by M Beetz, F Stulp, A Kirsch, A Müller and S Buck
Abstract:
Due to the complexity and sophistication of the skills needed in real world tasks, the development of autonomous robot controllers requires an ever increasing application of learning techniques. To date, however, learning steps are mainly executed in isolation and only the learned code pieces become part of the controller. This approach has several drawbacks: the learning steps themselves are undocumented and not executable. In this paper, we extend an existing control language with constructs for specifying control tasks, process models, learning problems, exploration strategies, etc. Using these constructs, the learning problems can be represented explicitly and transparently and, as they are part of the overall program implementation, become executable. With the extended language we rationally reconstruct large parts of the action selection module of the AGILO2001 autonomous soccer robots.
Reference:
Autonomous Robot Controllers Capable of Acquiring Repertoires of Complex Skills (M Beetz, F Stulp, A Kirsch, A Müller and S Buck), In RoboCup International Symposium 2003, 2003.
Bibtex Entry:
@inproceedings{beetz_autonomous_2003,
author = {M Beetz and F Stulp and A Kirsch and A Müller and S Buck},
title = {Autonomous Robot Controllers Capable of Acquiring Repertoires of
Complex Skills},
booktitle = {{RoboCup} International Symposium 2003},
year = {2003},
series = {Padova},
month = {jul},
abstract = {Due to the complexity and sophistication of the skills needed in real
world tasks, the development of autonomous robot controllers requires
an ever increasing application of learning techniques. To date, however,
learning steps are mainly executed in isolation and only the learned
code pieces become part of the controller. This approach has several
drawbacks: the learning steps themselves are undocumented and not
executable. In this paper, we extend an existing control language
with constructs for specifying control tasks, process models, learning
problems, exploration strategies, etc. Using these constructs, the
learning problems can be represented explicitly and transparently
and, as they are part of the overall program implementation, become
executable. With the extended language we rationally reconstruct
large parts of the action selection module of the {AGILO2001} autonomous
soccer robots.},
}