PFI:BIC: Smart Factories -An Intelligent Material Delivery System to Improve Human-Robot Workflow and Productivity in Assembly Manufacturing

PFI：BIC：智能工厂 - 智能物料输送系统，可改善装配制造中的人机工作流程和生产力

• 批准号: 1724982
• 负责人: Laurel Riek
• 金额: $ 100万
• 依托单位: University of California-San Diego
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-01-15 至 2020-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1724982&HistoricalAwards=false
• 关键词: PFI; BIC; Smart; Factories; Intelligent

Manufacturing represents a quarter of all employment in the US. To reshore jobs, improve operations, and recruit, retain, and retrain skilled workers, companies are increasingly using robotics technology. Ideally, robots will not replace humans but team with them to improve productivity. However, most industrial robots are poorly integrated into human workflow, causing expensive work stoppage problems ($1.7M per hour), worker stress, and talent loss. The research goal of this project is to address this problem by designing novel methods to improve human-robot workflow and productivity in assembly manufacturing through the use of an intelligent material delivery system (IMDS), which will closely integrate with and support the manual work process. This project will investigate innovative, multi-disciplinary approaches to this research area, dramatically advancing the state-of-the art in smart manufacturing and human-centered robotics. The research team will make the following contributions to human-centered smart service systems: 1) Revolutionize the use of robotics in assembly manufacturing processes to closely support skilled human workers, enabling them to focus on tasks they value (their trade) as opposed to tasks that distract from their talent (material movement). 2) Dramatically improve the productivity and flexibility of factories through nimble, real-time scheduling of an IMDS system that dynamically incorporates real-time models of human workflow. 3) Deeply explore the socio-technical implications of having an IMDS system in the workplace, in terms of human workers' cognition, fatigue, affect, and job satisfaction. The project's approach serves as a direct contrast to industry state-of-the-art, which relies on strict bifurcation of human and robot work, and rigid delivery schedules that fail to take local trim-line variations into account. By closely integrating an IMDS into the manual work process and understanding worker and material status, the project will readily enable flexibility and reconfigurability of a human workforce, an absolute necessity in made-to-order, small-batch manufacturing settings. This project will help the US manufacturing sector dramatically improve their operations by using automation to directly support a talented, skilled workforce. It has the potential to impact all major US manufacturing sectors, including automotive, construction, healthcare, energy, and goods. It will help US companies reshore operations, as well as create new opportunities for US worker STEM skill acquisition. Furthermore, this project involves a detailed investigation of multiple human worker implications of the transition from traditional to intelligent material delivery using robotics. By understanding reactions to such change, there will be new understanding on how to optimize a system not only for workflow and task efficiency but also for the human experience. Such knowledge is critical to maintaining job satisfaction, safety and health, and long-term well-being of the human workforce.The lead institution is the University of Notre Dame, Department of Computer Science and Engineering, in collaboration with the Massachusetts Institute of Technology, Department of Aerospace and Aeronautics (Cambridge, MA) and University of Colorado at Boulder, Department of Civil, Environmental, and Architectural Engineering (Boulder, CA). The primary industrial partner is Steelcase, Inc. (Grand Rapids, MI), a large manufacturer that specializes in customizable, made-to-order furniture.This proposal is co-funded by The Directorate for Computer and Information Science and Engineering (CISE), Divisions of Information and Intelligent Systems (IIS) and Computer and Network Systems (CNS)

