Show simple item record

dc.contributor.authorRubí Perelló, Bartomeu
dc.contributor.authorMorcego Seix, Bernardo
dc.contributor.authorPérez Magrané, Ramon
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Automàtica, Robòtica i Visió
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial
dc.date.accessioned2020-09-18T08:35:18Z
dc.date.available2020-09-18T08:35:18Z
dc.date.issued2020
dc.identifier.citationRubi, 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.
dc.identifier.isbn978-3-907144-02-2
dc.identifier.urihttp://hdl.handle.net/2117/328906
dc.description© 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.
dc.description.abstractThis 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.
dc.description.sponsorshipThis 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).
dc.format.extent7 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subject.lcshMachine learning
dc.subject.lcshDrone aircraft
dc.subject.otherTraining
dc.subject.otherMachine learning
dc.subject.otherHeuristic algorithms
dc.subject.otherLearning (artificial intelligence)
dc.subject.otherAttitude control
dc.subject.otherPrediction algorithms
dc.subject.otherUnmanned aerial vehicles
dc.titleA deep reinforcement learning approach for path following on a quadrotor
dc.typeConference report
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacAvions no tripulats
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://ieeexplore.ieee.org/document/9143591
dc.rights.accessOpen Access
local.identifier.drac29058776
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/AEI/1PE/DPI2017-88403-R
dc.relation.projectidinfo:eu-repo/grantAgreement/AGAUR/FI/2017FI B 00212
local.citation.authorRubi, B.; Morcego, B.; Perez, R.
local.citation.contributorEuropean Control Conference
local.citation.publicationNameProceedings of the 2020 European Control Conference (ECC): Saint Petersburg, Russia, May 12-15, 2020
local.citation.startingPage1092
local.citation.endingPage1098


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder