Learning interaction control policies by demonstration

Vasiliki Koropouli, Dongheui Lee, Sandra Hirche

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

17 Scopus citations

Abstract

This paper explores learning of interaction force skills by human demonstration in dynamic interaction tasks. Skillful force regulation is required in many cases to achieve the goal of a task and at the same time, not to cause undesired stress on the manipulator or the object under manipulation which could result in physical failure. For example, manipulation of compliant objects with varying physical properties or artistic tasks such as engraving require skillful force modulation. Humans gracefully manipulate objects by using their sense of touch and skillfully regulating exerted forces. To learn the demonstrated force for a task by demonstration, an interaction force control policy, in terms of a goal-directed dynamical system, is proposed which stems from the parallel force/position control. The control policy is parameterized and its parameters are learned by Locally Weighted Regression from human demonstrated data to learn a force trajectory. Scaling of learned force is possible by modifying the goal of the system. The proposed method is evaluated in virtual manipulation tasks using a two degrees-of-freedom haptic device.

Original languageEnglish
Title of host publicationIROS'11 - 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems
Subtitle of host publicationCelebrating 50 Years of Robotics
Pages344-349
Number of pages6
DOIs
StatePublished - 2011
Event2011 IEEE/RSJ International Conference on Intelligent Robots and Systems: Celebrating 50 Years of Robotics, IROS'11 - San Francisco, CA, United States
Duration: 25 Sep 201130 Sep 2011

Publication series

NameIEEE International Conference on Intelligent Robots and Systems

Conference

Conference2011 IEEE/RSJ International Conference on Intelligent Robots and Systems: Celebrating 50 Years of Robotics, IROS'11
Country/TerritoryUnited States
CitySan Francisco, CA
Period25/09/1130/09/11

Fingerprint

Dive into the research topics of 'Learning interaction control policies by demonstration'. Together they form a unique fingerprint.

Cite this