A collision avoidance decision-making system for autonomous ship based on modified velocity obstacle method

Abstract

This paper proposed a new collision avoidance decision-making system designed for autonomous ship. The system outputs collision avoidance decisions based on the latest information at a certain frequency, which is suitable for real ship application. Front end and back end are two main components of this system. Front end provides preliminary information while back end generates collision avoidance decisions. Based on modified velocity obstacle method, the multistage optimization decision model is introduced and various constrains are considered including ship maneuverability, multi-ship, COLREGS, off-course and seamanship. Then the interactive actions taken by other ships during collision avoidance process are further analyzed. The modified velocity obstacle method incorporates a Finite State Machine (FSM) which can be used to handle the dynamic behavior of other ships. Finally, the case study is completed on the Electronic Chart System (ECS) to show that the proposed collision avoidance decision-making system is robust and effective under various marine scenarios. Therefore, the system has great potential to be equipped on board in the future.