Despite the increasing adoption of Deep Reinforcement Learning (DRL) for Autonomous Surface Vehicles (ASVs), there still remain challenges limiting real-world deployment. In this paper, we first integrate buoyancy and hydrodynamics models into a modern Reinforcement Learning framework to reduce training time. Next, we show how system identification coupled with domain randomization improves the RL agent performance and narrows the sim-to-real gap. Real-world experiments for the task of capturing floating waste show that our approach lowers energy consumption by 13.1\% while reducing task completion time by 7.4\%. These findings, supported by sharing our open-source implementation, hold the potential to impact the efficiency and versatility of ASVs, contributing to environmental conservation efforts.
@article{arxiv.2407.08263,
title = {A Deep Reinforcement Learning Framework and Methodology for Reducing the Sim-to-Real Gap in ASV Navigation},
author = {Luis F W Batista and Junghwan Ro and Antoine Richard and Pete Schroepfer and Seth Hutchinson and Cedric Pradalier},
journal= {arXiv preprint arXiv:2407.08263},
year = {2024}
}
Comments
IROS 2024, IEEE, Oct 2024, Abu Dhabi, United Arab Emirates