A Multi-Agent Simulation System to Evaluate the Disaster Response Team Coordination and Performance Open Access
Downloadable ContentDownload PDF
Identifying the best design configuration for a disaster-response team is important for minimizing total operation time and reducing the human cost of natural and manmade disasters. This research presents a simulation system that is able to optimally design a disaster-response team and evaluate the team design configuration prior to initiation of search and rescue operation. An agent-based simulation system was developed using machine learning techniques and design of experiments methods to test different configuration setups and determine various factors’ effects on operation completion time. The evaluation of a team design for a disaster scenario revealed that some design factors have a significant effect on operation outcome. Removing the effect of uncontrollable factors, such as damage level and robot reliability, yielded a robust team design that could function in a particular disaster environment regardless of the effects of such factors.The proposed system assists decision makers in evaluating an emergency-response operation, revising the current strategy based on resources on hand, redesigning the available team, and visually tracking operation performance before launching the actual team in the disaster field. This research extends previous disaster response coordination systems by proposing a new simulation model and evaluating a disaster-response team design.