HCC: Small: Cyber-Enabled Analysis and Control of Building Evacuation

本项目将：(1)建立一个实验装置，在3D虚拟在线社区内进行疏散实验。(2)分析实验设置的现实性，研究改进方法。(3)研究在紧急情况下使用智能标志来控制人们的行为。建筑、体育场馆和城市街区设计的一个主要方面是疏散的适宜性。人们的生命取决于这些建筑物在火灾、地震、恐怖袭击和建筑物倒塌等紧急情况下的疏散速度。然而，由于9/11恐怖袭击，很明显，目前针对各种建筑类型（如高层建筑、机场和体育场馆）的紧急疏散的建筑设计方法需要重新审视。特别是，必须根据疏散程序仔细评估设计。这引起了人们对缺乏工具的关注，这些工具可以在设计的环境中对现实的人类运动和互动进行强有力的预测。在成千上万的人在每一种可能的紧急情况下疏散每一种可能的建筑设计的情况下进行现场实验显然是不切实际的。这项研究不仅将评估虚拟世界信息技术作为建筑设计工具，以方便疏散，而且还将开发新的信息技术，可纳入现实世界的建筑。例如，在紧急情况下，智能出口标志可以根据已知的建筑信息、紧急情况的类型和位置以及当前人员的分布情况，自动引导人们。在三维虚拟在线社区中建立疏散实验的实验设置，需要回答一些非常规的问题，如如何吸引研究对象参与实验，如何在发生紧急情况时激励参与者疏散建筑物，以及应该建立什么样的设置来尽可能真实地评估疏散效率。分析和改进设置的真实感需要研究火灾等自然效果的真实感模拟、数百个人物的实时逼真人体动作合成以及开发有效的测量参与者沉浸感的手段。最后，智能标识的控制策略设计需要研究适合大规模多智能体系统控制的不确定性下的实时决策规划算法。建筑物的安全对任何社会都是至关重要的。自然灾害、恐怖袭击和火灾事故每年造成成千上万人丧生。通过设计更容易疏散的建筑，工程师可以挽救这些生命的很大一部分。然而，缺乏工具可以让工程师在疏散效率方面对建筑设计进行高保真度评估。这项研究旨在为工程师提供以比以前低得多的费用进行大规模高保真实验的途径。这方面的进展也将对教育产生积极影响。该项目将在本科数字媒体设计课程中发挥重要作用，该课程约有50%的女学生。

This project will: (1) Build an experimental setup for conducting evacuation experiments inside 3D virtual online communities. (2) Analyze the realism of the experimental setup and research the ways to improve it. (3) Investigate the use of intelligent signs for controlling peoples' behavior in emergency situations. One of the major aspects in the design of buildings, stadiums and city blocks is their suitability for evacuation. Peoples' lives depend on how quickly these constructions can be evacuated in the emergency situations such as fires, earthquakes, terrorist attacks and collapsing structures. As a result of the 9/11 terrorist attacks however, it became apparent that current approaches to building design in regard to emergency evacuation for various building typologies such as high-rises, airports and stadiums need to be re-examined. In particular, the designs must be carefully evaluated against evacuation procedures. This raised a major concern about the lack of tools that would allow robust predictions of realistic human movements and interaction in the designed environments. It is clearly impractical to establish live experiments with thousands of people evacuating every possible building design for every possible emergency condition. The research will not only evaluate virtual-world information technology as a tool for building design to facilitate evacuation, but it will also develop new information technology that could be incorporated in real-world buildings. For example, intelligent exit signs could automatically direct people during emergencies based on the known information about the construction, the type and location of emergency, and the current distribution of people. Building an experimental setup for conducting evacuation experiments within 3D virtual online communities requires answering such unorthodox questions as how to attract research subjects to the experiments, how to motivate the participants to evacuate buildings when emergency occurs, and what setup should be made to evaluate the efficiency of evacuation as truthfully as possible. The analysis and improvement of the realism of the setup requires research in realistic simulation of natural effects such as fire, real-time realistic human motion synthesis for hundreds of characters and developing effective means of measuring the immersiveness of participants. Finally, the design of control strategies for intelligent signs requires the research of real-time decision-theoretic planning under uncertainty algorithms suitable for the control of massive multi-agent systems. The safety of buildings is of critical importance to any society. Natural hazards, terrorist attacks and fire accidents cause losses of thousands of lives every year. By designing buildings that are easier to evacuate, engineers can save a significant fraction of these lives. Yet, there is a lack of tools that would allow engineers to conduct high-fidelity evaluations of building designs in terms of evacuation efficiency. This research is directed towards providing engineers with access to conducting such large-scale high-fidelity experiments at drastically lower expense than previously possible. Progress in this direction will also have positive educational impacts. The project will play a significant part in the classes offered in an undergraduate Digital Media Design program, which has about 50% female students.