Statistical Learning by Imitation of Competing Constraints in Joint Space and Task Space

We present a probabilistic architecture for solving generically the problem of extracting the task constraints through a programming by demonstration framework and for generalizing the acquired knowledge to various situations. In previous work, we proposed an approach based on Gaussian mixture regre...

Full description

Saved in:
Bibliographic Details
Published inAdvanced robotics Vol. 23; no. 15; pp. 2059 - 2076
Main Authors Calinon, Sylvain, Billard, Aude
Format Journal Article
LanguageEnglish
Published Taylor & Francis Group 01.01.2009
Subjects
GAUSSIAN MIXTURE REGRESSION
INVERSE KINEMATICS
KINESTHETIC TEACHING
LEARNING BY IMITATION
ROBOT PROGRAMMING BY DEMONSTRATION
Online AccessGet full text
ISSN0169-1864
1568-5535
1568-5535
DOI10.1163/016918609X12529294461843

Cover

More Information
Summary:We present a probabilistic architecture for solving generically the problem of extracting the task constraints through a programming by demonstration framework and for generalizing the acquired knowledge to various situations. In previous work, we proposed an approach based on Gaussian mixture regression to find a controller for the robot reproducing the statistical characteristics of a movement in joint space and in task space through Lagrange optimization. In this paper, we develop an alternative procedure to handle simultaneously constraints in joint space and in task space by combining directly the probabilistic representation of the task constraints with a solution to Jacobian-based inverse kinematics. The method is validated in manipulation tasks with two 5-d.o.f. Katana robotic arms displacing a set of objects.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0169-1864
1568-5535
1568-5535
DOI:10.1163/016918609X12529294461843