Agile Planning for Real-World Disaster Response

Wu, Feng; Ramchurn, Sarvapali D.; Jiang, Wenchao; Fischer, Joel E.; Rodden, Tom; Jennings, Nicholas R.

Authors

Feng Wu

Sarvapali D. Ramchurn

Wenchao Jiang

JOEL FISCHER Joel.Fischer@nottingham.ac.uk
Professor of Human-Computer Interaction

TOM RODDEN TOM.RODDEN@NOTTINGHAM.AC.UK
Pro-Vice-Chancellor of Research & Knowledge Exchange

Nicholas R. Jennings

Abstract

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.

Citation

Wu, F., Ramchurn, S. D., Jiang, W., Fischer, J. E., Rodden, T., & Jennings, N. R. (2015). Agile Planning for Real-World Disaster Response. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (132-138)

Conference Name	International Joint Conference on Artificial Intelligence (IJCAI-15)
Conference Location	Buenos Aires, Argentina
Start Date	Jul 25, 2015
End Date	Jul 31, 2015
Online Publication Date	Jul 25, 2015
Publication Date	Jul 25, 2015
Deposit Date	Jan 29, 2016
Publisher	Association for Computing Machinery (ACM)
Peer Reviewed	Peer Reviewed
Volume	2015-July
Pages	132-138
Book Title	Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence
ISBN	9781577357384
Public URL	https://nottingham-repository.worktribe.com/output/755965
Publisher URL	https://dl.acm.org/doi/10.5555/2832249.2832268
Additional Information	Published in: Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence: Buenos Aires, Argentina, 25–31 July 2015. Palo Alto, Calif. : AAAI Press/International Joint Conferences on Artificial Intelligence, 2015. ISBN: 978-1-5773-5738-4, pp. 132-138