Task-Semantic Graph-Driven Distributed Agent Networking for Underwater Target Tracking - 2026-05-15 - Research Publication - This paper addresses these issues by developing an open-source MARL-AUV platform that integrates DI-engine with a six-degree-of-freedom underwater AUV target-tracking simulator. Multi-agent reinforcement learning (MARL) is… - source: arxiv.org
Pushing subsea boundaries with hybrid AUV/ROV - 2023-05-01 - Research Publication - The vehicle can operate in three modes: it can be piloted remotely via a tether, it can receive through-water communication (to provide real-time control), or it can work autonomously, relying on designed-in software and… - source: hydro-international.com