Trajectory Optimization for Unknown Maneuvering Target Tracking with Bearing-only Measurements

TL;DR

This paper introduces a Gaussian process-based framework for autonomous underwater vehicles to optimize their trajectories for tracking maneuvering targets using only bearing measurements, incorporating online learning and planning.

Contribution

It presents a novel GP-based bearing-only tracking framework with error bounds and analytical optimal bearing computation for improved underwater target tracking.

Findings

The proposed method outperforms existing approaches in tracking accuracy.

The framework effectively handles unknown target motion.

Numerical results demonstrate superior tracking performance.

Abstract

This paper studies trajectory optimization of an autonomous underwater vehicle (AUV) to track an unknown maneuvering target both in the 2D and 3D space. Due to the restrictions on sensing capabilities in the underwater scenario, the AUV is limited to collecting only bearing measurements to the target. A framework called {\it GP-based Bearing-only Tracking (GBT)} is proposed with integration of online learning and planning. First, a Gaussian process learning method is proposed for the AUV to handle unknown target motion, wherein pseudo linear transformation of bearing measurements is introduced to address nonlinearity of bearings. A probabilistic bearing-data-dependent bound on tracking error is then rigorously established. Based on it, optimal desired bearings that can reduce tracking uncertainty are obtained analytically. Finally, the trajectory optimization problem is formulated and transformed into an easily solved one with parametric transformation. Numerical examples and comparison with existing methods verify the feasibility and superior performance of our proposed framework.