Identifying and Analyzing Safety Critical Maneuvers from High Resolution AIS Data

Abstract

The authors demonstrate the value in previously disregarded parameters in Automatic Identification System (AIS) data, and present a novel way of quickly identifying and characterizing potentially safety critical situations for vessels with a properly configured AIS transponder. The traditional approach of studying (near) collision situations, is through vessel conflict zones, based on vessel location and speed from low resolution AIS data. Their approach utilizes the rate of turn parameter in the AIS signal, at maximum time resolution. From collision investigation reports it is often seen that prior to or at collision navigators perform frenetic rudder actions in the hope to avoid collision in the last second. These hard maneuverings are easily spotted as non-normal rate of turn signals. An identified potential critical situation may then be further characterized by the occurring centripetal acceleration a vessel is exposed to. The authors demonstrate the novelty of their methodology in a case study of a real ship collision. As the rate of turn parameter is directly linkable to the navigator behavior it provides information about when and to what degree actions were taken. They believe their work will therefore inspire new research on safety and human factors as a risk profiles could be derived based on AIS data.