Human Swarm Interaction

ICT Lead: David Traum

We investigate issues of Human-Multi Robot and Agent-Robot collaboration in a simulated environment.
In the simulation, a small town is under threat of an approaching natural disaster (simulated wildfire), and a single-human/multirobot team has been tasked to find residents and help them evacuate safely. A human participant assumes the role of a swarm operator, tasked with the swift and safe evacuation of the town residents before the fire arrives at their location. The operator handles the high-level assignment of duties to members of the swarm, while low-level decisions are taken by the swarm itself. The operator also handles communication with residents who need to be evacuated.

An initial overview of the simulation can be foiund here:

  • Patricia Chaffey, Ron Artstein, Kallirroi Georgila, Kimberly A. Pollard, Setareh Nasihati Gilani, David M. Krum, David Nelson, Kevin Huynh, Alesia Gainer, Seyed Hossein Alavi, Rhys Yahata, Anton Leuski, Volodymyr Yanov, and David Traum. Human Swarm Interaction using Plays, Audibles, and a Virtual Spokesperson. In Proceedings of SPIE 11413, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II, 114130V, SPIE Defense + Commercial Sensing Conference, Online Only, California, USA, 2020.

Some recent findings from analyzing collected data can be found here:

We are currently continuing the data analysis and automating townspeople.