Validation and Evacuee Modeling of Virtual Robot-guided Emergency Evacuation Experiments

Virtual Reality (VR) is an increasingly common tool for investigating human responses to emergency situations. Nonetheless, studies validating and comparing human subject behavior during real world emergencies to their responses in VR are notably rare, and no prior studies have validated whether human emergency responses to guidance from a robot are comparable in VR versus the real world. In the present pre-registered study, we used VR to replicate a previous robot-guided emergency evacuation study conducted in the real world and compared human subject behavior in matched physical and virtual environments. In both environments, human subjects were asked to follow a robot to a location and to then read an article. While reading, a fire alarm sounds. The robot then attempted to guide them to a distant, unfamiliar exit rather than a nearby and familiar exit. We observed close correspondences between evacuee exit choice (the robot’s distant exit versus closer exits), evacuation time, and self-reported trust in the robot between the VR and physical environments. We further demonstrate that data collected in virtual reality can be used to create accurate motion models (mean positional error of 0.42 meters) predicting evacuee trajectories and locations in the physical environment.