Site Search  

Resources » Publication Details

Publication Details

Reference TypeJournal Article
Author(s)Pastor, P.;Kalakrishnan, M.;Meier, F.;Stulp, F.;Buchli, J.;Theodorou, E.;Schaal, S.
TitleFrom Dynamic Movement Primitives to Associative Skill Memories
Journal/Conference/Book TitleRobotics and Autonomous Systems
Keywordsassociative memoryreinforcement learningmovement primitives
AbstractIn recent years, research on movement primitives has gained increasing popular-ity. The original goals of movement primitives are based on the desire to have a sufficiently rich and abstract representation for movement generation, which al-lows for efficient teaching, trial-and-error learning, and generalization of motor skills (Schaal 1999). Thus, motor skills in robots should be acquired in a natural dialogue with humans, e.g., by imitation learning and shaping, while skill re-finement and generalization should be accomplished autonomously by the robot. Such a scenario resembles the way we teach children and connects to the bigger question of how the human brain accomplishes skill learning. In this paper, we review how a particular computational approach to movement primitives, called dynamic movement primitives, can contribute to learning motor skills. We will address imitation learning, generalization, trial-and-error learning by reinforce-ment learning, movement recognition, and control based on movement primi-tives. But we also want to go beyond the standard goals of movement primitives. The stereotypical movement generation with movement primitives entails pre-dicting of sensory events in the environment. Indeed, all the sensory events asso-ciated with a movement primitive form an associative skill memory that has the potential of forming a most powerful representation of a complete motor skill.
Short TitleFrom Dynamic Movement Primitives to Associative Skill Memories
Custom 3papers2://publication/uuid/8A16FB67-AF1E-4F12-8F48-626E2FD8CC09

Designed by: Nerses Ohanyan & Jan Peters
Page last modified on June 20, 2013, at 07:00 PM