Tanneberg, Daniel ; Peters, Jan ; Rueckert, Elmar (2022)
Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks.
In: Neural Networks, 109
doi: 10.26083/tuprints-00020537
Artikel, Zweitveröffentlichung, Postprint
Kurzbeschreibung (Abstract)
Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself are crucial. In this work, we propose a novel framework for probabilistic online motion planning with online adaptation based on a bio-inspired stochastic recurrent neural network. By using learning signals which mimic the intrinsic motivation signal cognitive dissonance in addition with a mental replay strategy to intensify experiences, the stochastic recurrent network can learn from few physical interactions and adapts to novel environments in seconds. We evaluate our online planning and adaptation framework on an anthropomorphic KUKA LWR arm. The rapid online adaptation is shown by learning unknown workspace constraints sample-efficiently from few physical interactions while following given way points.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Tanneberg, Daniel ; Peters, Jan ; Rueckert, Elmar |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks |
| Sprache: | Englisch |
| Publikationsjahr: | 2022 |
| Ort: | Darmstadt |
| Verlag: | Elsevier |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Neural Networks |
| Jahrgang/Volume einer Zeitschrift: | 109 |
| Kollation: | 18 Seiten |
| DOI: | 10.26083/tuprints-00020537 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/20537 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichungsservice |
| Kurzbeschreibung (Abstract): | Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself are crucial. In this work, we propose a novel framework for probabilistic online motion planning with online adaptation based on a bio-inspired stochastic recurrent neural network. By using learning signals which mimic the intrinsic motivation signal cognitive dissonance in addition with a mental replay strategy to intensify experiences, the stochastic recurrent network can learn from few physical interactions and adapts to novel environments in seconds. We evaluate our online planning and adaptation framework on an anthropomorphic KUKA LWR arm. The rapid online adaptation is shown by learning unknown workspace constraints sample-efficiently from few physical interactions while following given way points. |
| Freie Schlagworte: | Intrinsic motivation, Online learning, Experience replay, Autonomous robots, Spiking recurrent networks, Neural sampling |
| Status: | Postprint |
| URN: | urn:nbn:de:tuda-tuprints-205376 |
| 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 13:46 |
| Letzte Änderung: | 21 Nov 2022 10:21 |
| PPN: | |
| Zugehörige Links: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum