A dynamic collision avoidance method for unmanned boats

Abstract

The invention discloses a dynamic collision avoidance method for an unmanned ship based on a sparse iterative potential field algorithm. First, a safe distance model and potential function (distance function from the starting point and end point) are established, and then the idea of ​​binary search and sparse constraint method are used to find sparse points, thereby planning a shortest safe path at any angle in the raster map. Then, in view of the motion characteristics of unmanned boats and the need to comply with international maritime rules and conventions during the path planning process of unmanned boats, maritime rules and kinematic constraints are considered while avoiding collisions of unmanned boats, so that unmanned boats can plan a path in real time. The optimal path quantifies the safety distance. The invention can be applied to the field of path planning of unmanned boats, and can safely avoid collisions in real time, quickly and dynamically.

Description

Technical field [0001] The invention relates to the field of path planning for unmanned boats, specifically a dynamic collision avoidance method for unmanned boats. Background technique [0002] With the rapid development of unmanned systems and artificial intelligence technology, following drones and unmanned vehicles, unmanned surface vehicles (USVs) are becoming more and more popular in military and civilian fields. They are used in maritime search and rescue, maritime affairs, etc. It plays an important role in various marine applications such as forensics, environmental monitoring and enemy reconnaissance. [0003] Path planning technology is one of the core technologies in the field of unmanned surface watercraft. It is a key step from manned to unmanned and is the key development direction of intelligent unmanned watercraft. To a certain extent, it marks the autonomous navigation capability of unmanned surface watercraft. of high or low. Therefore, studying the path...

AI Technical Summary

Problems solved by technology

[0004] Most of the current path planning methods, such as the grid method, A* algorithm, dijkstra algorithm, etc., due to the defects caused by the discretization of the grid method, the above graph search algorithm cannot plan a path at any angle, which limits the path direction. The change can only be a multiple of π / 4, which will cause unnecessary movement and steering of the unmanned boat

[0005] However, the traditional artificial potential field method has the problem of local minima, which easily leads to path oscillation, the path cannot be identified in the group of similar obstacles, and the target is unreachable near the obstacle.

Images