Manschitz, Simon ; Gienger, Michael ; Kober, Jens ; Peters, Jan (2020)
Learning Sequential Force Interaction Skills.
In: Robotics, 9 (2)
doi: 10.3390/robotics9020045
Artikel, Bibliographie
Dies ist die neueste Version dieses Eintrags.
Kurzbeschreibung (Abstract)
Learning skills from kinesthetic demonstrations is a promising way of minimizing the gap between human manipulation abilities and those of robots. We propose an approach to learn sequential force interaction skills from such demonstrations. The demonstrations are decomposed into a set of movement primitives by inferring the underlying sequential structure of the task. The decomposition is based on a novel probability distribution which we call Directional Normal Distribution. The distribution allows infering the movement primitive’s composition, i.e., its coordinate frames, control variables and target coordinates from the demonstrations. In addition, it permits determining an appropriate number of movement primitives for a task via model selection. After finding the task’s composition, the system learns to sequence the resulting movement primitives in order to be able to reproduce the task on a real robot. We evaluate the approach on three different tasks, unscrewing a light bulb, box stacking and box flipping. All tasks are kinesthetically demonstrated and then reproduced on a Barrett WAM robot.
Typ des Eintrags: | Artikel |
---|---|
Erschienen: | 2020 |
Autor(en): | Manschitz, Simon ; Gienger, Michael ; Kober, Jens ; Peters, Jan |
Art des Eintrags: | Bibliographie |
Titel: | Learning Sequential Force Interaction Skills |
Sprache: | Englisch |
Publikationsjahr: | 2020 |
Ort: | Basel |
Verlag: | MDPI |
Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Robotics |
Jahrgang/Volume einer Zeitschrift: | 9 |
(Heft-)Nummer: | 2 |
Kollation: | 30 Seiten |
DOI: | 10.3390/robotics9020045 |
Zugehörige Links: | |
Kurzbeschreibung (Abstract): | Learning skills from kinesthetic demonstrations is a promising way of minimizing the gap between human manipulation abilities and those of robots. We propose an approach to learn sequential force interaction skills from such demonstrations. The demonstrations are decomposed into a set of movement primitives by inferring the underlying sequential structure of the task. The decomposition is based on a novel probability distribution which we call Directional Normal Distribution. The distribution allows infering the movement primitive’s composition, i.e., its coordinate frames, control variables and target coordinates from the demonstrations. In addition, it permits determining an appropriate number of movement primitives for a task via model selection. After finding the task’s composition, the system learns to sequence the resulting movement primitives in order to be able to reproduce the task on a real robot. We evaluate the approach on three different tasks, unscrewing a light bulb, box stacking and box flipping. All tasks are kinesthetically demonstrated and then reproduced on a Barrett WAM robot. |
Freie Schlagworte: | human-robot interaction, motor skill learning, learning from demonstration, behavioral cloning |
Zusätzliche Informationen: | Erstveröffentlichung; This article belongs to the Special Issue Feature Papers 2020 |
Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik 600 Technik, Medizin, angewandte Wissenschaften > 621.3 Elektrotechnik, Elektronik |
Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Intelligente Autonome Systeme |
Hinterlegungsdatum: | 15 Mai 2024 14:41 |
Letzte Änderung: | 15 Mai 2024 14:41 |
PPN: | |
Export: | |
Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
-
Learning Sequential Force Interaction Skills. (deposited 15 Jan 2024 14:03)
- Learning Sequential Force Interaction Skills. (deposited 15 Mai 2024 14:41) [Gegenwärtig angezeigt]
![]() |
Frage zum Eintrag |
Optionen (nur für Redakteure)
![]() |
Redaktionelle Details anzeigen |