Agile planning for real-world disaster response

We consider a setting where an agent-based planner instructs teams of human emergency responders to perform tasks in the real world. Due to uncertainty in the environment and the inability of the planner to consider all human preferences and all attributes of the real-world, humans may reject plans...

Full description

Bibliographic Details
Main Authors: Wu, Feng, Ramchurn, Sarvapali D., Jiang, Wenchao, Fischer, Joel E., Rodden, Tom, Jennings, Nicholas R.
Format: Conference or Workshop Item
Published: 2015
Online Access:https://eprints.nottingham.ac.uk/31398/
_version_ 1848794193352196096
author Wu, Feng
Ramchurn, Sarvapali D.
Jiang, Wenchao
Fischer, Joel E.
Rodden, Tom
Jennings, Nicholas R.
author_facet Wu, Feng
Ramchurn, Sarvapali D.
Jiang, Wenchao
Fischer, Joel E.
Rodden, Tom
Jennings, Nicholas R.
author_sort Wu, Feng
building Nottingham Research Data Repository
collection Online Access
description We consider a setting where an agent-based planner instructs teams of human emergency responders to perform tasks in the real world. Due to uncertainty in the environment and the inability of the planner to consider all human preferences and all attributes of the real-world, humans may reject plans computed by the agent. A na¨ıve solution that replans given a rejection is inefficient and does not guarantee the new plan will be acceptable. Hence, we propose a new model re-planning problem using a Multi-agent Markov Decision Process that integrates potential rejections as part of the planning process and propose a novel algorithm to efficiently solve this new model. We empirically evaluate our algorithm and show that it outperforms current benchmarks. Our algorithm is also shown to perform better in pilot studies with real humans.
first_indexed 2025-11-14T19:12:18Z
format Conference or Workshop Item
id nottingham-31398
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:12:18Z
publishDate 2015
recordtype eprints
repository_type Digital Repository
spelling nottingham-313982020-05-04T17:12:05Z https://eprints.nottingham.ac.uk/31398/ Agile planning for real-world disaster response Wu, Feng Ramchurn, Sarvapali D. Jiang, Wenchao Fischer, Joel E. Rodden, Tom Jennings, Nicholas R. We consider a setting where an agent-based planner instructs teams of human emergency responders to perform tasks in the real world. Due to uncertainty in the environment and the inability of the planner to consider all human preferences and all attributes of the real-world, humans may reject plans computed by the agent. A na¨ıve solution that replans given a rejection is inefficient and does not guarantee the new plan will be acceptable. Hence, we propose a new model re-planning problem using a Multi-agent Markov Decision Process that integrates potential rejections as part of the planning process and propose a novel algorithm to efficiently solve this new model. We empirically evaluate our algorithm and show that it outperforms current benchmarks. Our algorithm is also shown to perform better in pilot studies with real humans. 2015-07-31 Conference or Workshop Item PeerReviewed Wu, Feng, Ramchurn, Sarvapali D., Jiang, Wenchao, Fischer, Joel E., Rodden, Tom and Jennings, Nicholas R. (2015) Agile planning for real-world disaster response. In: International Joint Conference on Artificial Intelligence (IJCAI-15), 25-31 July 2015, Buenos Aires, Argentina. http://ijcai.org/papers15/Papers/IJCAI15-026.pdf
spellingShingle Wu, Feng
Ramchurn, Sarvapali D.
Jiang, Wenchao
Fischer, Joel E.
Rodden, Tom
Jennings, Nicholas R.
Agile planning for real-world disaster response
title Agile planning for real-world disaster response
title_full Agile planning for real-world disaster response
title_fullStr Agile planning for real-world disaster response
title_full_unstemmed Agile planning for real-world disaster response
title_short Agile planning for real-world disaster response
title_sort agile planning for real-world disaster response
url https://eprints.nottingham.ac.uk/31398/
https://eprints.nottingham.ac.uk/31398/