A simulation platform for multi-ship collision decision making

Abstract

Collision avoidance decision support system has been one of the hot topics in intelligent technologies. Moreover, trying to reduce the involvement of human operators is one of the most effective ways to reduce maritime accidents as well as enhance the intelligence of the ships. In this paper, a simulation platform is construct for the purpose of testing the performance of collision avoidance decision making under multi-ship encounter situations. The software of python is used in the development of the platform. The platform enables the maneuvering of ships manually, as well as guiding the ships using anti-collision decision making algorithms. In the simulation platform, the parameters of Distance to Closest Point of Approach (DCPA) and Time to CPA (TCPA) are used to reflect the collision risk. The collision risk is visualized in a real-time mode, so that the decisions can be made based on the evolution of collision risk. The platform can conduct simulation based on the information of the ships and the encounter situation. It can also evaluate and verify the feasibility of the collision avoidance decision-making scheme. The platform can be a useful testbed for evaluating the performance of collision avoidance decision making procedures in open waters.