Collaborative Research: Personalized Systems for Wayfinding for First Responders

协作研究：为急救人员提供寻路的个性化系统

• 批准号: 1761950
• 负责人: Qi Wang
• 金额: $ 19.71万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-06-01 至 2021-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1761950&HistoricalAwards=false
• 关键词: Collaborative; Research; Personalized; Systems; Wayfinding

First responders face serious risks when responding to emergencies, and disorientation induced by complex building features is a major cause of injuries. In order to successfully navigate complex, dangerous buildings during a crisis, first responders need to build accurate spatial memories of unfamiliar spaces in a timely manner. This requires retention and processing of a large amount of information such as maps and verbal instructions. An apparent gap between the enormous information processing needs during a mission and the limited processing capacity of people creates a potentially fatal situation in emergency wayfinding. This project will contribute to the NSF's Big Idea "Harnessing Data for 21st Century Science and Engineering" by conducting fundamental research in information processing and engineering in the field of disaster management. This project will test the theoretical foundation of personalized wayfinding information systems that can effectively minimize the cognitive load of first responders on the individual level. This scientific research contribution thus supports NSF's mission to promote the progress of science and to advance our national welfare. In this case, the benefits will be insights to improve emergency response wayfinding, which will save lives and potentially reduce economic losses during disasters. This project has three interdependent scientific objectives. First, the research quantifies the structured relationship between spatial information and different forms of cognitive load in wayfinding tasks. Spatial information for wayfinding will be categorized and measured using semantic metrics; then a quantitative model of the relationship between spatial information and cognitive load will be examined. Second, the research explores cognitive resilience that helps identify and prevent an abrupt drop in wayfinding performance. Virtual Reality (VR) based multi-mission experiments are performed to examine the hypothetical nonlinearity of the relationship between cognitive load and wayfinding performance. Third, the research evaluates the effectiveness of personalized wayfinding information system in simulated mission tasks. A holistic VR experiment is performed to compare the new personalized system against the current universal spatial information systems. The outcome of the scientific investigation includes an adaptive wayfinding information system that dynamically tailors the way spatial information is presented based on the real-time cognitive load of individual first responders, measured by a set of neurobiological and physiological metrics. The project will immediately impact first responders primarily firefighters for their missions. A number of collaborative outreach activities are planned between two project sites: Texas A&M University and Northeastern University. These include advancing VR technologies for STEM education, integrating the research outcomes to curriculum development at both institutions, and developing a free online course and open-source project for general public access.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.

第一反应者在应对紧急情况时面临严重的风险，复杂的建筑特征导致的迷失方向是受伤的主要原因。为了在危机期间成功地导航复杂的危险建筑，第一响应者需要及时建立对不熟悉空间的准确空间记忆。这需要保留和处理大量信息，如地图和口头指示。使命期间巨大的信息处理需求与人的有限处理能力之间的明显差距在紧急寻路中产生了潜在的致命情况。该项目将通过在灾害管理领域进行信息处理和工程方面的基础研究，为NSF的“利用数据促进21世纪世纪科学和工程”的大构想做出贡献。该项目将测试个性化寻路信息系统的理论基础，该系统可以有效地最大限度地减少个人层面上的第一响应者的认知负荷。这一科学研究的贡献，从而支持NSF的使命，以促进科学的进步和提高我们的国家福利。在这种情况下，其好处将是改善应急响应寻路的见解，这将挽救生命，并可能减少灾害期间的经济损失。该项目有三个相互依存的科学目标。首先，本研究量化了寻路任务中空间信息与不同形式认知负荷之间的结构关系。空间信息的寻路将进行分类和测量使用语义指标，然后空间信息和认知负荷之间的关系的定量模型将被检查。其次，该研究探索了认知弹性，有助于识别和防止寻路表现的突然下降。基于虚拟现实（VR）的多任务实验，以检验假设的认知负荷和寻路性能之间的关系的非线性。第三，研究评估个性化寻路信息系统在模拟使命任务中的有效性。一个整体的VR实验进行比较新的个性化系统对当前的通用空间信息系统。科学调查的结果包括一个自适应寻路信息系统，该系统根据个体第一响应者的实时认知负荷（通过一组神经生物学和生理学指标测量）动态调整空间信息的呈现方式。该项目将立即影响第一反应者，主要是消防队员的任务。 计划在两个项目地点：德克萨斯农工大学和东北大学之间开展一些合作推广活动。其中包括推进STEM教育的VR技术，将研究成果整合到两所院校的课程开发中，以及开发免费的在线课程和开放源代码项目供公众访问。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

A CNN-based personalized system for attention detection in wayfinding tasks

• DOI: 10.1016/j.aei.2020.101180
• 发表时间: 2020-10
• 期刊: Adv. Eng. Informatics
• 作者: Yanchao Wang;Yangming Shi;E. Du;Yingzi Lin;Qi Wang

Personalize Wayfinding Information for Fire Responders based on Virtual Reality Training Data

基于虚拟现实训练数据为消防响应人员提供个性化寻路信息

• 发表时间: 2019
• 期刊: Proceedings of the 52nd Hawaii International Conference on System Sciences
• 作者: Jing Du, Qi Wang