Hierarchical planning for resource-constrained long-term monitoring missions in time-varying environments
We consider autonomous robots deployed on long-term monitoring missions in unknown environments. The planning objective is to maximise the value of observations obtained over the course of a mission, subject to resource constraints which demand periodic visits to depots where resources can be replen...
Main Authors: | , , |
---|---|
Format: | Conference item |
Language: | English |
Published: |
IOS Press
2024
|
_version_ | 1826315172487102464 |
---|---|
author | Stephens, R Lacerda, B Hawes, N |
author_facet | Stephens, R Lacerda, B Hawes, N |
author_sort | Stephens, R |
collection | OXFORD |
description | We consider autonomous robots deployed on long-term monitoring missions in unknown environments. The planning objective is to maximise the value of observations obtained over the course of a mission, subject to resource constraints which demand periodic visits to depots where resources can be replenished. Effective planning in this setting requires reasoning over long horizons based on sparse observational data, and flexible management of the constrained resources. We present a hierarchical planning approach to this problem, using a spatiotemporal Gaussian process environment model at different levels of abstraction for short- and long-horizon planning. We empirically evaluate our approach on a series of synthetic domains, and a wildfire monitoring scenario based on real data. |
first_indexed | 2024-12-09T03:19:15Z |
format | Conference item |
id | oxford-uuid:d1c6dd84-7149-4d58-a8f4-90b8c1b48502 |
institution | University of Oxford |
language | English |
last_indexed | 2024-12-09T03:19:15Z |
publishDate | 2024 |
publisher | IOS Press |
record_format | dspace |
spelling | oxford-uuid:d1c6dd84-7149-4d58-a8f4-90b8c1b485022024-11-04T14:24:42ZHierarchical planning for resource-constrained long-term monitoring missions in time-varying environmentsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:d1c6dd84-7149-4d58-a8f4-90b8c1b48502EnglishSymplectic ElementsIOS Press2024Stephens, RLacerda, BHawes, NWe consider autonomous robots deployed on long-term monitoring missions in unknown environments. The planning objective is to maximise the value of observations obtained over the course of a mission, subject to resource constraints which demand periodic visits to depots where resources can be replenished. Effective planning in this setting requires reasoning over long horizons based on sparse observational data, and flexible management of the constrained resources. We present a hierarchical planning approach to this problem, using a spatiotemporal Gaussian process environment model at different levels of abstraction for short- and long-horizon planning. We empirically evaluate our approach on a series of synthetic domains, and a wildfire monitoring scenario based on real data. |
spellingShingle | Stephens, R Lacerda, B Hawes, N Hierarchical planning for resource-constrained long-term monitoring missions in time-varying environments |
title | Hierarchical planning for resource-constrained long-term monitoring missions in time-varying environments |
title_full | Hierarchical planning for resource-constrained long-term monitoring missions in time-varying environments |
title_fullStr | Hierarchical planning for resource-constrained long-term monitoring missions in time-varying environments |
title_full_unstemmed | Hierarchical planning for resource-constrained long-term monitoring missions in time-varying environments |
title_short | Hierarchical planning for resource-constrained long-term monitoring missions in time-varying environments |
title_sort | hierarchical planning for resource constrained long term monitoring missions in time varying environments |
work_keys_str_mv | AT stephensr hierarchicalplanningforresourceconstrainedlongtermmonitoringmissionsintimevaryingenvironments AT lacerdab hierarchicalplanningforresourceconstrainedlongtermmonitoringmissionsintimevaryingenvironments AT hawesn hierarchicalplanningforresourceconstrainedlongtermmonitoringmissionsintimevaryingenvironments |