seen from example 2 that the use of the virtual barrier potential field method effectively solves the problem that the conventional artificial potential field method cannot solve. When the follower is in a stress balance, namely, a position in which the local minimum point is trapped, the method can effectively help the follower to get rid of the local minimum point by adding a virtual repulsive force, and the added virtual obstacle can ensure that the ship cannot be trapped in the position again later.
Conclusion:
the track tracking and formation holding effects of the follower on the leader are realized by adopting a rapid travelling flattening method to plan a collision-free and smooth path for reference during navigation of the ship and adopting a leader-following control method. Aiming at the situation that a follower possibly encounters an obstacle in the course of navigation, a virtual obstacle potential field method is provided for solving, so that the follower can independently take collision avoidance actions, the method can effectively avoid the ship from entering the position of a local minimum point, and finally, the consistency theory is reused to return to the team after independent collision avoidance is completed.
Claims (1)
1. A ship formation algorithm combining a fast marching flattening method with a virtual obstacle potential field method, comprising the steps of:
1) Path planning based on fast travel flattening method
The fast travel flattening method comprises the following steps:
step1: modeling a navigation environment and converting the environment into a binary grid map; marking the cells belonging to the obstacle and the cells corresponding to the passable area respectively;
step2: the fast-marching flattening method takes each unit marked as an obstacle in a map as a wave source, and simultaneously expands a plurality of waves, wherein the result value of each unit in the map represents the time when the waves need to reach the nearest obstacle, and is proportional to the distance from the obstacle; the potential diagram obtained in the step is a velocity potential and is marked as W (x), each grid in the velocity potential diagram has a value which indicates the distance between the grid and the nearest barrier, and the value range is 0-1;
step3: on the basis of the potential map W (x), the target point is taken as a unique wave source to ensure that a global minimum spreads the wave on the map until the initial point is reached; for each cell in the feasible region, extracting the expansion speed of the wave from the velocity potential diagram W (x) calculated in the previous step;
step4: starting from a starting point of a ship, performing gradient descent on the whole arrival time map, and moving to a target point of the ship, so that a global minimum of the map is moved to obtain a path comprehensively considering the arrival time, smoothness and safety;
2) Capacity control based on Laplace matrix
For a lead-following multi-vessel formation system, each vessel in the system can be regarded as a node in the network, the information transfer links between vessels can be regarded as edges connecting different nodes, and the multi-vessel system and the communication network thereof can be modeled as a graph;
the directed graph is represented by g= { V, E }, where v= { V 1 ,v 2 ,...,v n N vessels in the system,
representing information transfer links between ships;
the laplace matrix L is defined as: l=d-a, where D is the entry matrix of the graph, and the elements on its diagonal are the sum of the entries of the nodes; a is the weight matrix of the graph, if the vertex v is the head of the edge E, then element a in the A matrix ij =1, otherwise a ij ＝0；
Definition x= [ x ] 1 ,x 2 ,...x 5 ] T For the current coordinate value of each ship, eta is the expected relative position of two adjacent points;
for each edge on the topology graph, it is available:
point x j Relative to point x i The difference from the expected value is: e, e ij ＝x i -x j -η
Point x j The differences with respect to all point distance expectations are:
wherein alpha is a relative position gain coefficient;
in order to enable the follower to track the leader track, e is required to be j The value of (2) is reduced to 0, and the formation is stabilized by eliminating the error amount;
3) Local obstacle avoidance based on virtual obstacle potential field method
ShipThe real-time coordinate position of (2) is P= (x, y), and the position of the target point is P g ＝(x g ,y g ) Then the gravitational field function is:
wherein the coefficient k is the gain coefficient of the gravitational field, and a proper value is selected through experiments;
the gradient relation between the gravitational force and the gravitational field can be known:
F a ＝-grad(U a )＝-k(P-P g ) (2)
the mathematical expression of the repulsive field is:
wherein the coefficient beta is the gain coefficient of the repulsive field, ρ is the distance from the ship to the obstacle, ρ 0 Is the influence radius of the repulsive force field, and the repulsive force exceeding the range is zero;
the expression of the repulsive force is:
when a ship enters a position of a local minimum point, a virtual obstacle is introduced, and the virtual repulsive force field function is as follows:
wherein beta 'is a virtual repulsive force potential field constant larger than zero, ρ' is the distance between the ship and the virtual obstacle, ρ '' 0 Is the influence distance of the virtual barrier to the ship;
the virtual repulsive force is as follows:
the resultant force expression is thus:
