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

Unsupervised symbol emergence for supervised autonomy using multi-modal latent Dirichlet allocations

Lay, Florian Samuel and Bauer, Adrian Simon and Albu-Schäffer, Alin and Stulp, Freek and Leidner, Daniel (2021) Unsupervised symbol emergence for supervised autonomy using multi-modal latent Dirichlet allocations. Advanced Robotics. Taylor & Francis. doi: 10.1080/01691864.2021.2007169. ISSN 0169-1864.

[img] PDF - Only accessible within DLR - Published version
11MB

Official URL: https://www.tandfonline.com/doi/full/10.1080/01691864.2021.2007169

Abstract

In future Mars exploration scenarios, astronauts orbiting the planet will control robots on the surface with supervised autonomy to construct infrastructure necessary for human habitation. Symbol-based planning enables intuitive supervised teleoperation by presenting relevant action possibilities to the astronaut. While our initial analog experiments aboard the International Space Station (ISS) proved this scenario to be very effective, the complexity of the problem puts high demands on domain models. However, the symbols used in symbolic planning are error-prone as they are often hand-crafted and lack a mapping to actual sensor information. While this may lead to biased action definitions, the lack of feedback is even more critical. To overcome these issues, this paper explores the possibility of learning the mapping between multi-modal sensor information and high-level preconditions and effects of robot actions. To achieve this, we propose to utilize a Multi-modal Latent Dirichlet Allocation (MLDA) for unsupervised symbol emergence. The learned representation is used to identify domain-specific design flaws and assis in supervised autonomy robot operation by predicting action feasibility and assessing the execution outcome. The approach is evaluated in a realistic telerobotics experiment conducted with the humanoid robot Rollin' Justin.,

Item URL in elib:https://elib.dlr.de/146960/
Document Type:Article
Title:Unsupervised symbol emergence for supervised autonomy using multi-modal latent Dirichlet allocations
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Lay, Florian SamuelUNSPECIFIEDhttps://orcid.org/0000-0002-5706-3278
Bauer, Adrian SimonUNSPECIFIEDhttps://orcid.org/0000-0002-1171-4709
Albu-Schäffer, AlinUNSPECIFIEDhttps://orcid.org/0000-0001-5343-9074
Stulp, FreekUNSPECIFIEDhttps://orcid.org/0000-0001-9555-9517
Leidner, DanielUNSPECIFIEDhttps://orcid.org/0000-0001-5091-7122
Date:3 December 2021
Journal or Publication Title:Advanced Robotics
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI:10.1080/01691864.2021.2007169
Publisher:Taylor & Francis
ISSN:0169-1864
Status:Published
Keywords:MLDA, Symbol Emergence, Supervised Autonomy, Space Robotics
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - On-Orbit Servicing [RO], R - Intelligent Mobility (RM) [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Deposited By: Lay, Florian Samuel
Deposited On:11 Jan 2022 15:40
Last Modified:11 Jan 2022 15:40

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.