A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Moving Platform

Rodríguez Ramos, Alejandro and Sampedro Pérez, Carlos and Bavle, Hriday and Puente Yusty, Paloma de la and Campoy Cervera, Pascual (2019). A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Moving Platform. "Journal of Intelligent & Robotic Systems", v. 93 (n. 1-2); pp. 351-366. ISSN 1573-0409. https://doi.org/10.1007/s10846-018-0891-8.

Description

Title: A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Moving Platform
Author/s:
  • Rodríguez Ramos, Alejandro
  • Sampedro Pérez, Carlos
  • Bavle, Hriday
  • Puente Yusty, Paloma de la
  • Campoy Cervera, Pascual
Item Type: Article
Título de Revista/Publicación: Journal of Intelligent & Robotic Systems
Date: 2019
ISSN: 1573-0409
Volume: 93
Subjects:
Freetext Keywords: Deep reinforcement learning; UAV; Autonomous landing; Continuous control
Faculty: E.T.S.I. Industriales (UPM)
Department: Automática, Ingeniería Eléctrica y Electrónica e Informática Industrial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

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 designed 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, which has been integrated in 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.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainDPI2014-60139-RUnspecifiedUnspecifiedAutonomía visual para vehículos aéreos no tripulados en entornos dinámicos

More information

Item ID: 67140
DC Identifier: https://oa.upm.es/67140/
OAI Identifier: oai:oa.upm.es:67140
DOI: 10.1007/s10846-018-0891-8
Official URL: https://link.springer.com/article/10.1007/s10846-018-0891-8
Deposited by: Memoria Investigacion
Deposited on: 19 May 2021 15:39
Last Modified: 19 May 2021 15:39
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM