Autonomous Motion Conference Paper 2009

Learning and generalization of motor skills by learning from demonstration

We provide a general approach for learning robotic motor skills from human demonstration. To represent an observed movement, a non-linear differential equation is learned such that it reproduces this movement. Based on this representation, we build a library of movements by labeling each recorded movement according to task and context (e.g., grasping, placing, and releasing). Our differential equation is formulated such that generalization can be achieved simply by adapting a start and a goal parameter in the equation to the desired position values of a movement. For object manipulation, we present how our framework extends to the control of gripper orientation and finger position. The feasibility of our approach is demonstrated in simulation as well as on a real robot. The robot learned a pick-and-place operation and a water-serving task and could generalize these tasks to novel situations.

Author(s): Pastor, P. and Hoffmann, H. and Asfour, T. and Schaal, S.
Book Title: International Conference on Robotics and Automation (ICRA2009)
Year: 2009
Bibtex Type: Conference Paper (inproceedings)
Address: Kobe, Japan, May 12-19, 2009
URL: http://www-clmc.usc.edu/publications/P/pastor-ICRA2009.pdf
Cross Ref: p10331
Electronic Archiving: grant_archive
Note: clmc

BibTex

@inproceedings{Pastor_ICRA_2009,
  title = {Learning and generalization of motor skills by learning from demonstration},
  booktitle = {International Conference on Robotics and Automation (ICRA2009)},
  abstract = {We provide a general approach for learning
  robotic motor skills from human demonstration. To represent
  an observed movement, a non-linear differential equation is
  learned such that it reproduces this movement. Based on this
  representation, we build a library of movements by labeling
  each recorded movement according to task and context (e.g.,
  grasping, placing, and releasing). Our differential equation is
  formulated such that generalization can be achieved simply by
  adapting a start and a goal parameter in the equation to the
  desired position values of a movement. For object manipulation,
  we present how our framework extends to the control of gripper
  orientation and finger position. The feasibility of our approach
  is demonstrated in simulation as well as on a real robot. The
  robot learned a pick-and-place operation and a water-serving
  task and could generalize these tasks to novel situations.},
  address = {Kobe, Japan, May 12-19, 2009},
  year = {2009},
  note = {clmc},
  slug = {pastor_icra_2009},
  author = {Pastor, P. and Hoffmann, H. and Asfour, T. and Schaal, S.},
  crossref = {p10331},
  url = {http://www-clmc.usc.edu/publications/P/pastor-ICRA2009.pdf}
}