A ship route planning method and system for exploring potential water surface dangerous areas

Abstract

The application relates to the technical field of ship path planning, and particularly discloses a ship path planning method and system for exploring potential water surface dangerous areas, which comprises the following steps: acquiring known dangerous areas and potential dangerous areas; generating observation points on the edges of each potential dangerous area to obtain a set of potential observation points; establishing a visibility graph, wherein the nodes of the visibility graph are the observation points, the edges are paths between two observation points which do not pass through the known dangerous areas and the potential dangerous areas, and the edge weight is the length of the path; solving a TSP problem with group constraints by using an improved ant colony algorithm on the visibility graph to obtain a shortest path covering all the potential dangerous areas, which is used as a ship planning path. The application realizes shortest path planning of a ship in a target sea area to bypass the known dangerous areas and traverse the edges of all the potential dangerous areas, and realizes safe and efficient shortest path planning.

Description

Technical Field

[0001] This invention relates to the field of ship path planning technology, and in particular to a ship path planning method and system for detecting potential surface hazard areas. Background Technology

[0002] In fields such as marine exploration and environmental monitoring, ships need to approach potentially dangerous areas for identification and exploration while avoiding known dangerous areas (such as reefs, shipwrecks, and oil spills).

[0003] Traditional path planning methods struggle to simultaneously address the optimization requirements of obstacle avoidance and the Traveling Salesman Problem (TSP), leading to path redundancy or collision risks. Traditional path planning methods (such as the A* algorithm) can only solve the shortest path problem and cannot handle constraints requiring traversal of multiple potentially hazardous area edges. While TSP solutions can cover multiple nodes, they do not support access problems with grouping constraints, do not consider obstacle avoidance requirements in known hazardous areas, and lack dynamic collision detection mechanisms. Summary of the Invention

[0004] The present invention aims to solve the above-mentioned problems. To this end, the present invention provides a method and system for ship path planning to explore potential surface hazard areas, realizing the shortest path planning for ships to bypass known hazard areas and traverse the edges of all potential hazard areas within the target sea area, thus achieving safe and efficient shortest path planning.

[0005] This invention provides a method for ship path planning to detect potential surface hazard areas, and the technical solution adopted is as follows: including: S1: Obtain known and potential danger zones in the mission area; S2: Generate observation points at the edge of each potential hazard zone to obtain a set of potential observation points; S3: Based on the set of potential observation points, construct a visibility graph. The nodes of the visibility graph are observation points, and the edges are paths between two observation points that do not cross known danger zones or potential danger zones. The edge weight is the length of the path. S4: The improved ant colony algorithm is used to solve the TSP problem with group constraints on the visibility graph to obtain a shortest path covering all potential hazard areas, which is used as the ship planning path; the ship planning path avoids all known hazard areas and potential hazard areas, and includes at least one observation point in each potential hazard area. Step S4 specifically includes: S4.1: The ant colony algorithm is used to initialize the node set, group constraints, pheromone matrix, heuristic information, and ant colony parameters; among them, the group constraint is that the set of observation points in the same potential danger zone belongs to a group; S4.2: For each ant, a path is constructed independently with a random starting point. During the path construction process, if there are unvisited nodes that do not belong to the covered group, the attractiveness of all points in the uncovered group is temporarily amplified. S4.3: For all paths constructed by ants, calculate the path fitness, select elite ant paths, and ensure that the pheromone on the edges of elite ant paths does not evaporate or decay, while the pheromone on the remaining edges does evaporate or decay, thus completing the pheromone update. S4.4: Iterate through steps S4.2-S4.3 until the iteration stopping condition is met, and return the valid shortest path among all ants to obtain the ship planning path.

[0006] Furthermore, in step S2, observation points are generated at equal angles at the edge of each potential hazard zone, and the vertical distance between the observation points and the edge of the potential hazard zone is not less than a safety threshold.

[0007] Furthermore, in step S2, observation points located in known danger zones and potential danger zones are removed from the set of potential observation points.

[0008] Furthermore, in step S2, observation points that provide poor visibility to known and potential hazard areas are removed from the set of potential observation points.

[0009] Furthermore, step S3 includes: S3.1: Generate the initial straight-line path for each pair of observation points based on the set of potential observation points; S3.2: Traverse and check whether the initial straight path intersects with the known danger zone and the potential danger zone; if they do not intersect, use the length of the initial straight path of the pair of observation points as the edge weight; if they intersect, generate a detour path by going around the known danger zone and the potential danger zone, and use the length of the detour path as the edge weight.

