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

  • Ricardo B. Grando Technological University of Uruguay
  • Junior C. de Jesus FURG
  • Victor A. Kich UFSM
  • Alisson H. Kolling UFSM
  • Pedro M. Pinheiro FURG
  • Rodrigo S. Guerra FURG
  • Paulo L. J. Drews FURG

Resumo


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.
Palavras-chave: Location awareness, Recurrent neural networks, Navigation, Education, Reinforcement learning, Robot sensing systems, Solids
Publicado
18/10/2022
GRANDO, Ricardo B.; JESUS, Junior C. de; KICH, Victor A.; KOLLING, Alisson H.; PINHEIRO, Pedro M.; GUERRA, Rodrigo S.; DREWS, Paulo L. J.. Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Deep Reinforcement Learning Through Environmental Generalization. In: SIMPÓSIO BRASILEIRO DE ROBÓTICA E SIMPÓSIO LATINO AMERICANO DE ROBÓTICA (SBR/LARS), 19. , 2022, São Bernardo do Campo/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 199-204.