Previous works showed that Deep-RL can be applied to perform mapless navigation, including the medium transition of Hybrid Unmanned Aerial Underwater Vehicles (HUAUVs). This paper presents new approaches based on the state-of-the-art actor-critic algorithms to address the navigation and medium transition problems for a HUAUV. We show that a double critic Deep-RL with Recurrent Neural Networks improves the navigation performance of HUAUVs using solely range data and relative localization. Our Deep-RL approaches achieved better navigation and transitioning capabilities with a solid generalization of learning through distinct simulated scenarios, outperforming previous approaches.
@article{arxiv.2209.06332,
title = {Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Deep Reinforcement Learning Through Environmental Generalization},
author = {Ricardo B. Grando and Junior C. de Jesus and Victor A. Kich and Alisson H. Kolling and Rodrigo S. Guerra and Paulo L. J. Drews-Jr},
journal= {arXiv preprint arXiv:2209.06332},
year = {2022}
}
Comments
Paper accepted to the Latin American Robotics Symposium 2022