by M Beetz and T Belker
Abstract:
Autonomous robots, such as robot office couriers, need navigation routines that support flexible task execution and effective action planning. This paper describes XfrmLearn, a system that learns structured symbolic navigation plans. Given a navigation task, XfrmLearn learns to structure continuous navigation behavior and represents the learned structure as compact and transparent plans. The structured plans are obtained by starting with monolithic default plans that are optimized for average performance and adding subplans to improve the navigation performance for the given task. Compactness is achieved by incorporating only subplans that achieve significant performance gains. The resulting plans support action planning and opportunistic task execution. XfrmLearn is implemented and extensively evaluated on an autonomous mobile robot.
Reference:
Learning Structured Reactive Navigation Plans from Executing MDP policies (M Beetz and T Belker), In Proceedings of the 5th International Conference on Autonomous Agents, 2001.
Bibtex Entry:
@inproceedings{beetz_learning_2001,
author = {M Beetz and T Belker},
title = {Learning Structured Reactive Navigation Plans from Executing {MDP}
policies},
booktitle = {Proceedings of the 5th International Conference on Autonomous Agents},
year = {2001},
pages = {19–20},
abstract = {Autonomous robots, such as robot office couriers, need navigation
routines that support flexible task execution and effective action
planning. This paper describes {XfrmLearn}, a system that learns
structured symbolic navigation plans. Given a navigation task, {XfrmLearn}
learns to structure continuous navigation behavior and represents
the learned structure as compact and transparent plans. The structured
plans are obtained by starting with monolithic default plans that
are optimized for average performance and adding subplans to improve
the navigation performance for the given task. Compactness is achieved
by incorporating only subplans that achieve significant performance
gains. The resulting plans support action planning and opportunistic
task execution. {XfrmLearn} is implemented and extensively evaluated
on an autonomous mobile robot.},
}