TU Darmstadt / ULB / TUbiblio

Learning Coupled Forward-Inverse Models with Combined Prediction Errors

Koert, Dorothea ; Maeda, Guilherme ; Neumann, Gerhard ; Peters, Jan (2022)
Learning Coupled Forward-Inverse Models with Combined Prediction Errors.
International Conference on Robotics and Automation (ICRA) 2018. Brisbane, QLD, Australia (21.-25.05.2018)
doi: 10.26083/tuprints-00020546
Konferenzveröffentlichung, Zweitveröffentlichung, Postprint

Kurzbeschreibung (Abstract)

Challenging tasks in unstructured environments require robots to learn complex models. Given a large amount of information, learning multiple simple models can offer an efficient alternative to a monolithic complex network. Training multiple models-that is, learning their parameters and their responsibilities-has been shown to be prohibitively hard as optimization is prone to local minima. To efficiently learn multiple models for different contexts, we thus develop a new algorithm based on expectation maximization (EM). In contrast to comparable concepts, this algorithm trains multiple modules of paired forward-inverse models by using the prediction errors of both forward and inverse models simultaneously. In particular, we show that our method yields a substantial improvement over only considering the errors of the forward models on tasks where the inverse space contains multiple solutions.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2022
Autor(en): Koert, Dorothea ; Maeda, Guilherme ; Neumann, Gerhard ; Peters, Jan
Art des Eintrags: Zweitveröffentlichung
Titel: Learning Coupled Forward-Inverse Models with Combined Prediction Errors
Sprache: Englisch
Publikationsjahr: 2022
Ort: Darmstadt
Verlag: IEEE
Buchtitel: 2018 IEEE International Conference on Robotics and Automation (ICRA)
Kollation: 7 Seiten
Veranstaltungstitel: International Conference on Robotics and Automation (ICRA) 2018
Veranstaltungsort: Brisbane, QLD, Australia
Veranstaltungsdatum: 21.-25.05.2018
DOI: 10.26083/tuprints-00020546
URL / URN: https://tuprints.ulb.tu-darmstadt.de/20546
Zugehörige Links:
Herkunft: Zweitveröffentlichungsservice
Kurzbeschreibung (Abstract):

Challenging tasks in unstructured environments require robots to learn complex models. Given a large amount of information, learning multiple simple models can offer an efficient alternative to a monolithic complex network. Training multiple models-that is, learning their parameters and their responsibilities-has been shown to be prohibitively hard as optimization is prone to local minima. To efficiently learn multiple models for different contexts, we thus develop a new algorithm based on expectation maximization (EM). In contrast to comparable concepts, this algorithm trains multiple modules of paired forward-inverse models by using the prediction errors of both forward and inverse models simultaneously. In particular, we show that our method yields a substantial improvement over only considering the errors of the forward models on tasks where the inverse space contains multiple solutions.

Status: Postprint
URN: urn:nbn:de:tuda-tuprints-205461
Sachgruppe der Dewey Dezimalklassifikatin (DDC): 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Intelligente Autonome Systeme
TU-Projekte: EC/H2020|640554|SKILLS4ROBOTS
Hinterlegungsdatum: 18 Nov 2022 14:02
Letzte Änderung: 21 Nov 2022 10:47
PPN:
Zugehörige Links:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen