ERI: An Emotion-Based Robotic Behavior Optimization System for Comfortable and Friendly Human-Robot Collaboration

该工程研究启动（ERI）奖将支持将贡献与制造中舒适和友好的人机协作相关的新知识的研究，促进机器人技术的发展进步和推进人机交互技术。制造业中的协作机器人与人类一起从事重复性和危险的任务，以提高效率和生产力。然而，目前机器人的僵硬和机械交互行为降低了协作过程的自然度和灵活性。长期与此类机器人一起工作将给人类工人带来巨大的压力。因此，改进协作机器人的交互行为是至关重要的。该奖项支持基础研究，为基于情感的机器人行为优化系统的开发提供所需的知识。其目的是将当前的协作机器人变成一个具有同理心和友好的工作伙伴，能够自适应地调整其交互行为，以促进舒适友好的协作过程。这项研究的结果可以通过将人类带回制造业自动化，进一步造福美国经济和社会。本计划的跨学科研究活动将有助扩大未获充分代表的团体参与工程研究，并对工程教育产生积极影响。为了实现人与机器人在制造中以人为本、舒适友好的协作，本项目将开发基于情感的机器人行为优化系统。该系统可以将当前的协作机器人转变为智能伙伴，不仅可以理解和响应人类的意图和情感，还可以自适应优化其行为，以促进制造任务的舒适友好协作。该项目将：(1)开发一种新的计算模型，使机器人能够理解人类的意图并测量人类的情绪；(2)开发一种交互系统，使协作机器人能够智能地响应人类的情绪并优化其行动，实现自然而灵活的人机协作；(3)进行真实世界的实验，以验证和评估所开发系统的有效性、效率和人类的接受程度。该奖项反映了美国国家科学基金会的法定使命，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。

This Engineering Research Initiation (ERI) award will support research that will contribute new knowledge related to comfortable and friendly human-robot collaboration in manufacturing, promoting the development progress of robotics and advancing human-robot interaction technologies. Collaborative robots in manufacturing work with humans on repetitive and dangerous tasks to improve efficiency and productivity. However, stiff and mechanical interaction behaviors of the current robots lower the naturalness and flexibility of the collaboration process. Prolonged exposure to working with such robots will cause significant stress among human workers. Therefore, it is crucial to improve the interaction behaviors of the collaborative robot. This award supports fundamental research to provide needed knowledge for the development of an emotion-based robotic behavior optimization system. It aims to turn the current collaborative robot into an empathetic and friendly working companion that can adaptively adjust its interaction behaviors for facilitating comfortable and friendly collaboration processes. Results from this research can further benefit the U.S. economy and society by bringing humans back to manufacturing automation. The interdisciplinary research activities in this project will help broaden the participation of underrepresented groups in engineering research and positively impact engineering education.To realize a human-centered, comfortable, and friendly collaboration between the human and the robot in manufacturing, this project will develop an emotion-based robotic behavior optimization system. The system can turn the current collaborative robot into a smart companion which can not only understand and respond to human intentions and emotions but also adaptively optimize its actions to facilitate comfortable and friendly collaboration in manufacturing tasks. This project will: (1) develop a new computational model to let the robot understand human intentions and measure human emotions, (2) develop an interaction system to enable the collaborative robot to intelligently respond to human emotions and optimize its actions for a natural and flexible human-robot collaboration, and (3) conduct real-world experiments to validate and assess the effectiveness, efficiency, and human acceptance of the developed system.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.