by F Stulp and M Beetz
Abstract:
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 through Subgoal Refinement (F Stulp and M Beetz), 2005. (ICAPS Workshop “Plan Execution: A Reality Check”)
Bibtex Entry:
@book{stulp_optimized_2005,
title = {Optimized Execution of Action Chains through Subgoal Refinement},
year = {2005},
author = {F Stulp and M Beetz},
abstract = {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.},
url = {http://ic.arc.nasa.gov/people/sailesh/icaps2005wksp/},
}