[0010] Furthermore, S3.3: retain edges whose weights are less than the length threshold.

[0011] Furthermore, in step S4.2, when there are unvisited nodes that do not belong to the covered group, the attractive force of all points in the uncovered group is temporarily amplified, and the calculation formula is expressed as follows: in, For the node To the node The probability of choosing, For the node To the node pheromone concentration, For the node Total number of edges started from, For the node To the node pheromone concentration, For the node To the node Heuristic information, For the node To the node The amplified heuristic information, For the node To the node Heuristic information, This is the heuristic amplification factor for the uncovered group, used to increase the heuristic information weight of nodes in the uncovered group. As the first heuristic factor, It is the second heuristic factor.

[0012] Furthermore, in step S4.2, when there are unvisited nodes that do not belong to the covered group, the local pheromone update strategy adopts... ,in, The local pheromone evaporation coefficient. , The global pheromone evaporation coefficient. It is much smaller than.

[0013] This invention also provides a ship path planning system for detecting potential surface hazard areas, the technical solution of which includes: The danger zone information acquisition module is used to acquire known and potential danger zones in the mission sea area; The observation point generation module is used to generate observation points at the edge of each potential hazard zone, thus obtaining a set of potential observation points. The visibility graph construction module is used to build a visibility graph based on a set of potential observation points. The nodes of the visibility graph are observation points, the edges are paths between two observation points that do not cross known danger zones or potential danger zones, and the edge weights are the lengths of the paths. The path calculation module is used to solve the TSP problem with group constraints on the visibility map using an improved ant colony algorithm to obtain a shortest path covering all potential hazard areas, which serves as the ship planning path. The ship planning path avoids all known and potential hazard areas and includes at least one observation point for each potential hazard area.

[0014] The above-described one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: 1. This invention proposes an improved ant colony algorithm with group constraints. Traditional ant colony algorithms only solve the standard TSP problem and cannot handle grouped access problems where each group visits at least one node. This invention introduces a group constraint mechanism, defining the set of observation points for each potential danger zone as a group. Through a forced preference strategy for uncovered groups, the heuristic information of nodes in uncovered groups is temporarily amplified, guiding ants to prioritize visiting uncovered groups and ensuring that the path covers all potential danger zones. This invention is particularly suitable for exploration tasks of dangerous areas on the water surface in complex scenarios (multiple known danger zones and multiple potential danger zones). Because the task requires traversing the edges of multiple areas while ensuring the safety of the ship, this algorithm accelerates convergence through a positive feedback mechanism and avoids local optima.

[0015] 2. The observation points in this invention are not simply uniformly distributed, but are generated at equal angles. Through intrusive verification and visibility optimization, invalid nodes are reduced, improving computational efficiency. Compared to random sampling or fixed-density methods, this invention can reduce the size of the observation point set, decrease the complexity of the graph model, and significantly improve path quality. Due to the dynamic complexity of the marine environment, visibility optimization directly addresses ship positioning errors and obstacle occlusion issues, improving path feasibility.

[0016] 3. When constructing the visibility graph, this invention not only calculates the Euclidean distance edge weights, but also introduces path detours. When a straight line is blocked by a danger zone, a circular arc detour is used instead, thereby achieving unified optimization of obstacle avoidance and path length, improving path safety, and ensuring that the path is actually navigable through geometric calculations.

[0017] In summary, this invention solves the core problem of "obstacle avoidance-traversal-global optimization" in the exploration of dangerous areas on the sea surface through an innovative combination of technologies. It has both theoretical innovation and engineering practical value, and provides reliable technical support for ship autonomous navigation.

[0018] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is a flowchart of the method provided by the present invention.

[0021] Figure 2 This is an implementation effect diagram of the environment modeling and initialization provided by the present invention.

[0022] Figure 3 This is an implementation effect diagram of the observation point set generation provided by the present invention.

[0023] Figure 4 This is an implementation effect diagram of the visibility graph construction provided by the present invention.

[0024] Figure 5 This is a diagram illustrating the implementation effect of the group constraint TSP solution provided by the present invention.

[0025] Figure 6 This is a diagram illustrating the implementation effect of the path smoothing process provided by the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention. The following embodiments are used to illustrate this invention but should not be used to limit the scope of this invention.

