Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Deep Reinforcement Learning Through Environmental Generalization

TL;DR

This paper introduces a deep reinforcement learning method for mapless navigation and medium transition in hybrid aerial underwater vehicles, emphasizing improved performance and environmental generalization using recurrent neural networks.

Contribution

It proposes a novel double critic Deep-RL approach with RNNs that enhances navigation and transition capabilities of HUAUVs using only range and relative localization data.

Findings

Improved navigation performance with Deep-RL using range data.

Enhanced medium transition capabilities in simulated scenarios.

Better generalization across different environments.

Abstract

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.