Research On Path Planning Algorithms Of Unmanned Surface Vehicle Based On COLREGs

Unmanned Surface Vehicle(USV)has the advantages of modularized,autonomous and intelligence,etc.,besides,when assembled with different sensors and modules,it can execute a large amount of complex assignments,therefore,USV has been widely applied in the field of ocean exploitation and military applications.USV must be capable of a relatively high degree of autonomous navigation in highly dynamic and unexpected marine environment,so efficient?reliable and real-time obstacle avoidance path planning is very important.This thesis mainly researches on global path planning which is on static environmental information and real-time dynamic avoidance of unmarked obstacles during navigation.The concrete work is as follows: firstly,the paper briefly introduces the research status of path planning technology at home and abroad and the related concepts of path planning.Then the characteristics and general steps of USV path planning are discussed.After that,it focuses on the USV global path planning method and the real-time dynamic obstacle avoidance based on Convention on the International Regulations for Preventing Collision at Sea(COLREGs).Firstly,to solve the defect of Cuckoo Search algorithm,such as lack of adaptability and slow pre-convergence speed,the algorithm is improved to an adaptive cuckoo search algorithm.Using the grid method to model the marine environment,taking the path length as the evaluation function of the path,using the adaptive cuckoo search algorithm to search for the optimal path and output the optimal path.Secondly,the real-time dynamic obstacle avoidance strategy of USV is studied.According to the rules of COLREGS,the possible meeting situations are analyzed.Velocity Obstacle algorithm has good real-time and Optical Reciprocal Collision Avoidance(ORCA)algorithm can solve the problems when both sides have the ability to avoid obstacles autonomously.According to the type of obstacle,dynamic obstacle avoidance problem is divided into two kinds of situations.If the obstacle has autonomous obstacle avoidance ability,ORCA algorithm is used to avoid the threat;if not,the Velocity Obstacle algorithm is adopted.Finally,in the environment of Visual Studio 2008,a path planning platform was developed for simulation experiments.The software implements the USV global path planning based on the adaptive Cuckoo Search algorithm,and the simulation results show that the proposed method is efficient.The software simulates the unexpected situations that mayoccur in the course of USV navigation.The USV avoids obstacles in a safe manner and complies with COLREGS rules,and the simulation results exhibit the reliability and safety of the presented method.