[0027] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0028] The following is combined Figures 1 to 6 The present invention will be further described in detail below, providing a method and system for ship path planning to detect potential surface hazard areas: In this embodiment, as Figure 1 As shown, a method for ship path planning to explore potential surface hazard areas is provided, including the following steps: S1: Obtain known and potential danger zones in the mission area.

[0029] In this embodiment, known danger zones and potential danger zones are abstracted as circular areas, and their information includes the coordinates of the center and the safety radius.

[0030] In the mission area, based on the information from previous surveys, the coordinates and radii of known and potential danger zones were obtained.

[0031] The known set of danger zones is , ; The potential hazard zone is set as follows , ; in, For the first One known danger zone, Given the total number of known danger zones, For the first One known danger zone, For the first The x-coordinate of the center of a known danger zone. For the first The ordinate of the center of a known danger zone. For the first The safe radius of a known danger zone For the first A potentially dangerous area, This represents the total number of potential hazard zones. For the first A potentially dangerous area, For the first The x-coordinate of the center of each potential danger zone. For the first The ordinate of the center of each potential danger zone. For the first The safety radius of a potential danger zone.

[0032] like Figure 2 As shown, there are 3 known danger zones and 4 potential danger zones to be explored in the mission area. The relevant information is as follows: Danger zone D1 is known to have a center at (100.0, 150.0) and a radius of 30.0. Danger zone D2 is known to have a center at (300.0, 200.0) and a radius of 25.0. Danger zone D3 is known to have a center at (450.0, 350.0) and a radius of 40.0. Potential hazard zone P1: Center (200.0, 50.0), radius 20.0; Potential hazard zone P2: Center (350.0, 350.0), radius 35.0; Potential hazard zone P3: Center (150.0, 400.0), radius 28.0; Potential hazard zone P4: Center (400.0, 150.0), radius 22.0.

[0033] The ship's departure position is at coordinates (0,0).

[0034] S2: Generate observation points distributed at equal angles at the edge of each potential hazard zone to obtain a set of potential observation points.

[0035] Specifically, the following steps are included: S2.1: Observation point generation: Observation points are generated at equal angles at the edge of each potential hazard zone. The vertical distance between the observation point and the edge of the potential hazard zone is not less than the safety threshold.

[0036] In this embodiment, the potential danger zone Using the center of the circle as a reference, generate Each direction is at an equal angle, and in each direction is a distance from the center of the circle. Observation points are generated at the specified locations, resulting in an observation point set. .in, The safety threshold is set based on the ship's handling precision and maneuverability. For the first The set of all observation points in a potential hazard area; , For the first The first potential danger zone One observation point.

[0037] By summing up the observation points of all potential hazard areas, we obtain the potential observation point set. : .

[0038] S2.2: Remove observation points located in known hazard zones and potential hazard zones from the potential observation point set.

[0039] Observation point intrusion check: If the observation point has entered a known or potential danger zone, then remove the observation point from the designated area. Delete it.

[0040] S2.3: Remove observation points from the potential observation point set that do not provide good visibility to known and potential hazard areas.

[0041] Observation point optimization and elimination: A traversal method is used to connect the current observation point and the set of potential observation points respectively. For other observation points, multiple line segments are obtained. It is determined whether the line segments pass through known danger zones or potential danger zones. The proportion of line segments that pass through known danger zones or potential danger zones to all line segments of the current observation point is counted. If the proportion exceeds the preset visibility threshold, it means that the external visibility (known danger zones and potential danger zones) of the current observation point is low, and it is removed from the potential observation points. Only observation points with high visibility to other observation points are retained to improve the calculation efficiency of subsequent steps.

[0042] like Figure 3 As shown, 12 observation points at equal angles are generated for each potential hazard area (ships must pass through these observation points to investigate the potential hazard area), for a total of 48 observation points. Safety threshold. A 10-meter range was used. The visibility threshold was set to 65%, and two low-visibility observation points were identified (belonging to the potential hazard zone P3). Ultimately, the potential observation point cluster included 46 observation points (V1-V46).

[0043] S3: Based on the set of potential observation points, construct a visibility graph. The nodes of the visibility graph are observation points, and the edges are paths between two observation points that do not cross known danger zones or potential danger zones. The edge weight is the length of the path.

