Metis is a multi-agent based crisis simulation system that provides the ability to design and simulate dynamic indoor crisis scenarios.
Design and setup the entire environment and building to be evacuated, dynamically.
Place pedestrians (agents) in different parts of the building, designate which doors are exits, mark areas of the environment in which the pedestrians will be safe and place fires in different places.
Choose when the simulation automatically ends and manage a dynamically changing crisis. The evacuation process and the modules responsible for the simulation exploit Reinforcement Learning models.
Sidiropoulos, G., Kiourt C. and Moussiades, L., (2020), “Metis: Multi-Agent Based Crisis Simulation System”, Games and AI, Technological, Cultural and Societal aspects (SETN 2020 Workshop), September 2nd-4th - Athens, Greece. arXiv link
G. K.Sidiropoulos, C. Kiourt, and L. Moussiades, “Crowd simulation for crisis management: The outcomes of the last decade,” Mach. Learn. Appl., vol. 2, p. 100009, Dec. 2020. arXiv link