NRI: FND: A Novel Intervention Method to Promote Workers' Safety Awareness and Mental Health During Human-Robot Collaboration

涉及人机协作的工作是美国制造业中越来越普遍的工作配置。由于协作机器人和工人在很近的地方执行任务，因此不能像过去那样将工人与协作机器人隔离以避免事故。到目前为止，多种工程方法，包括限制机器人速度和消除机器人上的尖锐特征，已经在工业协作机器人设计中实施，以提高工人的安全性。然而，人机协作的整体风险仍然是一个问题，因为人类工作人员与机器人队友合作的经验有限。该奖项支持基础研究，以提供开发干预方法所需的新知识，从而在人机协作期间促进工人的安全意识和心理健康。由于协作机器人市场预计将在未来十年迅速增长，这项研究的结果将有利于美国的工作场所安全，该研究涉及多个学科，包括职业安全，认知科学，计算机视觉，运筹学和生产自动化。这种多学科方法将有助于扩大代表性不足的群体在研究中的参与，并加强工程和安全教育。心理学证据表明，单调的人机协作任务可能导致安全意识下降。人机协作也会增加工人的心理健康风险，因为工人将合作机器人视为社会实体。本研究系统地调查了工人的情境意识和精神压力状态，以应对与合作机器人的互动。研究小组将研究解释视频图像的算法，使合作机器人能够识别工人的情境意识和精神压力，从而使合作机器人能够在不增加人类同事精神压力的情况下执行安全干预。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。

Work involving human-robot collaboration is an increasingly prevalent work configuration in U.S. manufacturing industries. Since co-robots and workers perform tasks in close proximity, it is not an option to isolate workers from co-robots to avoid accidents, as has been the practice in the past. To date, multiple engineering approaches, including limiting robot speed and eliminating sharp features on the robot, have been implemented in industrial co-robot design to promote the safety of workers. However, the overall risk in human-robot collaboration remains a concern because human workers have limited experience working with co-robot teammates. This award supports fundamental research to provide the new knowledge needed to develop intervention methods to promote the safety awareness and mental health of workers during human-robot collaborations. As the market for collaborative robots is expected to rapidly grow in the next decade, results from this research will benefit workplace safety in the U.S. The research involves multiple disciplines, including occupational safety, cognitive science, computer vision, operations research, and production automation. This multidisciplinary approach will help broaden participation of underrepresented groups in research and strengthen engineering and safety education.Psychological evidence has revealed that monotonous human-robot collaboration tasks can lead to decreased safety awareness. Human-robot collaboration can also increase workers’ greater mental health risks, as workers treat co-robots as social entities. This research systematically investigates workers' situational awareness and mental stress states in response to interactions with co-robots. The research team will investigate algorithms that interpret video images to enable co-robots to recognize workers' situational awareness and mental stress, thereby enabling the co-robot to perform safety interventions without increasing the mental stress of their human coworkers. Experiments with co-robots will be conducted to evaluate the performance and implementation feasibility of the safety intervention methods.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.