[0044] Specifically, the following steps are included: S3.1: Based on the set of potential observation points, generate the initial straight-line path for each pair of observation points. Using the observation points in the set of potential observation points as nodes, traverse the nodes to establish the initial straight-line path for each pair of nodes (observation points): in, For edge set, For the node To the node The path; For the a-th node, For the b-th node, Define a function for a straight path.

[0045] S3.2: Generate the edge weights for each pair of observation points based on the initial straight path, known danger zone, and potential danger zone.

[0046] The process iterates through the area to check if the initial straight path intersects with known or potential hazard zones. If they do not intersect, the length of the initial straight path between the two observation points is used as the edge weight, i.e., the edge weight is the Euclidean distance between the two observation points. , for The edge weights are calculated; if they intersect, a detour path (obstacle avoidance path) is generated by circling the circumference of the known danger zone and the potential danger zone, and the length of the detour path is calculated as the edge weight. If it intersects with a certain hazard area, and the hazard area includes both known and potential hazard areas, then... ,in, For the initial straight path The first intersection with the danger zone, For the initial straight path The second intersection with the danger zone, To travel along the circumference of the danger zone from arrive The length of the detour path, a shorter arc path. When intersecting with multiple danger zones, a detour path is generated for each danger zone, and then the edge weight is calculated.

[0047] Calculate the edge weights for each pair of observation points to obtain the weight set. , ; S3.3: Optimize the path graph: Only retain edges with weights less than the length threshold, delete long edges, and reduce graph complexity. In this embodiment, the length threshold is 80% of the diagonal length of the task area.

[0048] Finally, we obtain the set of potential observation points. (Node set), Edge set Weight set Visibility map , In the visibility graph, nodes are observation points, edges are paths between two observation points that do not cross known danger zones or potential danger zones, and edge weights are the lengths of the paths.

[0049] like Figure 4 As shown, the visibility graph includes 47 nodes (1 starting point and 46 observation points) and 1074 valid edges, with 7 excessively long edges removed. In the graph, green lines represent initial straight paths (467 in total), and brown lines represent detour paths (607 in total).

[0050] S4: An improved ant colony algorithm is used to solve the TSP problem with group constraints on the visibility graph, resulting in a shortest path covering all potential hazard zones, which serves as the ship planning path. The ship planning path avoids all hazard zones and includes at least one observation point for each potential hazard zone.

[0051] Unlike the traditional Traveling Salesman Problem (TSP) that traverses all nodes, this embodiment traverses all potential hazard zones. Each potential hazard zone is not a single point, but a collection of many nodes. Moreover, this embodiment does not need to traverse every node of every potential hazard zone; it is sufficient to pass through at least one node of each potential hazard zone.

[0052] Specifically, the following steps are included: S4.1: Modeling and Initialization: Ant colony algorithm is used to initialize node set, group constraints, pheromone matrix, heuristic information and ant colony parameter information.

[0053] (1) The node set and group constraint relationship is given by step S3. The group constraint is that the set of observation points in the same potential hazard area belongs to one group; (2) The pheromone matrix is , , For the edge The pheromone concentration on the surface is initially uniformly distributed; (3) Heuristic information is , ; (4) Ant colony parameter information includes: number of ants (Proportional to the number of nodes), Global pheromone evaporation coefficient The first heuristic factor (Corresponding pheromone weights), second heuristic factor (Corresponding heuristic information weights), group constraint penalty coefficients (Paths used to penalize uncovered groups), the set of visited nodes. , , For visited nodes, the sets that have been covered , .

[0054] S4.2: Ant path construction: Construct a path independently for each ant, using a strategy of random starting point, forced preference for uncovered groups, and local pheromone evaporation, iterating until the ant path covers all groups, ensuring that all potential danger zones are traversed.

[0055] If any unvisited node does not belong to the covered group, meaning all groups have not yet been covered, a forced preference strategy for uncovered groups is adopted. This strategy amplifies the heuristic information of nodes in uncovered groups, increases the preference for uncovered groups, and induces ants to prioritize visiting nodes in uncovered groups. The calculation formula for this strategy is expressed as follows: in, For the node To the node The probability of choosing, For the node To the node pheromone concentration, For the node Total number of edges started from, For the node To the node pheromone concentration, For the node To the node Heuristic information, For the node To the node The amplified heuristic information, For the node To the node Heuristic information, This is the heuristic amplification factor for uncovered groups, used to increase the heuristic information weight of nodes in uncovered groups.

