| Abstract | This paper presents a multiagent-based simulation system as aparadigm for the decision-making research of ship collision avoidance. Thesimulation system has the characteristics of flexible agent, variable topology,isomorphic function structure, distributed knowledge storage, and integratedcontrol method. The architecture is proposed with four kinds of agent models,which are Control_Agent, Union_Agent, Ship_Agent and VTS_Agent. Wedeveloped these agent models for modeling the behaviors for human, ship andVTS using a BDI (Beliefs, Desires, and Intentions) agent framework. The agentcommunication mechanism based on AIS (Automatic Identification System)message is also established and discussed in this paper. The proposedmultiagent-based simulation system provides a useful platform for studyingmulti-target encountering problems and different decision-making methods forcollision avoidance. |
|---|
