Vessel Trajectory Prediction using COLREGs-aware Optimal Planning
Robotics
Summary
The authors developed a way to predict where boats will go by first making a rough path that avoids obstacles using a method called A*-search. Then, they refine this path using an optimizer to make sure the boat follows maritime navigation rules (COLREG). Their approach only needs the current position, speed, and destination of nearby boats, which are available from AIS messages, making predictions quicker than some AI methods. The method was tested on real boat movement data and worked well.
Authors
David Kaikkonen, Fredrik Ljungberg, Erik Frisk
Abstract
This paper presents a trajectory prediction method for marine vessels based on optimal planning. Crude initial trajectories respecting static obstacles are first generated using A*-search to provide a feasible warm start. In the second step, a numerical optimizer is used to ensure COLREG compliance. The prediction problem is posed as sequential trajectory planning from the perspective of each surrounding vessel, requiring only their current positions, velocities, and intended destinations as input. As the latter is included in AIS messages, this enables faster predictions than learning-based methods that typically require longer data histories. The proposed method is validated using real-world scenarios constructed from AIS data.