SAI: Modeling Equitable and Accessible Public Spaces

SAI：公平且无障碍的公共空间建模

• 批准号: 2324598
• 负责人: Karin Stromswold
• 金额: $ 75万
• 依托单位: Rutgers University New Brunswick
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-15 至 2026-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2324598&HistoricalAwards=false
• 关键词: SAI; Modeling; Equitable; Accessible; Public

Strengthening American Infrastructure (SAI) is an NSF Program seeking to stimulate human-centered fundamental and potentially transformative research that strengthens America’s infrastructure. Effective infrastructure provides a strong foundation for socioeconomic vitality and broad quality of life improvement. Strong, reliable, and effective infrastructure spurs private-sector innovation, grows the economy, creates jobs, makes public-sector service provision more efficient, strengthens communities, promotes equal opportunity, protects the natural environment, enhances national security, and fuels American leadership. To achieve these goals requires expertise from across the science and engineering disciplines. SAI focuses on how knowledge of human reasoning and decision-making, governance, and social and cultural processes enables the building and maintenance of effective infrastructure that improves lives and society and builds on advances in technology and engineering.Substantial resources have been spent (re)designing America’s public transportation hubs to make them more accessible and easier to use, but people still find many transportation hubs hard to navigate. This is especially true for the one in four Americans who have mobility, sensory or cognitive impairments. Part of the difficulty stems from the failure to understand how social factors affect the way people with differing abilities interact with one another as they navigate different environments. Using virtual reality (VR) simulations of public transportation hubs, this project examines how people who have impairments or are temporarily encumbered navigate around physical objects and other people. It also considers how nondisabled people navigate around people who are disabled or encumbered, and how announcements and signs change the way diverse people travel through transportation hubs. These findings are used to create more realistic computer models of how people navigate crowded spaces, and to test what factors make public spaces more efficient and usable. Public transportation hubs are the primary focus because improving the usability of public transportation expands the educational, social, health and occupational opportunities that are available to all Americans. Improving the usability of public transportation hubs also helps to decrease America’s reliance on private transportation.This project is organized around three interlocking parts. One uses virtual reality (VR) to explore the navigational choices of people who have varying mobility and perceptual abilities. A second uses computational simulations of the navigational choices and flow of diverse people. The third part develops evaluation metrics for assessing the (re)design of real public spaces that take into consideration the variability in people and their navigational choices. A series of experiments on human wayfinding uses VR to embed human participants in simulated public transportation hubs. Unlike traditional navigation studies, these experiments focus on how human wayfinding is affected by the presence of other people. The VR experiments examine how people navigate environments that are populated by simulated others with varying mobility. They also consider how people respond when placed in situations that negatively impact their ability to navigate certain spaces, identify potential routes, or perceive instructions. The VR experiments also examine how those who use mobility aids navigate virtual environments that are populated with virtual people. This project aims to increase the usability of public spaces and transportation hubs for everyone, regardless of ability, thereby expanding educational, social, health and occupational opportunities for all.This award is supported by the Directorate for Social, Behavioral, and Economic (SBE) Sciences and the Directorate for Mathematical and Physical Sciences.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.

