This paper proposes an integrated software-hardware approach for automated bathymetry mapping using low-cost unmanned surface vehicles (USVs). The solution takes inspiration from adaptive sampling, aiming to minimize the time, hardware, and training costs compared to traditional coverage path planning (CPP) methods. The proposed approach implements a scalable Markov Decision Process (MDP)-based model and a planning method based on multi-agent approximate dynamic programming (ADP), which prescribes USVs to seek the most informative samples in bandwidth-limited environments with uncertain and incomplete prior map information. The control structure offloads surrogate model updates and path planning to the control station and ensures mission completion even with communication dropouts. Computer simulation results on both real-world and computer-generated bathymetry data demonstrate the effectiveness of the proposed approach in terms of predictive accuracy and efficiency. The proposed solution has the potential to significantly aid coastal development by streamlining access to accurate models of near-shore bathymetry.

This work formalizes the Route Planning Problem (RPP), wherein a set of distributed assets (e.g., ships, submarines, unmanned systems) simultaneously plan routes to optimize a team goal (e.g., find the location of an unknown threat or object in minimum time and/or fuel consumption) while ensuring that the planned routes satisfy certain constraints (e.g., avoiding collisions and obstacles). This problem becomes overwhelmingly complex for multiple distributed assets as the search space grows exponentially to design such plans. The RPP is formalized as a Team Discrete Markov Decision Process (TDMDP) and we propose a Multi-agent Multi-objective Reinforcement Learning (MaMoRL) framework for solving it. We investigate challenges in deploying the solution in real-world settings and study approximation opportunities. We experimentally demonstrate MaMoRL's effectiveness on multiple real-world and synthetic grids, as well as for transfer learning. MaMoRL is deployed for use by the Naval Research Laboratory - Marine Meteorology Division (NRL-MMD), Monterey, CA.