by A Kirsch
Abstract:
For planning in the domain of autonomous robots, abstraction of state and actions is indispensable. This abstraction however comes at the cost of suboptimal execution, as relevant information is ignored. A solution is to maintain abstractions for planning, but to fill in precise information on the level of execution. To do so, the control program needs models of its own behavior, which could be learned by the robot automatically. In my dissertation I develop a robot control and plan language, which provides mechanisms for the representation of state variables, goals and actions, and integrates learning into the language.
Reference:
Towards High-performance Robot Plans with Grounded Action Models: Integrating Learning Mechanisms into Robot Control Languages (A Kirsch), In ICAPS Doctoral Consortium, 2005.
Bibtex Entry:
@inproceedings{kirsch_towards_2005,
author = {A Kirsch},
title = {Towards High-performance Robot Plans with Grounded Action Models:
Integrating Learning Mechanisms into Robot Control Languages},
booktitle = {{ICAPS} Doctoral Consortium},
year = {2005},
abstract = {For planning in the domain of autonomous robots, abstraction of state
and actions is indispensable. This abstraction however comes at the
cost of suboptimal execution, as relevant information is ignored.
A solution is to maintain abstractions for planning, but to fill
in precise information on the level of execution. To do so, the control
program needs models of its own behavior, which could be learned
by the robot automatically. In my dissertation I develop a robot
control and plan language, which provides mechanisms for the representation
of state variables, goals and actions, and integrates learning into
the language.},
}