Online Approximate Optimal Station Keeping of a Marine Craft in the Presence of a Current

TL;DR

This paper presents an adaptive dynamic programming approach for online optimal station keeping of a marine craft in ocean currents, using reinforcement learning and system identification to handle unknown hydrodynamics.

Contribution

It introduces a novel adaptive control strategy combining system identification and reinforcement learning for marine craft station keeping in currents, without needing persistent excitation.

Findings

Successfully maintains station in experiments with an underwater vehicle.

Guarantees bounded convergence to desired station without persistent excitation.

Validates approach in real-world spring environment.

Abstract

Online approximation of the optimal station keeping strategy for a fully actuated six degrees-of-freedom marine craft subject to an irrotational ocean current is considered. An approximate solution to the optimal control problem is obtained using an adaptive dynamic programming technique. The hydrodynamic drift dynamics of the dynamic model are assumed to be unknown; therefore, a concurrent learning-based system identifier is developed to identify the unknown model parameters. The identified model is used to implement an adaptive model-based reinforcement learning technique to estimate the unknown value function. The developed policy guarantees uniformly ultimately bounded convergence of the vehicle to the desired station and uniformly ultimately bounded convergence of the approximated policies to the optimal polices without the requirement of persistence of excitation. The developed strategy is validated using an autonomous underwater vehicle, where the three degrees-of-freedom in the horizontal plane are regulated. The experiments are conducted in a second-magnitude spring located in central Florida.