制造业占美国就业总量的四分之一。为了回流工作岗位、改善运营以及招聘、保留和再培训技术工人，公司越来越多地使用机器人技术。理想情况下，机器人不会取代人类，而是与人类合作以提高生产力。然而，大多数工业机器人未能很好地融入人类工作流程，导致昂贵的停工问题（每小时 170 万美元）、工人压力和人才流失。 该项目的研究目标是通过设计新颖的方法来解决这个问题，通过使用智能材料输送系统（IMDS）来改善装配制造中的人机工作流程和生产力，该系统将与手工工作流程紧密结合并提供支持。该项目将研究该研究领域的创新、多学科方法，极大地推进智能制造和以人为中心的机器人技术的最先进水平。研究团队将为以人为本的智能服务系统做出以下贡献：1）彻底改变机器人在装配制造过程中的使用，以密切支持熟练的人类工人，使他们能够专注于他们重视的任务（他们的行业），而不是任务分散他们的才能（物质运动）。 2) 通过动态整合人工工作流实时模型的 IMDS 系统的灵活实时调度，显着提高工厂的生产力和灵活性。 3) 深入探讨在工作场所使用 IMDS 系统对人类工人的认知、疲劳、情感和工作满意度的社会技术影响。该项目的方法与行业最先进的方法形成了直接对比，最先进的行业依赖于人类和机器人工作的严格划分，以及严格的交付时间表，而没有考虑到当地的装饰线变化。通过将 IMDS 紧密集成到手工工作流程中并了解工人和物料状态，该项目将轻松实现劳动力的灵活性和可重新配置性，这在定制、小批量制造环境中是绝对必要的。该项目将通过利用自动化直接支持有才华、技术熟练的劳动力，帮助美国制造业大幅改善运营。它有可能影响美国所有主要制造业，包括汽车、建筑、医疗保健、能源和商品。它将帮助美国公司回流业务，并为美国工人获得 STEM 技能创造新的机会。此外，该项目还详细调查了从传统到使用机器人的智能材料交付的转变对多种人类工人的影响。通过了解对此类变化的反应，将对如何优化系统不仅针对工作流程和任务效率而且针对人类体验有新的理解。这些知识对于维持工作满意度、安全和健康以及劳动力的长期福祉至关重要。牵头机构是圣母大学计算机科学与工程系，与麻省理工学院合作、航空航天系（马萨诸塞州剑桥）和科罗拉多大学博尔德分校土木、环境和建筑工程系（加利福尼亚州博尔德）。主要工业合作伙伴是 Steelcase, Inc.（密歇根州大急流城），这是一家专门生产定制家具的大型制造商。该提案由计算机和信息科学与工程理事会 (CISE) 共同资助，信息和智能系统（IIS）和计算机和网络系统（CNS）部门

项目成果

Socially intelligent task and motion planning for human-robot interaction

用于人机交互的社交智能任务和运动规划

• 发表时间: 2019-01
• 期刊: and Systems (RSS
• 作者: Frank, A;Riek, L.D.
• 通讯作者: Riek, L.D.

Activity recognition in manufacturing: The roles of motion capture and sEMG+inertial wearables in detecting fine vs. gross motion

制造业中的活动识别：运动捕捉和表面肌电图惯性可穿戴设备在检测精细运动与粗大运动中的作用

• DOI: 10.1109/icra.2019.8793954
• 发表时间: 2019-05-01
• 期刊: 2019 International Conference on Robotics and Automation (ICRA)
• 作者: A. Kubota;T. Iqbal;J. Shah;L. Riek
• 通讯作者: L. Riek

Consider the Human Work Experience When Integrating Robotics in the Workplace

在工作场所集成机器人技术时考虑人类的工作体验

• DOI: 10.1109/hri.2019.8673139
• 发表时间: 2019-01
• 期刊: 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI
• 作者: Welfare, Katherine S.;Hallowell, Matthew R.;Shah, Julie A.;Riek, Laurel D.
• 通讯作者: Riek, Laurel D.

Trust-aware control in proximate human-robot teaming

近距离人机协作中的信任感知控制

• DOI: 10.1016/b978-0-12-819472-0.00015-0
• 发表时间: 2020-01
• 期刊: Trust in Human Robot Interaction
• 作者: Washburn, A;Matsumoto, S.;Riek, L. D.
• 通讯作者: Riek, L. D.

Wearable activity recognition for robust human-robot teaming in safety-critical environments via hybrid neural networks

通过混合神经网络在安全关键环境中进行可穿戴活动识别，实现强大的人机协作

• DOI: 10.1109/iros40897.2019.8968615
• 发表时间: 2019-11-01
• 期刊: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• 作者: Andrea E. Frank;A. Kubota;L. Riek
• 通讯作者: L. Riek