Fullest COLREGs Evaluation Using Fuzzy Logic for Collaborative Decision-Making Analysis of Autonomous Ships in Complex Situations

Abstract

Maritime Autonomous Surface Ships (MASSs) will reshape the fast-evolving ecosystem for their attractive socio-economic benefits and potential to improve safety. However, their new systems and technology need thorough verifications to identify unintended components of risk. The interaction between MASS cyber-physical systems and the existing regulatory framework is currently unpredictable; AI-powered intelligent situation awareness and autonomous navigation algorithms must safely and efficiently adhere to the regulations which are only designed for human interpretation without MASSs consideration. This paper contributes to algorithmic regulations and particularly algorithmic COLREGs in real-world MASS applications. It focuses on codifying COLREGs into a machine-executable system applicable to MASSs. This fullest COLREGs evaluation is modelled in form of a fuzzy expert system based on ordinary seamanship practice. The full input space spans 21 features derived from maneuverability-dependent risk, AIS traffic data, vessel information, maps and nautical charts, water-depth, visibility, and sea conditions. The model assesses pairwise vessel encounters over the full time-window of a situation from entrance to exit. 42 fuzzy rules are designed in 6 criteria that represent COLREGs Rules 2–19 and model their logical connections, priorities, and relationships. This algorithmic COLREGs form satisfies the crucial needs in simulation, collision-avoidance, complexity monitoring, and compliance quantification in MASS applications. The fullest COLREGs evaluation model is verified on a large database of historical encounters using real data from multiple sources.