King's College London

Research portal

A Disaster Response System based on Human-Agent Collectives

Research output: Contribution to journalArticle

Sarvapali Ramchurn, Edwin Simpson, Joel Fischer, Trung Dong Huynh, Yuki Ikuno, Steven Reece, Wenchao Jiang, Feng Wu, Jack Flann, Stephen J. Roberts, Luc Moreau, T. Rodden, N.R. Jennings

Original languageEnglish
Pages (from-to)661-708
Number of pages48
JournalJournal Artificial Intelligence Research
Volume57
Early online date31 Dec 2016
DOIs
Publication statusPublished - 2016

Documents

Links

King's Authors

Abstract

Major natural or man-made disasters such as Hurricane Katrina or the 9/11 terror attacks pose sig- nificant challenges for emergency responders. First, they have to develop an understanding of the unfolding event either using their own resources or through third-parties such as the local popu- lation and agencies. Second, based on the information gathered, they need to deploy their teams in a flexible manner, ensuring that each team has the best available capabilities to perform tasks successfully as they navigate a space that may have significantly changed in structure from its pre-disaster state. Third, given the dynamic nature of a disaster space, and the uncertainties in- volved in performing rescue missions, information about the disaster space and the actors within it needs to be stored and verified to ensure that responders are always acting on up-to-date and trusted information. Against this background, this paper proposes a novel disaster response system called HAC-ER that addresses some of the situational awareness and coordination challenges faced by emergency responders in real-world disaster environments. Informed by focus groups with domain experts and real-world trials with volunteers from a number of organisations, HAC- ER interweaves humans and agents, both robotic and software, in social relationships that augment their individual and collective capabilities. HAC-ER thus demonstrates how such Human-Agent Collectives (HACs) can address key challenges in disaster response. Specifically, we show how HAC-ER utilises crowdsourcing combined with machine learning to gather most important sit- uational awareness from large streams of reports posted by members of the public and trusted organisations. We then show how this information can inform human-agent teams in coordinating multi-UAV deployments, as well as task planning for responders on the ground. Finally, HAC-ER incorporates a provenance infrastructure for tracking the provenance of information shared across the entire system to ensure its accountability. A Provenance Agent was also developed to monitor recorded provenance data to help stakeholders in the system to react to changes during an operation in a timely manner. We individually validate each of these elements of HAC-ER and show how they perform against standard (non-HAC) baselines. In summary, this paper describes a prototype system, validated by real-world emergency responders, that combines several state-of-the-art tech- niques for integrating humans and agents, and illustrates, for the first time, how such an approach can enable more effective disaster response operations.

Download statistics

No data available

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454