English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Since the application of Deep Q-Learning to the continuous action domain inAtari-like games, Deep Reinforcement Learning (Deep-RL) techniques for motioncontrol have been qualitatively enhanced. Nowadays, modern Deep-RL can besuccessfully applied to solve a wide range of complex decision-making tasks formany types of vehicles. Based on this context, in this paper, we propose theuse of Deep-RL to perform autonomous mapless navigation for Hybrid UnmannedAerial Underwater Vehicles (HUAUVs), robots that can operate in both, air orwater media. We developed two approaches, one deterministic and the otherstochastic. Our system uses the relative localization of the vehicle and simplesparse range data to train the network. We compared our approaches with atraditional geometric tracking controller for mapless navigation. Based onexperimental results, we can conclude that Deep-RL-based approaches can besuccessfully used to perform mapless navigation and obstacle avoidance forHUAUVs. Our vehicle accomplished the navigation in two scenarios, being capableto achieve the desired target through both environments, and even outperformingthe geometric-based tracking controller on the obstacle-avoidance capability.

Deep Reinforcement Learning for Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Medium Transition