the application steps of the virtual obstacle potential field method in the formation navigation of the ship are as follows:
step1: inputting parameters such as the current position, the sailing speed, the direction and the like of each ship;
step2: determining whether the ship of the follower enters the influence range of the obstacle, if so, calculating repulsive force and attractive force, otherwise, continuing sailing;
step3: when the follower has been affected by the obstacle, it is judged whether or not the resultant force received is 0. If the virtual obstacle is 0, adding the virtual obstacle, then recalculating resultant force, and judging the movement direction; if the motion direction is not 0, directly calculating the motion direction; repeating this step until it leaves the area of influence of the obstacle;
step4: and when the ship of the follower breaks away from the collision risk, continuing to navigate according to the original track.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310166496.9A CN116400679A (en) | 2023-02-25 | 2023-02-25 | Ship formation algorithm combining rapid travel leveling method and virtual obstacle potential field method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310166496.9A CN116400679A (en) | 2023-02-25 | 2023-02-25 | Ship formation algorithm combining rapid travel leveling method and virtual obstacle potential field method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116400679A true CN116400679A (en) | 2023-07-07 |
Family
ID=87011340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310166496.9A Pending CN116400679A (en) | 2023-02-25 | 2023-02-25 | Ship formation algorithm combining rapid travel leveling method and virtual obstacle potential field method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116400679A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116661502A (en) * | 2023-07-25 | 2023-08-29 | 吉林农业大学 | Intelligent agricultural unmanned aerial vehicle path planning method |
-
2023
- 2023-02-25 CN CN202310166496.9A patent/CN116400679A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116661502A (en) * | 2023-07-25 | 2023-08-29 | 吉林农业大学 | Intelligent agricultural unmanned aerial vehicle path planning method |
| CN116661502B (en) * | 2023-07-25 | 2023-10-10 | 吉林农业大学 | Intelligent agricultural unmanned aerial vehicle path planning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | The review unmanned surface vehicle path planning: Based on multi-modality constraint | |
| Guo et al. | Global path planning and multi-objective path control for unmanned surface vehicle based on modified particle swarm optimization (PSO) algorithm | |
| Candeloro et al. | A Voronoi-diagram-based dynamic path-planning system for underactuated marine vessels | |
| CN109933067B (en) | Unmanned ship collision avoidance method based on genetic algorithm and particle swarm algorithm | |
| Chen et al. | Optimal time-consuming path planning for autonomous underwater vehicles based on a dynamic neural network model in ocean current environments | |
| Zeng et al. | Shell space decomposition based path planning for AUVs operating in a variable environment | |
| Tan et al. | Fast marching square method based intelligent navigation of the unmanned surface vehicle swarm in restricted waters | |
| CN109782779B (en) | AUV path planning method in ocean current environment based on population hyperheuristic algorithm | |
| Li et al. | Autonomous underwater vehicle optimal path planning method for seabed terrain matching navigation | |
| Zhuang et al. | Cooperative path planning of multiple autonomous underwater vehicles operating in dynamic ocean environment | |
| CN112558612B (en) | Heterogeneous intelligent agent formation control method based on cloud model quantum genetic algorithm | |
| CN112650246B (en) | Ship autonomous navigation method and device | |
| Wang et al. | Local path optimization method for unmanned ship based on particle swarm acceleration calculation and dynamic optimal control | |
| Xu et al. | Heuristic and random search algorithm in optimization of route planning for Robot’s geomagnetic navigation | |
| Li et al. | Path planning method for AUV docking based on adaptive quantum-behaved particle swarm optimization | |
| CN116400679A (en) | Ship formation algorithm combining rapid travel leveling method and virtual obstacle potential field method | |
| Deraj et al. | Deep reinforcement learning based controller for ship navigation | |
| Li et al. | Three-dimensional path planning for AUVs in ocean currents environment based on an improved compression factor particle swarm optimization algorithm | |
| Pairet et al. | Uncertainty-based online mapping and motion planning for marine robotics guidance | |
| He et al. | A novel model predictive artificial potential field based ship motion planning method considering COLREGs for complex encounter scenarios | |
| Yang et al. | Intelligent path planning of underwater robot based on reinforcement learning | |
| CN112819255A (en) | Particle swarm-genetic algorithm-based multi-criterion ship route determining method and device, computer equipment and storage medium | |
| Yao et al. | Multi-USV cooperative path planning by window update based self-organizing map and spectral clustering | |
| Su et al. | A constrained locking sweeping method and velocity obstacle based path planning algorithm for unmanned surface vehicles in complex maritime traffic scenarios | |
| Lee et al. | Multi-resolution path planning for marine surface vehicle considering environmental effects |
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 |