[0056] Local pheromones (when ants move) are used Update strategy The local pheromone evaporation coefficient. This avoids excessive repetition of path edges. It is much smaller than.

[0057] This embodiment adds a grouping concept to the ant colony algorithm: when an unvisited node does not belong to a covered group, the attractiveness of all nodes in the unvisited group is temporarily amplified, thus ensuring that at least one node in each group is visited. As the iteration progresses, the attractiveness of the nodes in the group will return to normal once the group has been visited.

[0058] If all unvisited nodes belong to the covered group (meaning all groups have been covered and there are no uncovered groups), the following formula is used to calculate the slave node count. To the node Selection probability: .

[0059] The termination condition for constructing a path for a single ant is: when all groups are covered, or the number of visited nodes exceeds [a certain threshold]. Stop when the time comes.

[0060] S4.3: Pheromone Update: For all paths constructed by ants, calculate the path fitness, select elite ant paths, and use differentiated local and global pheromone update strategies to complete the pheromone update.

[0061] After all ants have completed their work, calculate the fitness of each ant based on the path length constructed by each ant and its coverage of all groups. , ,in, The length of the path constructed for the ant. This represents the number of uncovered groups. The group constraint penalty coefficient.

[0062] Pheromones are updated according to the following strategy: pheromones on edges of the top 10% of ant paths (elite ant paths) do not decay or evaporate; pheromones on other edges are updated according to the following strategy. Volatilization attenuation occurs.

[0063] S4.4: Iterate through steps S4.2-S4.3 until the iteration stopping condition is met, returning the shortest valid path among all ants. This path covers all groups and has the shortest length, yielding the ship's planned path. The ship's planned path includes the ship's observation point visit sequence.

[0064] Iteration stopping condition: All groups are fully covered, and the shortest path length is output in two consecutive iterations. and historical shortest path length Compared to the less significant improvement, in this embodiment, .

[0065] S4.5: Smooth the planned ship path to generate a smooth path. The planned ship path is a polygonal path. Cubic spline interpolation or tangent transition arcs are used to smooth the planned ship path, generating a smooth path. Then, feasibility verification is performed to verify the safety and executability of the smoothed path; adjustments are made to any problematic sections.

[0066] In this embodiment, the number of ants Take 50 animals, global pheromone evaporation coefficient Take 0.3, Take 2.1, Set the group constraint penalty coefficient to 0.8. Take 0.15 as the heuristic amplification factor for the uncovered group. Take 0.15.

[0067] Based on the ant colony algorithm, the TSP problem with group constraints was solved. After 13 iterations, it converged, and the optimal path was obtained as follows: Node 0 (0,0) → Node 7 (170.0,50.0) → Node 6 (174.0,65.0) → Node 41 (368.0,150.0) → Node 20 (311.0,327.5) → Node 33 (169,367.1). This path has 6 nodes and a length of 738.38 meters. Figure 5 As shown.

[0068] Path smoothing: Node 41 (368.0, 150.0) was identified as a large-angle turning node. After smoothing with a tangent transition arc, the final smooth, executable path includes 15 nodes with a total length of 734.99 meters. Figure 6 As shown.

[0069] For missions involving the exploration of potentially hazardous areas on the water, vessels are generally required to wait for further instructions after completing the exploration and are not required to return directly.

