FW-HTF-R: Collaborative Research: Worker-AI Teaming to Enable ADHD Workforce Participation in the Construction Industry of the Future

FW-HTF-R：协作研究：工人与人工智能团队合作，使多动症劳动力参与未来的建筑行业

• 批准号: 2128867
• 负责人: Behzad Esmaeili
• 金额: $ 120万
• 依托单位: George Mason University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2023-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2128867&HistoricalAwards=false
• 关键词: FW; HTF; Collaborative; Research; Worker

While people with neurodiversity have been marginalized in the construction workplace due to potentially higher risks of injuries, their unique talents could be leveraged using an ecosystem of co-bots driven by artificial intelligence (AI). For humans and machines to become true teammates—and correlatively, for technology to extend occupational opportunities to people with such neurodiversity—intelligent machines must assess, adapt, and respond to both workers and their environment. Such agility requires a reciprocal teaming capability wherein workers can engage their AI counterparts as more than tools, and AI systems can collaborate with workers seamlessly by predicting their behaviors. To extend future occupational opportunities for people with neurodiversity, this project builds an AI-driven learning platform to enable distribution of AI teammates in construction workplaces to support employment opportunities and safety outcomes for construction workers with varying abilities. This study also investigates the intended work scenarios of worker-AI teaming, the unintended consequences of AI-teaming for workers, and the well-being of society. Considering that 4.2% of workers are diagnosed with attention-deficit/hyperactivity disorder (ADHD)—a disorder that is associated with more than 120 million lost workdays in the USA each year, equating to a human capital value of $19.5 billion—this project’s efforts to enable diverse workforce participation in the construction industry will have positive social and economic impacts. Additionally, this project will educate a new generation of leaders in worker-AI teaming and will create partnerships between academia and industry.To lay the necessary foundations for building this human-AI teaming workspace for construction workers with neurodiversity, this proof-of-concept project will translate non‐invasive biomechanical and neuro-psychophysiological responses into information a personalized AI-based training systems can assess, model, and leverage to predict workers’ behaviors for improved worker‐machine teaming without cultivating technological over-reliance or threats to privacy. In this project, a multidisciplinary team of researchers integrates expertise in civil engineering, computer science, cognitive and behavioral psychology, industrial engineering, and public policy and economics to address fundamental questions regarding the risk taking behavior and cognitive processes of workers with ADHD, barriers to adopting AI and wearable technologies, and the socioeconomic impacts of improved access to construction jobs for ADHD-diagnosed workers, especially in the context of interdependent human-AI partnerships. As this project’s global paradigm moves toward deeper human-machine teaming, the knowledge gained through this project advances the science and technology that influences diverse workforce development, education, and positive work outcomes for workers and society at large. By demonstrating the effectiveness of this AI-driven platform, this project illustrates how human-machine teams can progress on job sites and within communities across all sectors to augment human cognitive capabilities.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.

尽管由于潜在的受伤风险较高，具有神经多样性的人在建筑工作场所中被剥夺了，但他们独特的才能可以通过人工智能 (AI) 驱动的协作机器人生态系统得到利用，让人类和机器成为真正的队友。相应地，为了让技术能够为具有这种神经多样性的人提供就业机会，智能机器必须评估、适应和响应工人及其环境，这种敏捷性需要工人能够与他们的人工智能伙伴合作。工具和人工智能系统可以通过预测工人的行为来与工人无缝协作，为了扩大具有神经多样性的人未来的职业机会，该项目构建了一个人工智能驱动的学习平台，使人工智能团队成员能够在建筑工作场所进行分配，以支持就业机会和安全结果。考虑到 4.2% 的工人被诊断为患有不同能力的建筑工人，这项研究还调查了工人与人工智能团队的预期工作场景、人工智能团队对工人的意外后果以及社会福祉。注意力缺陷/多动障碍 (ADHD)——一种在美国每年导致超过 1.2 亿个工作日损失的疾病，相当于 195 亿美元的人力资本价值——该项目致力于让多元化的劳动力参与建筑行业此外，该项目还将培养新一代工人-人工智能团队的领导者，并在学术界和工业界之间建立伙伴关系。为建立这种人类-人工智能团队奠定必要的基础。该概念验证项目将为具有神经多样性的建筑工人提供工作空间，将非侵入性生物力学和神经心理生理反应转化为基于人工智能的个性化培训系统可以评估、建模和利用的信息，以预测工人的行为，从而改善工人的行为。在这个项目中，一个多学科研究团队整合了土木工程、计算机科学、认知和行为心理学、工业工程以及公共政策和经济学方面的专业知识，以解决基本问题。关于患有多动症的工人的冒险行为和认知过程、采用人工智能和可穿戴技术的障碍，以及改善多动症诊断工人获得建筑工作的机会的社会经济影响，特别是在相互依赖的人类与人工智能伙伴关系的背景下。该项目的全球范例转向更深入的人机团队，通过该项目获得的知识通过展示这种人工智能驱动的有效性，推动了影响多元化劳动力发展、教育和积极工作成果的科学技术。平台，该项目说明了如何人机团队可以在工作现场和各个部门的社区内取得进步，以增强人类的认知能力。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

Synthesizing Personalized Construction Safety Training Scenarios for VR Training

综合个性化施工安全培训场景进行VR培训

• DOI: 10.1109/tvcg.2022.3150510
• 发表时间: 2022
• 期刊: IEEE Transactions on Visualization and Computer Graphics
• 影响因子: 5.2
• 作者: Li, Wanwan;Huang, Haikun;Solomon, Tomay;Esmaeili, Behzad;Yu, Lap-Fai
• 通讯作者: Yu, Lap-Fai