Collaborative Research: CISE-MSI: RCBP-RF: CPS, CNS: Emergency Response and Evacuation Training for Active Shooter Events

该奖项全部或部分由《2021年美国救援计划法案》（公法117-2）资助。近年来，我们目睹了活跃枪手事件的急剧增加；然而，不幸的是，并没有引进新的技术或战术来增加对主动射击事件的准备和训练。该项目通过在鲍伊州立大学（BSU）和内华达大学拉斯维加斯分校（UNLV）之间建立跨学科合作伙伴关系和研究能力，促进科技发展的进步，对高等教育学院（IHE）的主动枪手事件进行探索性调查。该项目的目标是为两个校园进行数据收集，初步实验和原型开发，以利用协作式沉浸式虚拟现实（VR）环境改善主动射击事件的应急准备。该项目开发算法，实施软件，并使用建筑系统作为挑战应用领域演示概念验证。这项研究涉及设计新的概念方法，为人类和机器在高度不确定、复杂、时间紧迫和动态变化的任务中做出决策的环境提供新的理论和经验指导。本提案的研究目标包括：1)使用Oculus开发一个沉浸式协作虚拟环境（CVE），用于主动射击事件的行动过程、可视化和态势感知；2)开发一个独特的沉浸式图形用户界面（GUI），用于pc（玩家角色）和npc（非玩家角色）之间的通信，用于用户交互；3)实现主动射击事件中npc的人类行为算法。（如敌意、非敌意、自私、追随领导者、恐慌）；4)基于深度学习（数据驱动）的现实npc行为建模。成功实施的项目有助于利用虚拟现实进行最先进的应急响应培训，开发知识，形成公共教育和意识方案的基础，帮助设施居住者、救援人员和城市官员在极端紧急情况下作出适当反应。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).In recent years, we have witnessed a sharp increase in active shooter events; however, unfortunately, there has been no introduction of new technology or tactics capable of increasing preparedness and training for active shooter events. This project promotes the progress of science and technology development by building interdisciplinary partnerships and research capacity between Bowie State University (BSU) and University of Nevada, Las Vegas (UNLV) for exploratory investigation of active shooter events at Institutes of Higher Education (IHE). The goal of this project is to conduct data collection, preliminary experiments, and a prototype development for the two campuses for improving emergency preparedness for an active shooter event using collaborative immersive virtual reality (VR) environment. This project develops algorithms, implement software and demonstrate proof-of-concept using building systems as a challenge application area. This research involves devising novel conceptual methods for new theoretical and empirical guidance needed to have an environment for human and machine decision making for highly uncertain, complex, time urgent, and dynamically changing missions. The research objectives of this proposal include: 1) Develop an immersive Collaborative Virtual Environment (CVE) using Oculus for course of action, visualization, and situational awareness for active shooter events, 2) Develop a unique immersive graphical user interface (GUI) for communicating between PCs (Player characters) and NPCs (Non-Player Characters) for user interaction, 3) Implementing algorithms for human behavior for NPCs in active shooter events. (e.g. Hostile, Non-Hostile, Selfish, Leader-Following, Panic), 4) Deep learning-based (data-driven) behavioral modeling for realistic NPCs. The successfully implemented project contributes to the state-of-the-art in emergency response training using VR by developing knowledge that could form the basis of public education and awareness programs to help facility occupants, their rescuers and city officials respond appropriately during extreme emergency situation.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.