Path optimization method and system for traversal monitoring of unmanned ship in sea area with complex terrain

Abstract

The invention discloses a path optimization method and system for traversal monitoring of an unmanned ship in a sea area with complex terrain. The method comprises the following steps: firstly, determining distribution of points to be traversed on grid lines in a traversal area range; when the obstacles do not exist at all the to-be-traversed points around the starting point, judging whether a to-be-traversed point exists around the starting point or not; if yes, selecting the point to be traversed with the maximum probability, taking a path between the starting point and the point to be traversed with the maximum probability as an optimal working path, and taking the point to be traversed with the maximum probability as the next starting point; if not, selecting the to-be-traversed point meeting the traversing condition from the residual pool as the next starting point, and judging whether the residual pool is empty or not; if the residual pool is empty, ending the traversal; and if the remaining pool is not empty,re-judging the obstacle. According to the scheme disclosed by the invention, traversal inspection in offshore multi-island reef, submerged reef and multi-bay areas is realized, and repeated paths are greatly reduced while omission of bays and dead angles is avoided.

Description

technical field [0001] The invention relates to the technical field of path optimization, in particular to a path optimization method and system for unmanned ships in traversal monitoring of sea areas with complex topography. Background technique [0002] my country has a vast territory, a long coastline, and numerous archipelagos and submerged reefs. All-weather and normalized monitoring of the marine environment near the coast and around the islands, and real-time grasp of the changing trends of the water surface and underwater environmental elements are of great importance to environmental protection, security, and national defense. is of great significance. However, the terrain conditions of "coastal landform" are complex, and generally belong to areas with many islands, reefs, and bays. It is extremely difficult to monitor the marine environment in coastal waters by using traditional manned ships for manual sampling. The fuel is easy to cause secondary pollution to the ...

AI Technical Summary

Problems solved by technology

However, according to the experience in the actual use process, the disadvantage of the artificial potential field method is that once the terrain is too complex, the unmanned ship may fall into the local optimal solution when using this algorithm to complete the traversal path planning, and then produce missing areas; Algorithm search efficiency is low, and it is difficult to meet the ergodicity requirements in the face of complex and changeable seabed environments; neural network algorithms and heuristic algorithms need to collect enough training sample data in advance to train the algorithm model, and there will be random selection and repeated coverage defects, it is not suitable for the requirements of online real-time terrain coverage scanning tasks in unknown and complex seabed areas

[0007] To sum up, the traditional path traversal algorithm suitable for unmanned ships is difficult to meet the traversal and inspection needs of unmanned ships in offshore multi-island reefs, submerged reefs, and multi-bay areas.

Images