Header logo is ei

Learning Perceptual Coupling for Motor Primitives

2008

Conference Paper

ei


Dynamic system-based motor primitives [1] have enabled robots to learn complex tasks ranging from Tennisswings to locomotion. However, to date there have been only few extensions which have incorporated perceptual coupling to variables of external focus, and, furthermore, these modifications have relied upon handcrafted solutions. Humans learn how to couple their movement primitives with external variables. Clearly, such a solution is needed in robotics. In this paper, we propose an augmented version of the dynamic systems motor primitives which incorporates perceptual coupling to an external variable. The resulting perceptually driven motor primitives include the previous primitives as a special case and can inherit some of their interesting properties. We show that these motor primitives can perform complex tasks such as Ball-in-a-Cup or Kendama task even with large variances in the initial conditions where a skilled human player would be challenged. For doing so, we initialize the motor primitives in the traditional way by imitation learning without perceptual coupling. Subsequently, we improve the motor primitives using a novel reinforcement learning method which is particularly well-suited for motor primitives.

Author(s): Kober, J. and Mohler, B. and Peters, J.
Book Title: IROS 2008
Journal: Proceedings of the 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2008)
Pages: 834-839
Year: 2008
Month: September
Day: 0
Publisher: IEEE Service Center

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Address: Piscataway, NJ, USA
Digital: 0
DOI: 10.1109/IROS.2008.4650953
Event Name: 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems
Event Place: Nice, France
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{5414,
  title = {Learning Perceptual Coupling for Motor Primitives},
  author = {Kober, J. and Mohler, B. and Peters, J.},
  journal = {Proceedings of the 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2008)},
  booktitle = {IROS 2008},
  pages = {834-839},
  publisher = {IEEE Service Center},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Piscataway, NJ, USA},
  month = sep,
  year = {2008},
  month_numeric = {9}
}