Observatorio de I+D+i UPM

Memorias de investigación
Artículos en revistas:
A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Moving Platform?
Año:2018
Áreas de investigación
  • Automática
Datos
Descripción
The use of multi-rotor UAVs in industrial and civil applications has been extensively encouraged by the rapid innovation in all the technologies involved. In particular, deep learning techniques for motion control have recently taken a major qualitative step, since the successful application of Deep Q-Learning to the continuous action domain in Atari-like games. Based on these ideas, Deep Deterministic Policy Gradients (DDPG) algorithm was able to provide outstanding results with continuous state and action domains, which are a requirement in most of the robotics-related tasks. In this context, the research community is lacking the integration of realistic simulation systems with the reinforcement learning paradigm, enabling the application of deep reinforcement learning algorithms to the robotics field. In this paper, a versatile Gazebo-based reinforcement learning framework has been established and validated with a continuous UAV landing task. The UAV landing maneuver on a moving platform has been solved by means of the novel DDPG algorithm and our reinforcement learning framework. Several experiments have been performed in a wide variety of conditions for both simulated and real flights, demonstrating the generality of the approach. As an indirect result, a powerful work flow for robotics has been validated, where robots can learn in simulation and perform properly in real operation environments. To the best of the authors knowledge, this is the first work that addresses the continuous UAV landing maneuver on a moving platform by means of a state-of-the-art deep reinforcement learning algorithm, trained in simulation and tested in real flights.
Internacional
Si
JCR del ISI
Si
Título de la revista
Journal of Intelligent & Robotic Systems
ISSN
0921-0296
Factor de impacto JCR
1.583
Información de impacto
Volumen
DOI
Número de revista
Desde la página
351
Hasta la página
366
Mes
SIN MES
Ranking
Esta actividad pertenece a memorias de investigación
Participantes
  • Autor: Alejandro Rodriguez Ramos (UPM)
  • Autor: Carlos Sampedro Perez (UPM)
  • Autor: Hriday Bavle Milind (UPM)
  • Autor: Pascual Campoy Cervera (UPM)
  • Autor: Paloma de la Puente Yusty (UPM)
Grupos de investigación, Departamentos, Centros e Institutos de I+D+i relacionados
  • Creador: Grupo de Investigación: Visión por Computador y Robótica Aérea
  • Departamento: Automática, Ingeniería Eléctrica y Electrónica e Informática Industrial
S2i 2021 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)