elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Learning-Based Path Following Control for an Over-Actuated Robotic Vehicle

Ultsch, Johannes and Brembeck, Jonathan and de Castro, Ricardo (2019) Learning-Based Path Following Control for an Over-Actuated Robotic Vehicle. VDI Verlag GmbH. AUTOREG 2019, 02.-03. Juli 2019, Mannheim, Deutschland. ISBN 978-3-18-092349-9 ISSN 0083-5560

[img] PDF - Registered users only
1MB

Abstract

Motion control, in particular path following control (PFC), is an important function of autonomous vehicles. PFC controls the propulsion, steering and braking such that the vehicle follows a parametric path and reference velocity. For the design of traditional model-based PFC approaches a sufficiently accurate synthesis model of the vehicle has to be available in order to design a performant controller. However, constructing, parametrizing and testing these model-based PFC as well as deriving the synthesis model is known to be a time-consuming task. Recently the application of reinforcement learning (RL) methods to solve control problems without a synthesis model but based on high fidelity simulation models has gained increasing interest. In this paper we investigate the application of RL methods to solve the path following problem for DLR’s ROboMObil, an over-actuated robotic vehicle. Simulation results demonstrate that the RL-based PFC exhibits similar tracking performance as a model-based controller, executed on the path used for training. Moreover the RL-based PFC provides encouraging generalization capabilities, when facing unseen reference paths.

Item URL in elib:https://elib.dlr.de/127819/
Document Type:Conference or Workshop Item (Speech)
Title:Learning-Based Path Following Control for an Over-Actuated Robotic Vehicle
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Ultsch, JohannesJohannes.Ultsch (at) dlr.deUNSPECIFIED
Brembeck, Jonathanjonathan.brembeck (at) dlr.deUNSPECIFIED
de Castro, RicardoRicardo.DeCastro (at) dlr.deUNSPECIFIED
Date:2019
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Volume:2349
Page Range:pp. 25-46
Editors:
EditorsEmail
UNSPECIFIEDVDI Wissensforum GmbH
Publisher:VDI Verlag GmbH
Series Name:VDI-Berichte
ISSN:0083-5560
ISBN:978-3-18-092349-9
Status:Published
Keywords:Reinforcement Learning, Pfadfolgeregelung
Event Title:AUTOREG 2019
Event Location:Mannheim, Deutschland
Event Type:national Conference
Event Dates:02.-03. Juli 2019
Organizer:VDI Wissensforum
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Technik für Raumfahrtsysteme
DLR - Research theme (Project):R - Vorhaben Intelligente Mobilität
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of System Dynamics and Control > Vehicle System Dynamics
Deposited By: Ultsch, Johannes
Deposited On:12 Jul 2019 14:21
Last Modified:17 Dec 2019 15:05

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.