Artificial forces for virtual autonomous ships with encountering situations in restricted waters

Even if the same two ships operate in the same encountering situation, the actual strategies and timing of operations may be different. Therefore, the fixed collision avoidance trajectory and ship movements are no longer suitable for simulating the real ship behaviour. This paper tries to develop an artificial intelligent system that fully sensitive to the local circumstances and command a ship in virtual environment. Based on AIS (Automatic Identification System) data, this study has developed artificial forces which help decision makings on-board independently under different situations and catching the stochastic nature of ship behaviours during collision avoidances manoeuvring. Actual ship tracks are helpful for ascertaining the parameters that contribute to artificial forces in collision avoidances, while the correlation coefficient analysis is helpful to distinguish the parameters. This study will help to develop a navigation traffic simulation to reflect the realistic ship behaviour and provide reliable information for port and waterway planning, risk analysis, and mitigation measures. The method can be used in developing algorithms for autonomous ships. The method introduced in this study lays a foundation for developing artificial forces at intersections or bends, although the model is only applicable in straight channels at the moment.