Extended Kalman Filter Design and Motion Prediction of Ships using Live Automatic Identification System (AIS) Data

Abstract

This paper addresses the problem of ship motion estimation using live data from Automatic Identification Systems (AIS) and extended Kalman filter (EKF) design. AIS data are transmitted from ships globally and a very-high frequency (VHF) AIS receiver picks up the signals as coded ASCII characters in a format specified by the National Marine Electronics Association (NMEA). Hence, the AIS sentences must be decoded using a parser to obtain real-time ship position, course and speed measurements. The state estimates are intended for collision detection and real-time visualization, which are important features of modern decision-support systems. The EKF is validated using live AIS data from the Trondheim harbor in Norway and it is demonstrated that the estimator can track ships in real time. It is also demonstrated that the EKF can predict the future motion of ships and different evasive maneuvers were analyzed in a collision avoidance scenario. Index Terms—Kalman filter, state estimation, motion prediction, collision detection, unmanned surface vehicles, ships