Preparing for the aftermath: Using emotional agents in game-based training for disaster response

摘要

Ground truth, a training game developed by Sandia National Laboratories in partnership with the University of Southern California GamePipe Lab, puts a player in the role of an incident commander working with teammate agents to respond to urban threats. These agents simulate certain emotions that a responder may feel during this high-stress situation. We construct psychology-plausible models compliant with the Sandia Human Embodiment and Representation Cognitive Architecture (SHERCA) that are run on the sandia cognitive runtime engine with active memory (SCREAM) software. SCREAM's computational representations for modeling human decision-making combine aspects of ANNs and fuzzy logic networks. This paper gives an overview of ground truth and discusses the adaptation of the SHERCA and SCREAM into the game. We include a semiformal description of SCREAM.