Sign up & Download
Sign in

Learning new basic Movements for Robotics

by Jens Kober, Jan Peters
Proceedings of Autonome Mobile Systeme ()

Abstract

Obtaining novel skills is one of the most important problems in robotics. Machine learning techniques may be a promising approach for automatic and autonomous acquisition of movement policies. How- ever, this requires both an appropriate policy representation and suitable learning algorithms. Employing the most recent form of the dynami- cal systems motor primitives originally introduced by Ijspeert et al. [1], we show how both discrete and rhythmic tasks can be learned using a concerted approach of both imitation and reinforcement learning, and present our current best performing learning algorithms. Finally, we show that it is possible to include a start-up phase in rhythmic primitives.We apply our approach to two elementary movements, i.e., Ball-in-a-Cup and Ball-Paddling, which can be learned on a real Barrett WAM robot arm at a pace similar to human learning.

Cite this document (BETA)

Readership Statistics

12 Readers on Mendeley
by Discipline
 
 
 
by Academic Status
 
42% Student (Master)
 
25% Ph.D. Student
 
17% Researcher (at an Academic Institution)
by Country
 
8% Italy
 
8% Spain

Sign up today - FREE

Mendeley saves you time finding and organizing research. Learn more

  • All your research in one place
  • Add and import papers easily
  • Access it anywhere, anytime

Start using Mendeley in seconds!

Already have an account? Sign in