Convergence Accelerator Phase I (RAISE): Preparing the Future Workforce of Architecture, Engineering, and Construction for Robotic Automation Processes

融合加速器第一阶段 (RAISE)：为机器人自动化流程的未来架构、工程和施工人员做好准备

• 批准号: 1937019
• 负责人: Shahin Vassigh
• 金额: $ 97.33万
• 依托单位: Florida International University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-01 至 2021-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1937019&HistoricalAwards=false
• 关键词: Convergence; Accelerator; Phase; RAISE; Preparing

The NSF Convergence Accelerator supports team-based, multidisciplinary efforts that address challenges of national importance and show potential for deliverables in the near future. The broader impact/potential benefits of this Convergence Accelerator Phase I project will address a crucial national problem by preparing the nation's workers and businesses in the Architecture, Engineering, and Construction (AEC) industries for an increasingly automated future workplace. This convergent research and development project involves researchers in architecture, construction, engineering, computer science, STEM education and economic development, as well as industry collaborators from the robotics, architecture, engineering, construction and software industries. Its Phase 1 deliverables will benefit businesses, workers and professionals in the AEC industry cluster, as well as regional and national economic development policy. Phase 1 provides the platform for critical solutions: maximizing employment opportunity, minimizing job displacement, and improving national economic competitiveness in the AEC industries. Improving AEC industry performance also promises solutions leading to a more energy efficient and sustainable built environment.This Convergence Accelerator Phase I project will contribute to research and application of Artificial Intelligence (AI) and immersive virtual environments in education as well as examining economic impacts of automation technology adoption in the AEC industries. The rapid adoption of AI and automation promises new employment and business opportunities, but will also create job displacement and business disruption. The Project's Phase 1 research objectives are to develop 1) a prototype interactive virtual reality robotics training and educational software package, and 2) a new model to measure the economic impact of automation adoption. Phase 1 will provide a platform for an immersive virtual software to teach new skills, improve process workflows, and increase efficiency in the AEC industries. Integrating advanced technologies including Reinforcement Learning, Computer Vision, Augmented and Virtual Reality, the project will advance methods of remote and on-site training for a large segment of employees in the AEC industries. By applying STEM learning strategies, the project will contribute to understanding how people learn in technology rich environments and bridge the gap between technology advancement and application to practice. The Project's economic analysis will utilize a "bottom-up" approach to estimating the employment impacts resulting from the adoption of AI and robotics.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.

NSF融合加速器支持以团队为基础的多学科努力，以应对国家重要性的挑战，并在不久的将来展示可交付成果的潜力。 这个融合加速器第一阶段项目的更广泛的影响/潜在利益将通过为建筑，工程和建筑（AEC）行业的国家工人和企业做好准备，为日益自动化的未来工作场所解决一个关键的国家问题。这个融合的研究和开发项目涉及建筑，建筑，工程，计算机科学，STEM教育和经济发展的研究人员，以及来自机器人，建筑，工程，建筑和软件行业的行业合作者。其第一阶段的交付成果将使AEC产业集群中的企业、工人和专业人士以及区域和国家经济发展政策受益。 第一阶段为关键解决方案提供了平台：最大限度地增加就业机会，最大限度地减少失业，并提高AEC行业的国家经济竞争力。该融合加速器第一期项目将致力于人工智能（AI）和沉浸式虚拟环境在教育领域的研究和应用，以及研究自动化技术在AEC行业中的应用对经济的影响。人工智能和自动化的快速采用有望带来新的就业和商业机会，但也会造成就业岗位流失和业务中断。该项目第一阶段的研究目标是：1）开发一个交互式虚拟现实机器人培训和教育软件包的原型; 2）开发一个新的模型来衡量自动化采用的经济影响。第一阶段将为沉浸式虚拟软件提供一个平台，以教授新技能，改进流程工作流，并提高AEC行业的效率。该项目整合了强化学习、计算机视觉、增强现实和虚拟现实等先进技术，将为AEC行业的大部分员工提供远程和现场培训方法。通过应用STEM学习策略，该项目将有助于了解人们如何在技术丰富的环境中学习，并弥合技术进步与应用实践之间的差距。该项目的经济分析将采用“自下而上”的方法来估计人工智能和机器人技术的采用所带来的就业影响。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。

项目成果

Evolutionary Programming Based Deep Feature and Model Selection for Visual Data Classification

基于进化规划的视觉数据分类深度特征和模型选择

• DOI: 10.1109/mipr49039.2020.00020
• 发表时间: 2020
• 期刊: 2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR
• 作者: Tian, Haiman;Chen, Shu-Ching;Shyu, Mei-Ling
• 通讯作者: Shyu, Mei-Ling

Multi-task Multimodal Learning for Disaster Situation Assessment

• DOI: 10.1109/mipr49039.2020.00050
• 发表时间: 2020-08
• 期刊: 2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)
• 作者: Tianyi Wang;Yudong Tao;Shu‐Ching Chen;Mei-Ling Shyu

Work in Progress: Towards an Immersive Robotics Training for the Future of Architecture, Engineering, and Construction Workforce

正在进行的工作：为建筑、工程和建筑劳动力的未来提供沉浸式机器人培训

• DOI: 10.1109/edunine48860.2020.9149493
• 发表时间: 2020
• 期刊: World Conference on Engineering Education
• 作者: Bogosian, Biayna;Bobadilla, Leonardo;Alonso, Miguel;Elias, Albert;Perez, Giancarlo;Alhaffar, Hadi;Vassigh, Shahin
• 通讯作者: Vassigh, Shahin