Pitz, Johannes und Röstel, Lennart und Sievers, Leon und Bäuml, Berthold (2023) Dextrous Tactile In-Hand Manipulation Using a Modular Reinforcement Learning Architecture. In: 2023 IEEE International Conference on Robotics and Automation, ICRA 2023, Seiten 1852-1858. IEEE. International Conference on Robotics and Automation, 2023-05-29 - 2023-06-03, London, UK. doi: 10.1109/ICRA48891.2023.10160756. ISBN 979-835032365-8. ISSN 1050-4729.
Dieses Archiv kann nicht den Volltext zur Verfügung stellen.
Offizielle URL: https://ieeexplore.ieee.org/document/10160756
Kurzfassung
Dextrous in-hand manipulation with a multi-fingered robotic hand is a challenging task, esp. when performed with the hand oriented upside down, demanding permanent force-closure, and when no external sensors are used. For the task of reorienting an object to a given goal orientation (vs. infinitely spinning it around an axis), the lack of external sensors is an additional fundamental challenge as the state of the object has to be estimated all the time, e.g., to detect when the goal is reached. In this paper, we show that the task of reorienting a cube to any of the 24 possible goal orientations in a Pi/2-raster using the torque-controlled DLR-Hand II is possible. The task is learned in simulation using a modular deep reinforcement learning architecture: the actual policy has only a small observation time window of 0.5s but gets the cube state as an explicit input which is estimated via a deep differentiable particle filter trained on data generated by running the policy. In simulation, we reach a success rate of 92% while applying significant domain randomization. Via zero-shot Sim2Real-transfer on the real robotic system, all 24 goal orientations can be reached with a high success rate.
elib-URL des Eintrags: | https://elib.dlr.de/195400/ | ||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Poster) | ||||||||||||||||||||
Zusätzliche Informationen: | https://arxiv.org/abs/2303.04705 | ||||||||||||||||||||
Titel: | Dextrous Tactile In-Hand Manipulation Using a Modular Reinforcement Learning Architecture | ||||||||||||||||||||
Autoren: |
| ||||||||||||||||||||
Datum: | Juni 2023 | ||||||||||||||||||||
Erschienen in: | 2023 IEEE International Conference on Robotics and Automation, ICRA 2023 | ||||||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||||||
Open Access: | Nein | ||||||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||||||
In ISI Web of Science: | Nein | ||||||||||||||||||||
DOI: | 10.1109/ICRA48891.2023.10160756 | ||||||||||||||||||||
Seitenbereich: | Seiten 1852-1858 | ||||||||||||||||||||
Verlag: | IEEE | ||||||||||||||||||||
ISSN: | 1050-4729 | ||||||||||||||||||||
ISBN: | 979-835032365-8 | ||||||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||||||
Stichwörter: | In-Hand Manipulation, Deep Reinforcement Learning | ||||||||||||||||||||
Veranstaltungstitel: | International Conference on Robotics and Automation | ||||||||||||||||||||
Veranstaltungsort: | London, UK | ||||||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||||||
Veranstaltungsbeginn: | 29 Mai 2023 | ||||||||||||||||||||
Veranstaltungsende: | 3 Juni 2023 | ||||||||||||||||||||
Veranstalter : | IEEE | ||||||||||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||||||
HGF - Programm: | Raumfahrt | ||||||||||||||||||||
HGF - Programmthema: | Robotik | ||||||||||||||||||||
DLR - Schwerpunkt: | Raumfahrt | ||||||||||||||||||||
DLR - Forschungsgebiet: | R RO - Robotik | ||||||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | R - Autonome, lernende Roboter [RO] | ||||||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||||||
Institute & Einrichtungen: | Institut für Robotik und Mechatronik (ab 2013) | ||||||||||||||||||||
Hinterlegt von: | Pitz, Johannes | ||||||||||||||||||||
Hinterlegt am: | 21 Sep 2023 10:32 | ||||||||||||||||||||
Letzte Änderung: | 24 Apr 2024 20:55 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags