Intention modeling and inference for autonomous collision avoidance at sea. (15th December 2022)

• Record Type: Journal Article
• Authors: Rothmund, Sverre Velten; Tengesdal, Trym; Brekke, Edmund Førland; Johansen, Tor Arne
• Is Part Of: Ocean engineering. Volume 266(2022)Part 4
• Publication Date: 2022-12-15
• Subjects: Autonomous ship -- COLREGs -- Dynamic Bayesian Network (DBN) -- Intention inference -- Collision avoidance -- Situational awareness; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2022.113080
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: The open wording of the traffic rules of the sea, COLREGS, and the existence of unwritten rules, make it essential for an autonomous ship to understand the intentions of other ships. This article uses a dynamic Bayesian network (DBN) to model and infer the intentions of other ships in open waters based on their observed real-time behavior. Multiple intention nodes are included to describe the different ways a ship can interpret and conflict with the behavioral rules outlined in COLREGS. The prior probability distributions of the intention nodes are adapted to the current situation based on observable characteristics such as location and relative ship size. The resulting model is able to identify situations that are prone to cause misunderstandings and infer the state of multiple intention variables that describe how the ship is likely to behave. Different collision avoidance algorithms can use the resulting intention information to better know if, when, and how to act. Highlights: Intention modeling and inference of ships for use in collision avoidance systems. Intentions of ships are modeled and inferred using a dynamic Bayesian network. Multiple different intention states are considered. Underlying cases are inferred by combining information over time. Prior information is used to adapt the model to the current situation.