Intent Inference of Ship Collision Avoidance Behavior Under Maritime Traffic Rules

This paper proposes an algorithm to infer the maneuver intention of obstacle ship and check its compliance with maritime traffic rules avoid collision ensure safety. A probabilistic graphical model is constructed represent relationship between motion observations hidden comply rules. The belief ship's modeled quantified using tools such as dynamic Bayesian networks. Three different intent inference models are formulated considering levels observation configurations, their calculation procedures described. To demonstrate feasibility proposed algorithm, Monte-Carlo simulations were conducted results presented.