CCRI: Planning-C: Capturing and Logging Ecological Virtual Experiences and Reality (CLEVER)

人工智能（AI）、计算机视觉和机器学习在研究方面取得了进展，部分原因是大型数据集的创建和共享。这些类型的数据集不存在于虚拟现实（VR）研究社区。该规划补助金形成了创建大型VR相关数据集的框架。VR社区的专家将创建、捕获和共享这些所需的VR数据集。这些数据将包括头部、手部和眼睛跟踪数据。他们将在使用VR系统时收集有关用户行为和交互的信息。这些数据集将推动VR软件开发、技术和应用。这将使软件的进步，如在VR硬件消费者市场观察到的。这项规划拨款的主要目标是设计和创建一个大型VR数据集基础设施。该项目将解决虚拟现实研究中的一个重要空白。VR专家团队将帮助捕获多模态VR数据（例如，头部跟踪、眼睛注视）并建立该数据的共享。他们还将跟踪与VR系统的交互和行为。VR专家将在大多数VR应用程序（包括消费者应用程序）中管理标准化问卷。预计这将导致数据集的生态有效性。该项目计划捕获并发布一个大型数据集，以帮助形成供VR社区使用的框架。该项目将为研究人员提供一个开源工具包，以捕获他们自己的VR数据集。他们的目标是将他们的数据集贡献给VR研究社区。该项目的一个关键部分是组建一个由计算专家组成的咨询委员会，以指导VR研究方向。该项目将组织一个为期一天的研讨会，以吸引VR研究界的参与。这将有助于确定社区的需求和优先事项，以推进研究。本次研讨会的参与者将支持这一重要基础设施的发展。该奖项反映了NSF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。

Artificial intelligence (AI), computer vision, and machine learning have seen advances in research, driven in part by the creation and sharing of large datasets. These types of datasets do not exist for the virtual reality (VR) research communities. This planning grant forms a framework for the creation of large VR-related datasets. Experts in the VR community will create, capture, and share these needed VR datasets. This data will include head, hand, and eye tracking data. They will collect information on user behaviors and interactions while using VR systems. These datasets will advance VR software development, techniques, and applications. This will allow software advancements like observed in the VR hardware consumer markets.A primary goal of this planning grant is to design and create a large VR dataset infrastructure. This project will address an important gap in virtual reality research. A team of experts in VR will help capture multi-modal VR data (e.g., head tracking, eye gaze) and set up sharing of this data. They will also track interactions and behaviors with VR systems. VR experts will administer standardized questionnaires within most VR applications including consumer applications. It is expected that this will result in ecological validity of the datasets. The project plans to capture and publish a large dataset to help form the framework for use by the VR community. The project will provide an open-source toolkit for researchers to capture their own VR datasets. It is a goal that they will then contribute their datasets back to the VR research community. A key part of this project is to form an advisory board of computing experts to guide VR research directions. The project will organize a full-day workshop to engage the VR research community. This will help to identify community needs and priorities to advance research. The participants of this workshop will support the development of this important infrastructure.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.