by F Stulp and M Beetz
Abstract:
Many plan-based autonomous robot controllers generate chains of abstract actions in order to achieve complex, dynamically changing, and possibly interacting goals. The execution of these action chains often results in robot behavior that shows abrupt transitions between subsequent actions, causing suboptimal performance. The resulting motion patterns are so characteristic for robots that people imitating robotic behavior will do so by making abrupt movements between actions. In this paper we propose a novel computation model for the execution of abstract action chains. In this computation model a robot first learns situation-specific performance models of abstract actions. It then uses these models to automatically specialize the abstract actions for their execution in a given action chain. This specialization results in refined chains that are optimized for performance. As a side effect this behavior optimization also appears to produce action chains with seamless transitions between actions.
Reference:
Optimized Execution of Action Chains Using Learned Performance Models of Abstract Actions (F Stulp and M Beetz), In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI), 2005.
Bibtex Entry:
@inproceedings{stulp_optimized_2005-1,
author = {F Stulp and M Beetz},
title = {Optimized Execution of Action Chains Using Learned Performance Models
of Abstract Actions},
booktitle = {Proceedings of the Nineteenth International Joint Conference on Artificial
Intelligence ({IJCAI)}},
year = {2005},
abstract = {Many plan-based autonomous robot controllers generate chains of abstract
actions in order to achieve complex, dynamically changing, and possibly
interacting goals. The execution of these action chains often results
in robot behavior that shows abrupt transitions between subsequent
actions, causing suboptimal performance. The resulting motion patterns
are so characteristic for robots that people imitating robotic behavior
will do so by making abrupt movements between actions. In this paper
we propose a novel computation model for the execution of abstract
action chains. In this computation model a robot first learns situation-specific
performance models of abstract actions. It then uses these models
to automatically specialize the abstract actions for their execution
in a given action chain. This specialization results in refined chains
that are optimized for performance. As a side effect this behavior
optimization also appears to produce action chains with seamless
transitions between actions.},
}