Adaptive Collaborative Channel Finding Approaches for Autonomous Marine Vehicles

Abstract

This thesis presents an investigation into the problem of rapid identification of a channel that crosses a body of water, using one or more Autonomous Marine Vehicles (AMVs). A new algorithm called Proposal Based Adaptive Channel Search (PBACS) is presented as a potential solution that improves upon current methods. The empirical performance of PBACS is compared to lawnmower surveying and to Markov decision process (MDP) planning with two state-of-the-art reward functions: Upper Confidence Bound (UCB) and Maximum Value Information (MVI). The performance of each method is evaluated through comparison of the time it takes to identify a continuous channel through an area, using one, two, three, or four Autonomous Surface Vehicles (ASVs). The performance of each method is compared across ten simulated bathymetry scenarios and one field area, each with different channel layouts.

The results from simulations and field trials presented in this thesis indicate that on average multi-vehicle PBACS outperforms lawnmower, UCB, and MVI based methods, with two main exceptions. One case is when lawnmower start locations are aligned with a straight channel, which can happen for any number of vehicles. The lawnmower outperforms other approaches in this case. However, this alignment on an unknown bathymetry would happen purely by chance, while PBACS identifies the channel regardless of any alignment. The second case is when the shape of the channel is curved, and no straight path exists. In this case, PBACS outperforms other approaches only when more than two vehicles are used.