Adaptive and Collaborative Bathymetric Channel-Finding Approach for Multiple Autonomous Marine Vehicles

This paper reports an investigation into the problem of rapid identification a channel that crosses body water using one or more Unmanned Surface Vehicles (USV). A new algorithm called Proposal Based Adaptive Channel Search (PBACS) is presented as potential solution improves upon current methods. The empirical performance PBACS compared to lawnmower surveying and Markov decision process (MDP) planning with two state-of-the-art reward functions: Upper Confidence Bound (UCB) Maximum Value Information (MVI). each method evaluated through comparison time it takes identify continuous area, one, two, three, four USVs. across ten simulated bathymetry scenarios field different layouts. results from simulations trials indicate on average multi-vehicle outperforms lawnmower, UCB, MVI based methods, especially when at least three vehicles are used.