加强美国基础设施（SAI）是NSF的一项计划，旨在促进以人为本的基础和潜在的变革性研究，以加强美国的基础设施。有效的基础设施为社会经济活力和广泛改善生活质量奠定了坚实的基础。强大、可靠和有效的基础设施刺激私营部门创新，促进经济增长，创造就业机会，提高公共部门服务提供的效率，加强社区建设，促进机会平等，保护自然环境，增强国家安全，并推动美国的领导地位。为了实现这些目标，需要来自科学和工程学科的专业知识。SAI专注于人类推理和决策，治理以及社会和文化过程的知识如何使建设和维护有效的基础设施，改善生活和社会，并建立在技术和工程的进步上。大量的资源已经花费（重新）设计美国的公共交通枢纽，使其更容易获得和更容易使用，但是很多交通枢纽还是不好走。这对于四分之一的美国人来说尤其如此，他们有行动能力，感官或认知障碍。困难的部分原因在于无法理解社会因素如何影响具有不同能力的人在不同环境中相互作用的方式。 该项目使用虚拟现实（VR）模拟公共交通枢纽，研究有障碍或暂时受阻的人如何在物理对象和其他人周围导航。它还考虑了非残疾人如何在残疾人或障碍物周围导航，以及公告和标志如何改变不同人群通过交通枢纽的方式。这些发现被用于创建更真实的计算机模型，以了解人们如何在拥挤的空间中穿行，并测试哪些因素使公共空间更有效和可用。 公共交通枢纽是主要的焦点，因为改善公共交通的可用性扩大了所有美国人都可以获得的教育，社会，健康和职业机会。改善公共交通枢纽的可用性也有助于减少美国对私人交通的依赖。一种是使用虚拟现实（VR）来探索具有不同移动性和感知能力的人的导航选择。第二种方法是对不同人群的导航选择和流动进行计算机模拟。第三部分开发评估指标，以评估（重新）设计的真实的公共空间，考虑到人们的变化和他们的导航选择。一系列关于人类寻路的实验使用VR将人类参与者嵌入模拟的公共交通枢纽。与传统的导航研究不同，这些实验侧重于人类寻路如何受到其他人的影响。VR实验研究了人们如何在由具有不同移动性的模拟他人居住的环境中导航。他们还考虑了当人们处于对他们在某些空间中导航、识别潜在路线或感知指令的能力产生负面影响的情况下时，他们会如何反应。VR实验还研究了使用移动辅助设备的人如何在充满虚拟人的虚拟环境中导航。该项目旨在提高公共空间和交通枢纽对每个人的可用性，无论能力如何，从而扩大所有人的教育，社会，健康和职业机会。该奖项由社会，行为，经济（SBE）该奖项反映了NSF的法定使命，并被认为是值得支持的，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。

项目成果

The Importance of Multimodal Emotion Conditioning and Affect Consistency for Embodied Conversational Agents

• DOI: 10.1145/3581641.3584045
• 发表时间: 2023-03
• 期刊: Proceedings of the 28th International Conference on Intelligent User Interfaces
• 作者: Che-Jui Chang;Samuel S. Sohn;Sen Zhang;R. Jayashankar;Muhammad Usman;M. Kapadia

COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality

• DOI: 10.1007/978-3-031-19833-5_15
• 发表时间: 2021-12
• 作者: Honglu Zhou;Asim Kadav;Aviv Shamsian;Shijie Geng;Farley Lai;Long Zhao;Tingxi Liu;M. Kapadia

Harnessing Fourier Isovists and Geodesic Interaction for Long-Term Crowd Flow Prediction

利用傅里叶等量线和测地线相互作用进行长期人群流量预测

• DOI: 10.24963/ijcai.2022/185
• 发表时间: 2022
• 期刊: Thirty-First International Joint Conference on Artificial Intelligence (IJCAI
• 作者: Sohn, Samuel S.;Moon, Seonghyeon;Zhou, Honglu;Lee, Mihee;Yoon, Sejong;Pavlovic, Vladimir;Kapadia, Mubbasir
• 通讯作者: Kapadia, Mubbasir

Procedure-Aware Pretraining for Instructional Video Understanding

• DOI: 10.1109/cvpr52729.2023.01033
• 发表时间: 2023-03
• 期刊: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Honglu Zhou;Roberto Mart'in-Mart'in-Roberto-Mart'in-Mart'in-2196148773;M. Kapadia;S. Savarese;Juan Carlos Niebles

A Computational Method for the Classification of Mental Representations of Objects in 3D Space

3D 空间中物体心理表征分类的计算方法

• 发表时间: 2022
• 期刊: 15th International Conference on Spatial Information Theory (COSIT 2022
• 作者: Sam Sohn, Panagiotis Mavros