Simulating human behavior for national security human interactions.

Abstract

This 3-year research and development effort focused on what we believe is a significant technical gap in existing modeling and simulation capabilities: the representation of plausible human cognition and behaviors within a dynamic, simulated environment. Specifically, the intent of the Simulating Human Behavior for National Security Human Interactions project was to demonstrate initial simulated human modeling capability that realistically represents intra-and inter-group interaction behaviors between simulated humans and human-controlled avatars as they respond to their environment. Significant process was made towards simulating human behaviors through the development of a framework that produces realistic characteristics and movement. The simulated humans were created from models designed to be psychologically plausible by being based on robust psychological research and theory. Progress was also made towards enhancing Sandia National Laboratories' existing cognitive models to support culturally plausible behaviors that are important in representing group interactions. These models were implemented in the modular, interoperable, and commercially supported Umbra ® simulation framework.4

A case for Sandia investment in complex adaptive systems science and technology.

“…Sandia has built computational models based on human cognition 53 , improved and extended the use of agentbased models, and exploited meso-scale network structures to predict group behavior.…”

LDRD project final report : hybrid AI/cognitive tactical behavior framework for LVC.

“…The 2004-2006 LDRD, "Simulating Human Interactions for National Security Interactions", demonstrated an Umbra-based integration of a partial cognitive framework, SCREAM + SHERCA, with 3D simulated entities [Bernard, et al, 2007]. The 2006-2008 LDRD, "Enabling Immersive Simulation", produced several integrations, including: Trainable Automated Forces and Cognitive Foundry cognitive models with Umbra; and NPS's Delta3D with ABL [Abbott, et al, 2009].…”

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

“…Applying SHERCA for the conceptual and psychological model structure and SCREAM for the computational cognitive engine, [24] used runtime cognitive models to control the behavior of cognitive characters in a virtual 3D environment in a prototype training application emphasizing cultural awareness [22]. Standard embodied-agent simula-tion techniques implemented in Sandia's Umbra simulation framework [25] model the characters' ability to "perceive" their environment, other entities, and those entities' various attributes and actions.…”

“…A. SHERCA SHERCA was designed to correspond to the theories and supporting research mentioned in Section III [24]. SHERCA allows for multiple cues, cognitive perceptions, goals, action intentions, etc., to concurrently have some degree of activation.…”

“…While SHERCA is intended eventually to achieve human-plausibility at a detailed level as various cognitive component models improve [27], initial emphasis has been on applying it to virtual embodiment. In this role SHERCA has been instantiated as a human-representative computational model through which a cognitive character recognizes patterns of stimuli in the environment and responds to those stimuli according to current contexts, goals, and emotions [24]. Our main focus has been endowing characters with SHERCA's model of decision-making to select behaviorlevel actions rather than model detailed procedures or lowlevel control.…”