Agent-Based Modeling and Deep Neural Networks for Establishing Digital Twins of Secure Facilities under Sensing Restrictions

2025-03-29

AI Summary

High-security nuclear facilities are physically isolated, precluding deployment of personnel sensors and hindering construction of human behavioral digital twins. Method: This study proposes MetaPOL—a novel framework that, without any real-world trajectory data, integrates lightweight agent-based modeling (ABM) with deep neural networks (MLP + Mixture Density Networks, MDN) grounded in domain knowledge to synthesize high-fidelity personnel movement trajectories. These trajectories drive virtual reality (VR) NPCs to execute both routine operations and emergency response behaviors. Contribution/Results: Experimental evaluation demonstrates >89% accuracy in synthetic trajectory prediction. Kinematic features of the two behavioral modes are statistically separable (p < 0.001), enabling valid internal threat scenario modeling and verifiable behavioral differentiation—entirely without reliance on empirical human motion data.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Digital twin technologies help practitioners simulate, monitor, and predict undesirable outcomes in-silico, while avoiding the cost and risks of conducting live simulation exercises. Virtual reality (VR) based digital twin technologies are especially useful when monitoring human Patterns of Life (POL) in secure nuclear facilities, where live simulation exercises are too dangerous and costly to ever perform. However, the high-security status of such facilities may restrict modelers from deploying human activity sensors for data collection. This problem was encountered when deploying MetaPOL, a digital twin system to prevent insider threat or sabotage of secure facilities, at a secure nuclear reactor facility at Oak Ridge National Laboratory (ORNL). This challenge was addressed using an agent-based model (ABM), driven by anecdotal evidence of facility personnel POL, to generate synthetic movement trajectories. These synthetic trajectories were then used to train deep neural network surrogates for next location and stay duration prediction to drive NPCs in the VR environment. In this study, we evaluate the efficacy of this technique for establishing NPC movement within MetaPOL and the ability to distinguish NPC movement during normal operations from that during a simulated emergency response. Our results demonstrate the success of using a multi-layer perceptron for next location prediction and mixture density network for stay duration prediction to predict the ABM generated trajectories. We also find that NPC movement in the VR environment driven by the deep neural networks under normal operations remain significantly different to that seen when simulating responses to a simulated emergency scenario.

Problem

• Simulating human movement in secure nuclear facilities without live sensors
• Generating synthetic data to train AI for VR-based digital twins
• Distinguishing normal vs emergency movement patterns in virtual environments

Innovation

• Agent-based model generates synthetic movement trajectories
• Deep neural networks predict next location and duration
• VR environment simulates normal and emergency scenarios