DocumentCode :
3575716
Title :
Learning motion and impedance behaviors from human demonstrations
Author :
Saveriano, Matteo ; Dongheui Lee
Author_Institution :
Dept. of Autom. Control Eng., Tech. Univ. of Munich, Munich, Germany
fYear :
2014
Firstpage :
368
Lastpage :
373
Abstract :
Human-robot skill transfer has been deeply investigated from a kinematic point of view, generating various approaches to increase the robot knowledge in a simple and compact way. Nevertheless, social robotics applications require a close and active interaction with humans in a safe and natural manner. Torque controlled robots, with their variable impedance capabilities, seem a viable option toward a safe and profitable human-robot interaction. In this paper, an approach is proposed to simultaneously learn motion and impedance behaviors from tasks demonstrations. Kinematic aspects of the task are represented in a statistical way, while the variability along the demonstrations is used to define a variable impedance behavior. The effectiveness of our approach is validated with simulations on real and synthetic data.
Keywords :
human-robot interaction; robot kinematics; active interaction; human demonstrations; human-robot skill transfer; impedance behaviors; kinematic aspects; kinematic point of view; learning motion; profitable human-robot interaction; robot knowledge; simulations; social robotics applications; synthetic data; tasks demonstrations; torque controlled robots; variable impedance behavior; variable impedance capabilities; viable option; Computational modeling; Covariance matrices; Eigenvalues and eigenfunctions; Force; Impedance; Robots; Trajectory; Learning from Demonstrations; state-dependent behavior; variable impedance control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Ubiquitous Robots and Ambient Intelligence (URAI), 2014 11th International Conference on
Type :
conf
DOI :
10.1109/URAI.2014.7057371
Filename :
7057371
Link To Document :
بازگشت