THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
 |
Learning Dextrous Manipulation Skills Using the Evolution Strategy |
pdf 439 KB
ps.gz 2.14 MB
ps 6.65 MB
@InProceedings{Fuentes:97,
author = {Olac Fuentes and Randal C. Nelson},
title = {Learning Dextrous Manipulation Skills Using the Evolution Strategy}
booktitle = {Proc. of International Conference on Robotics and Automation (ICRA97)},
year = {1997},
address = {Albuquerque NM},
month = {April},
abstract = {This paper presents an approach based on the evolution
strategy for autonomous learning of dextrous manipulation
primitives with a dextrous robot hand. We use heuristics
derived from observations made onhuman hands to reduce the
degrees of freedom of the task andmake learning possible. Our
system does not rely on simulation; all the experimentation
is performed the 16degreeoffreedom Utah/MIT hand. We
present experimental results that show that accurate dextrous
manipulation skills can be learned in a period of a few minutes.
We also show the application of the learned primitives to
perform an assembly task. }
}