A novel approach to automate surrounding ships in a virtual maritime environment

Abstract

Full mission marine training scenarios are essential in training marine trainees with ship handling simulators. In a good training simulation not only the static environment but also the dynamic surrounding ships plays a major role in terms of behaviour realism. The surrounding ships also need to navigate according to COLREG (Convention on International Regulation for Preventing Collisions at Sea) navigational rules. This research presents a novel approach to automate the surrounding vessels in a marine simulation environment with a central controller to control the behaviours of each surrounding vessel in the marine environment. The controller uses positioning data of real ships which are derived from a set of historical Automatic Identification System (AIS) data and map the positioning data with the surrounding ships in virtual environment to obtain the navigation. An Ant Colony Optimization (ACO) algorithm is used to avoid the collisions by generating a new path when both trainee's ship and surrounding ships are in the vicinity of each other. The collision handling mechanism uses COLREG rules. The ACO algorithm generates successful collision avoided paths in all head-on, crossing and over-taking encountering situations. The number of turning points is used to measure the smoothness of the path and number of obstacles in the environment and number of nodes in the graph affects the smoothness of the path. With these results it is revealed that AIS data can be used as an assistant to automate surrounding vessels in a virtual maritime environment together with a proper collision avoidance mechanism.