Veiga, Filipe ; Akrour, Riad ; Peters, Jan (2024)
Hierarchical Tactile-Based Control Decomposition of Dexterous In-Hand Manipulation Tasks.
In: Frontiers in Robotics and AI, 2020, 7
doi: 10.26083/tuprints-00016159
Artikel, Zweitveröffentlichung, Verlagsversion
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
Kurzbeschreibung (Abstract)
In-hand manipulation and grasp adjustment with dexterous robotic hands is a complex problem that not only requires highly coordinated finger movements but also deals with interaction variability. The control problem becomes even more complex when introducing tactile information into the feedback loop. Traditional approaches do not consider tactile feedback and attempt to solve the problem either by relying on complex models that are not always readily available or by constraining the problem in order to make it more tractable. In this paper, we propose a hierarchical control approach where a higher level policy is learned through reinforcement learning, while low level controllers ensure grip stability throughout the manipulation action. The low level controllers are independent grip stabilization controllers based on tactile feedback. The independent controllers allow reinforcement learning approaches to explore the manipulation tasks state-action space in a more structured manner. We show that this structure allows learning the unconstrained task with RL methods that cannot learn it in a non-hierarchical setting. The low level controllers also provide an abstraction to the tactile sensors input, allowing transfer to real robot platforms. We show preliminary results of the transfer of policies trained in simulation to the real robot hand.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Veiga, Filipe ; Akrour, Riad ; Peters, Jan |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | Hierarchical Tactile-Based Control Decomposition of Dexterous In-Hand Manipulation Tasks |
| Sprache: | Englisch |
| Publikationsjahr: | 8 März 2024 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | 19 November 2020 |
| Ort der Erstveröffentlichung: | Lausanne |
| Verlag: | Frontiers Media S.A. |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Frontiers in Robotics and AI |
| Jahrgang/Volume einer Zeitschrift: | 7 |
| Kollation: | 12 Seiten |
| DOI: | 10.26083/tuprints-00016159 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/16159 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichung DeepGreen |
| Kurzbeschreibung (Abstract): | In-hand manipulation and grasp adjustment with dexterous robotic hands is a complex problem that not only requires highly coordinated finger movements but also deals with interaction variability. The control problem becomes even more complex when introducing tactile information into the feedback loop. Traditional approaches do not consider tactile feedback and attempt to solve the problem either by relying on complex models that are not always readily available or by constraining the problem in order to make it more tractable. In this paper, we propose a hierarchical control approach where a higher level policy is learned through reinforcement learning, while low level controllers ensure grip stability throughout the manipulation action. The low level controllers are independent grip stabilization controllers based on tactile feedback. The independent controllers allow reinforcement learning approaches to explore the manipulation tasks state-action space in a more structured manner. We show that this structure allows learning the unconstrained task with RL methods that cannot learn it in a non-hierarchical setting. The low level controllers also provide an abstraction to the tactile sensors input, allowing transfer to real robot platforms. We show preliminary results of the transfer of policies trained in simulation to the real robot hand. |
| Freie Schlagworte: | tactile sensation and sensors, robotics, in-hand manipulation, hierarchical control, reinforcement learning |
| ID-Nummer: | Artikel-ID: 521448 |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-161591 |
| Zusätzliche Informationen: | Specialty section: This article was submitted to Sensor Fusion and Machine Perception, a section of the journal Frontiers in Robotics and AI |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Intelligente Autonome Systeme |
| Hinterlegungsdatum: | 08 Mär 2024 13:19 |
| Letzte Änderung: | 12 Mär 2024 07:36 |
| PPN: | |
| Zugehörige Links: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
- Hierarchical Tactile-Based Control Decomposition of Dexterous In-Hand Manipulation Tasks. (deposited 08 Mär 2024 13:19) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum