Institute Homepage DE Sign In

Back

Autonomous Motion Conference Paper 1997

Robot learning from demonstration

Thumb ticker sm ss
Autonomous Motion
Stefan Schaal
  • Director

The goal of robot learning from demonstration is to have a robot learn from watching a demonstration of the task to be performed. In our approach to learning from demonstration the robot learns a reward function from the demonstration and a task model from repeated attempts to perform the task. A policy is computed based on the learned reward function and task model. Lessons learned from an implementation on an anthropomorphic robot arm using a pendulum swing up task include 1) simply mimicking demonstrated motions is not adequate to perform this task, 2) a task planner can use a learned model and reward function to compute an appropriate policy, 3) this model-based planning process supports rapid learning, 4) both parametric and nonparametric models can be learned and used, and 5) incorporating a task level direct learning component, which is non-model-based, in addition to the model-based planner, is useful in compensating for structural modeling errors and slow model learning. 

Author(s): Atkeson, C. G. and Schaal, S.
Book Title: Machine Learning: Proceedings of the Fourteenth International Conference (ICML ’97)
Pages: 12-20
Year: 1997
Editors: Fisher Jr., D. H.
Publisher: Morgan Kaufmann
Bibtex Type: Conference Paper (inproceedings)
Address: Nashville, TN, July 8-12, 1997
URL: http://www-clmc.usc.edu/publications/A/atkeson-ICML1997.pdf
Cross Ref: p42
Electronic Archiving: grant_archive
Note: clmc

BibTex 

@inproceedings{Atkeson_MLPFIC_1997,
  title = {Robot learning from demonstration},
  booktitle = {Machine Learning: Proceedings of the Fourteenth International Conference (ICML '97)},
  abstract = {The goal of robot learning from demonstration is to have a robot learn from watching a demonstration of the task to be performed. In our approach to learning from demonstration the robot learns a reward function from the demonstration and a task model from repeated attempts to perform the task. A policy is computed based on the learned reward function and task model. Lessons learned from an implementation on an anthropomorphic robot arm using a pendulum swing up task include 1) simply mimicking demonstrated motions is not adequate to perform this task, 2) a task planner can use a learned model and reward function to compute an appropriate policy, 3) this model-based planning process supports rapid learning, 4) both parametric and nonparametric models can be learned and used, and 5) incorporating a task level direct learning component, which is non-model-based, in addition to the model-based planner, is useful in compensating for structural modeling errors and slow model learning. },
  pages = {12-20},
  editors = {Fisher  Jr., D. H.},
  publisher = {Morgan Kaufmann},
  address = {Nashville, TN, July 8-12, 1997},
  year = {1997},
  note = {clmc},
  slug = {atkeson_mlpfic_1997},
  author = {Atkeson, C. G. and Schaal, S.},
  crossref = {p42},
  url = {http://www-clmc.usc.edu/publications/A/atkeson-ICML1997.pdf}
}