[0070] This embodiment also provides a ship path planning system for detecting potential surface hazard areas, and the technical solution adopted is as follows: including: The danger zone information acquisition module is used to acquire known and potential danger zones in the mission sea area; The observation point generation module is used to generate observation points at the edge of each potential hazard zone, thus obtaining a set of potential observation points. The visibility graph construction module is used to build a visibility graph based on a set of potential observation points. The nodes of the visibility graph are observation points, the edges are paths between two observation points that do not cross known danger zones or potential danger zones, and the edge weights are the lengths of the paths. The path calculation module is used to solve the TSP problem with group constraints on the visibility map using an improved ant colony algorithm to obtain a shortest path covering all potential hazard areas, which serves as the ship planning path. The ship planning path avoids all known and potential hazard areas and includes at least one observation point for each potential hazard area.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for ship path planning to explore potential surface hazard areas, characterized in that, include: S1: Obtain known and potential danger zones in the mission area; S2: Generate observation points at the edge of each potential hazard zone to obtain a set of potential observation points; S3: Based on the set of potential observation points, construct a visibility graph. The nodes of the visibility graph are observation points, and the edges are paths between two observation points that do not cross known danger zones or potential danger zones. The edge weight is the length of the path. S4: The improved ant colony algorithm is used to solve the TSP problem with group constraints on the visibility graph to obtain a shortest path covering all potential hazard areas, which is used as the ship planning path. The vessel's planned route avoids all known and potential hazard areas and includes at least one observation point for each potential hazard area; S4 specifically includes: S4.1: The ant colony algorithm is used to initialize the node set, group constraints, pheromone matrix, heuristic information, and ant colony parameters; among them, the group constraint is that the set of observation points in the same potential danger zone belongs to a group; S4.2: For each ant, a path is constructed independently with a random starting point. During the path construction process, if there are unvisited nodes that do not belong to the covered group, the attractiveness of all points in the uncovered group is temporarily amplified. In step S4.2, when there are unvisited nodes that do not belong to the covered group, the attractive force of all points in the uncovered group is temporarily amplified. The calculation formula is expressed as follows: in, For the node To the node The probability of choosing, For the node To the node pheromone concentration, For the node Total number of edges started from, For the node To the node pheromone concentration, For the node To the node Heuristic information, For the node To the node The amplified heuristic information, For the node To the node Heuristic information, This is the heuristic amplification factor for the uncovered group, used to increase the heuristic information weight of nodes in the uncovered group. As the first heuristic factor, It is the second heuristic factor; In step S4.2, when there are unvisited nodes that do not belong to the covered group, the local pheromone update strategy adopts... ,in, The local pheromone evaporation coefficient. , The global pheromone evaporation coefficient. It is much smaller than; S4.3: For all paths constructed by ants, calculate the path fitness, select elite ant paths, and ensure that the pheromone on the edges of elite ant paths does not evaporate or decay, while the pheromone on the remaining edges does evaporate or decay, thus completing the pheromone update. S4.4: Iterate through steps S4.2-S4.3 until the iteration stopping condition is met, and return the shortest valid path among all ants to obtain the ship planning path.

2. The method for ship path planning for detecting potential surface hazard areas as described in claim 1, characterized in that, In step S2, observation points are generated at equal angles at the edge of each potential hazard zone, and the vertical distance between the observation points and the edge of the potential hazard zone is not less than a safety threshold.

3. The method for ship path planning for detecting potential surface hazard areas as described in claim 1, characterized in that, In step S2, observation points located in known danger zones and potential danger zones are removed from the set of potential observation points.

4. The method for ship path planning for detecting potential surface hazard areas as described in claim 1, characterized in that, In step S2, observation points that provide poor visibility to known and potential hazard areas are removed from the set of potential observation points.

5. The method for ship path planning for detecting potential surface hazard areas as described in claim 1, characterized in that, Step S3 includes: S3.1: Generate the initial straight-line path for each pair of observation points based on the set of potential observation points; S3.2: Traverse and check whether the initial straight path intersects with the known danger zone and the potential danger zone; if they do not intersect, use the length of the initial straight path of the pair of observation points as the edge weight; if they intersect, generate a detour path by going around the known danger zone and the potential danger zone, and use the length of the detour path as the edge weight.

6. The method for ship path planning for detecting potential surface hazard areas as described in claim 5, characterized in that, S3.3: Keep edges whose weights are less than the length threshold.

7. A ship path planning system for detecting potential surface hazard areas, characterized in that, A method for ship path planning for detecting potential surface hazard areas as described in any one of claims 1 to 6, comprising: The danger zone information acquisition module is used to acquire known and potential danger zones in the mission sea area; The observation point generation module is used to generate observation points at the edge of each potential hazard zone, thus obtaining a set of potential observation points. The visibility graph construction module is used to build a visibility graph based on a set of potential observation points. The nodes of the visibility graph are observation points, the edges are paths between two observation points that do not cross known danger zones or potential danger zones, and the edge weights are the lengths of the paths. The path calculation module is used to solve the TSP problem with group constraints on the visibility map using an improved ant colony algorithm to obtain a shortest path covering all potential hazard areas, which serves as the ship planning path. The ship planning path avoids all known and potential hazard areas and includes at least one observation point for each potential hazard area.

Images