NRI: INT: COLLAB: Interactive and collaborative robot-assisted emergency evacuations

许多紧急情况要求人们迅速撤离建筑物。在紧急情况下，撤离人员必须迅速做出决定，因此他们往往依赖于可能使他们处于危险中的默认决策，例如从进入的方式退出，跟随人群或在适当的地方躲避。当人群试图通过单一出口撤离时，阻塞点和人群拥堵可能会阻碍撤离人员的安全流动，可能导致人员踩踏和生命损失。越来越多的移动机器人被用作城市街道、酒店、购物中心和医院的助手。未来这些系统的普及为改变人们从危险环境中撤离的方式提供了机会。特别是，与传统的应急基础设施（如火灾报警器和烟雾探测器）相比，移动机器人可以实现更好的态势感知，并利用这些信息加快疏散和提高安全性。此外，移动机器人可用于危险和危及生命的情况，例如化学品泄漏或活跃枪手场景，这些情况对人类第一响应者构成危险。本项目旨在推导出一个可扩展的设计框架，并开发一个具体化的多机器人疏散系统，其中多个移动机器人最初的任务是不同的目的，作为紧急疏散的第一响应者，将人们带到安全的地方。特别是，多个移动机器人能够有效地相互协调，并积极地与疏散人员互动，最大限度地实现疏散。该项目极大地有助于理解人们对机器人的指示和权威命令的反应。此外，该项目实施了这些发现，并通过对人类受试者的真实实验证明了它们的有效性。除了紧急疏散之外，研究结果还可以扩展到许多其他相关领域，特别是涉及机器人团队的合作，这些团队体现在不确定和动态的物理世界中，需要与人类积极互动；例如，战场、执法、城市交通系统、制造系统、康复和健康管理。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。

Many emergencies require people to evacuate a building quickly. During an emergency, evacuees must make quick decisions, so they tend to rely on default decision making that may put them at risk, such as exiting the way they entered, following a crowd, or sheltering in place. When a crowd attempts to exit through a single exit, choke points and crowd congestion may impede the safe flow of evacuees, potentially resulting in a stampede of people and the loss of human lives. Mobile robots are increasingly being deployed as assistants on city streets and in hotels, shopping centers and hospitals. The future ubiquity of these systems offers an opportunity to change how people are evacuated from dangerous situations. In particular, when compared with traditional emergency infrastructure, such as fire alarms and smoke detectors, mobile robots can achieve better situation awareness and use this information to expedite evacuation and enhance safety. Additionally, mobile robots can be used in risky and life-threatening situations, such as chemical spills or active shooter scenarios, which present dangers to human first responders. This project aims to derive a scalable design framework and develop an embodied multi-robot evacuation system where multiple mobile robots, originally tasked for different purposes, serve as emergency evacuation first responders leading people to safety. In particular, multiple mobile robots efficiently coordinate with each other and actively interact with evacuees to maximize their egress. The project significantly contributes to the understanding of how people respond to a robots' directions and authoritative commands. Furthermore, the project implements these findings and demonstrates their effectiveness using real-world experiments with human subjects. Beyond emergency evacuation, the research findings can be extended to many other related areas, especially those involving cooperative robot teams that are embodied in an uncertain and dynamic physical world with the need to actively interact with humans; e.g., battlefield, law enforcement, urban transportation systems, manufacturing systems, rehabilitation and health management.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.