Header logo is

Learning tasks from a single demonstration


Conference Paper


Learning a complex dynamic robot manoeuvre from a single human demonstration is difficult. This paper explores an approach to learning from demonstration based on learning an optimization criterion from the demonstration and a task model from repeated attempts to perform the task, and using the learned criterion and model to compute an appropriate robot movement. A preliminary version of the approach has been implemented on an anthropomorphic robot arm using a pendulum swing up task as an example

Author(s): Atkeson, C. G. and Schaal, S.
Book Title: IEEE International Conference on Robotics and Automation (ICRA97)
Volume: 2
Pages: 1706-1712
Year: 1997
Publisher: Piscataway, NJ: IEEE

Department(s): Autonomous Motion
Bibtex Type: Conference Paper (inproceedings)

Address: Albuquerque, NM, 20-25 April
Cross Ref: p44
Note: clmc
URL: http://www-clmc.usc.edu/publications/A/atkeson-ICRA1997.pdf


  title = {Learning tasks from a single demonstration},
  author = {Atkeson, C. G. and Schaal, S.},
  booktitle = {IEEE International Conference on Robotics and Automation (ICRA97)},
  volume = {2},
  pages = {1706-1712},
  publisher = {Piscataway, NJ: IEEE},
  address = {Albuquerque, NM, 20-25 April},
  year = {1997},
  note = {clmc},
  crossref = {p44},
  url = {http://www-clmc.usc.edu/publications/A/atkeson-ICRA1997.pdf}