Visualization and Collision Risk Assessment of Real Ships in a Mixed-Reality Environment using Live Automatic Identification System (AIS) Data

Abstract

This paper presents a concept for automated situational awareness using 3-D visualization. The Unity game engine is used for live visualization of real ships operating in a mixed-reality environment. A piloted unmanned surface vehicle (USV) is simulated when operating close to the real ships. The ship positions are obtained by decoding data from the Automatic Identification System (AIS), which are transmitted as VHF signals. After decoding, an extended Kalman filter (EKF) is designed to run at a fixed time step, typically 30-60 Hz, for smooth visualization at 30-60 frames per second (FPS). Since the AIS data are transmitted at asynchronous time samples, the EKF is implemented in discrete time using the predictor-corrector representation (Gelb, 1974) to get evenly-spaced data and to handle loss of data packets. An algorithm for computation of the minimum separation, that is the minimum distance between the USV and the ships, is coded in Unity's native C# scripting language. Finally, the concept of situational awareness and online computation of a ship collision risk index are demonstrated using live AIS data from the Trondheim harbor in Norway.