Interaction learning for dynamic movement primitives used in cooperative robotic tasks
2013 | journal article. A publication with affiliation to the University of Göttingen.
Jump to: Cite & Linked | Documents & Media | Details | Version history
Cite this publication
Interaction learning for dynamic movement primitives used in cooperative robotic tasks
Kulvicius, T.; Biehl, M.; Aein, M. J.; Tamosiunaite, M. & Woergoetter, F. (2013)
Robotics and Autonomous Systems, 61(12) pp. 1450-1459. DOI: https://doi.org/10.1016/j.robot.2013.07.009
Documents & Media
Details
- Authors
- Kulvicius, Tomas; Biehl, Martin; Aein, Mohamad Javad; Tamosiunaite, Minija; Woergoetter, Florentin
- Abstract
- Since several years dynamic movement primitives (DMPs) are more and more getting into the center of interest for flexible movement control in robotics. In this study we introduce sensory feedback together with a predictive learning mechanism which allows tightly coupled dual-agent systems to learn an adaptive, sensor-driven interaction based on DMPs. The coupled conventional (no-sensors, no learning) DMP-system automatically equilibrates and can still be solved analytically allowing us to derive conditions for stability. When adding adaptive sensor control we can show that both agents learn to cooperate. Simulations as well as real-robot experiments are shown. Interestingly, all these mechanisms are entirely based on low level interactions without any planning or cognitive component. (C) 2013 Elsevier B.V. All rights reserved.
- Issue Date
- 2013
- Status
- published
- Publisher
- Elsevier Science Bv
- Journal
- Robotics and Autonomous Systems
- ISSN
- 1872-793X; 0921-8890