• A deep reinforcement learning...

Treffer: A deep reinforcement learning approach for path following on a quadrotor

Title:
A deep reinforcement learning approach for path following on a quadrotor
Authors:
Universitat Politècnica de Catalunya. Doctorat en Automàtica, Robòtica i Visió, Universitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial, Rubí Perelló, Bartomeu, Morcego Seix, Bernardo, Pérez Magrané, Ramon
Publisher Information:
2020
Document Type:
E-Ressource Electronic Resource
Index Terms:
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic, Machine learning, Drone aircraft, Training, Heuristic algorithms, Learning (artificial intelligence), Attitude control, Prediction algorithms, Unmanned aerial vehicles, Aprenentatge automàtic, Avions no tripulats, Conference report
URL:
http://hdl.handle.net/2117/328906
https://ieeexplore.ieee.org/document/9143591
Availability:
Open access content. Open access content
Open Access
Note:
7 p.
application/pdf
English
Other Numbers:
HGF oai:upcommons.upc.edu:2117/328906
Rubi, B.; Morcego, B.; Perez, R. A deep reinforcement learning approach for path following on a quadrotor. A: European Control Conference. "Proceedings of the 2020 European Control Conference (ECC): Saint Petersburg, Russia, May 12-15, 2020". 2020, p. 1092-1098. ISBN 978-3-907144-02-2.
978-3-907144-02-2
1224048026
Contributing Source:
UNIV POLITECNICA DE CATALUNYA
From OAIster®, provided by the OCLC Cooperative.
Accession Number:
edsoai.on1224048026
Database:
OAIster

Weitere Informationen

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
This paper proposes the Deep Deterministic Policy Grandient (DDPG) reinforcement learning algorithm to solve the path following problem in a quadrotor vehicle. This agent is implemented using a separated control and guidance structure with an autopilot tracking the attitude and velocity commands. The DDPG agent is implemented in python and it is trained and tested in the RotorS-Gazebo environment, a realistic multirotor simulator integrated in ROS. Performance is compared with Adaptive NLGL, a geometric algorithm that implements an equivalent control structure. Results show how the DDPG agent is able to outperform the Adaptive NLGL approach while reducing its complexity.
This work has been partially funded by the Spanish State Research Agency (AEI) and the European Regional Development Fund (ERDF) through the SCAV project (ref. MINECO DPI2017-88403-R), and by SMART project (ref. EFA 153/16 Interreg Cooperation Program POCTEFA 2014- 2020). Bartomeu Rubí is also supported by the Secretaria d’Universitats i Recerca de la Generalitat de Catalunya, the European Social Fund (ESF) and AGAUR under a FI grant (ref. 2017FI B 00212).
Peer Reviewed
Postprint (author's final draft)