Unmanned ship self-adaptive step length path searching method based on terrain complexity

Abstract

The invention discloses an unmanned ship self-adaptive step length path searching method based on terrain complexity. The method comprises the following steps: acquiring an environment static image and carrying out binarization preprocessing; carrying out image expansion and rasterization to establish a map environment model; carrying out terrain complexity calculation and screening reduction on each grid; searching an optimal passing path in the map environment model by using an A* algorithm; and further optimizing the obtained optimal passing path to obtain a final optimized path. According to the method, the terrain complexity is calculated according to the map environment model, the map can be autonomously segmented for analysis and processing, calculation of a complete obstacle area is omitted, the calculation amount and the required running memory are reduced, the path is optimized, many unnecessary inflection points are reduced, the overall path length is shortened, and the path quality is improved.

Description

technical field [0001] The invention relates to an artificial intelligence-based path planning method for an unmanned ship, in particular to autonomous path planning and path optimization for an unmanned ship, specifically an adaptive step-length path search method for an unmanned ship based on terrain complexity. Background technique [0002] With the continuous development of technology in the field of marine monitoring in my country, the demand for automatic pathfinding algorithms for unmanned ships is becoming more and more extensive. Through unmanned ships with automatic navigation and pathfinding functions, people can achieve more frequent and more comprehensive maritime monitoring, and better complete surveys, sampling, rescue, etc. [0003] For example, the invention patent with application number CN 111930121 A proposes a mixed path planning method for indoor mobile robots, using the grid method to model the space where the robot is located, and using the bat algori...

AI Technical Summary

Problems solved by technology

[0005] In summary, the path planning in the prior art has at least the following defects: in some cases, the step size of the path search is too large, causing some possible paths to be ignored; in some cases, the step size of the path search is too small, resulting in There are too many grids on the map, which will cause unnecessary increase in the calculation amount of the algorithm and the required running memory, thereby increasing the time required for the algorithm and the memory consumption; the obtained path is not optimized, and the quality of the path is not good. Sharp inflection points, unnecessary detours, and a large gap with the optimal traffic path

Images