Koert, Dorothea ; Maeda, Guilherme ; Lioutikov, Rudolf ; Neumann, Gerhard ; Peters, Jan (2022)
Demonstration based trajectory optimization for generalizable robot motions.
International Conference on Humanoid Robots (Humanoids). Cancun, Mexico (15.-17.11.2016)
doi: 10.26083/tuprints-00020544
Konferenzveröffentlichung, Zweitveröffentlichung, Postprint
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
Kurzbeschreibung (Abstract)
Learning motions from human demonstrations provides an intuitive way for non-expert users to teach tasks to robots. In particular, intelligent robotic co-workers should not only mimic human demonstrations but should also be able to adapt them to varying application scenarios. As such, robots must have the ability to generalize motions to different workspaces, e.g. to avoid obstacles not present during original demonstrations. Towards this goal our work proposes a unified method to (1) generalize robot motions to different workspaces, using a novel formulation of trajectory optimization that explicitly incorporates human demonstrations, and (2) to locally adapt and reuse the optimized solution in the form of a distribution of trajectories. This optimized distribution can be used, online, to quickly satisfy via-points and goals of a specific task. We validate the method using a 7 degrees of freedom (DoF) lightweight arm that grasps and places a ball into different boxes while avoiding obstacles that were not present during the original human demonstrations.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Koert, Dorothea ; Maeda, Guilherme ; Lioutikov, Rudolf ; Neumann, Gerhard ; Peters, Jan |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | Demonstration based trajectory optimization for generalizable robot motions |
| Sprache: | Englisch |
| Publikationsjahr: | 2022 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | 2022 |
| Verlag: | IEEE |
| Buchtitel: | 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids) |
| Kollation: | 8 Seiten |
| Veranstaltungstitel: | International Conference on Humanoid Robots (Humanoids) |
| Veranstaltungsort: | Cancun, Mexico |
| Veranstaltungsdatum: | 15.-17.11.2016 |
| DOI: | 10.26083/tuprints-00020544 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/20544 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichungsservice |
| Kurzbeschreibung (Abstract): | Learning motions from human demonstrations provides an intuitive way for non-expert users to teach tasks to robots. In particular, intelligent robotic co-workers should not only mimic human demonstrations but should also be able to adapt them to varying application scenarios. As such, robots must have the ability to generalize motions to different workspaces, e.g. to avoid obstacles not present during original demonstrations. Towards this goal our work proposes a unified method to (1) generalize robot motions to different workspaces, using a novel formulation of trajectory optimization that explicitly incorporates human demonstrations, and (2) to locally adapt and reuse the optimized solution in the form of a distribution of trajectories. This optimized distribution can be used, online, to quickly satisfy via-points and goals of a specific task. We validate the method using a 7 degrees of freedom (DoF) lightweight arm that grasps and places a ball into different boxes while avoiding obstacles that were not present during the original human demonstrations. |
| Status: | Postprint |
| URN: | urn:nbn:de:tuda-tuprints-205443 |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik 600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Intelligente Autonome Systeme |
| TU-Projekte: | EC/H2020|640554|SKILLS4ROBOTS |
| Hinterlegungsdatum: | 18 Nov 2022 13:57 |
| Letzte Änderung: | 21 Nov 2022 10:45 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
- Demonstration based trajectory optimization for generalizable robot motions. (deposited 18 Nov 2022 13:57) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum