NSF Award
2433608
Manufacturing is undergoing a revolutionary change, with the rise of collaborative robots, or "cobots," becoming crucial in modern factory settings. Unlike traditional industrial robots that are isolated behind safety barriers, cobots are designed to work alongside humans in the same workspace. This harmonious blend of human intelligence (Mind), physical effort (Motor), and advanced robotics (Machine) necessitates new, innovative training methods to enhance worker safety, efficiency, and satisfaction. By leveraging machine learning, AI, and spatial computing, this EArly-concept Grants for Exploratory Research (EAGER) project aims to create a personalized training framework that adapts to each worker's cognitive functions and sensorimotor skills. The goal is to improve learning outcomes and job satisfaction through adaptive instructional methods, including novel synthetic actors like avatars. If successful, this research has the potential to revolutionize workforce training, addressing skill gaps in manufacturing while promoting inclusivity and accessibility with synthetic actors that can communicate across various cultures and demographics. The implications extend beyond manufacturing, potentially benefiting sectors like healthcare and education by enhancing safety, productivity, and economic growth.<br/><br/>This research focuses on advancing personalized training strategies for complex collaborative robotic manufacturing assembly tasks. An interdisciplinary framework is employed, integrating cognitive science, manufacturing, spatial computing, human factors, artificial intelligence, and advanced robotics to create an innovative, personalized learning paradigm. This paradigm is customized to each trainee's cognitive and sensorimotor capabilities, aiming to maximize the effectiveness of training transfer. The core challenge addressed is the accurate interpretation of physiological data and its translation into real-time training modifications with the help of machine learning algorithms. This effort emphasizes the importance of understanding the complex interplay between physiological data, sensorimotor interactions, and cognitive processes. The main research questions are: How can personalized training frameworks incorporating cognitive function, sensorimotor interaction, and machine learning improve the efficiency and effectiveness of workers in collaborative robotic manufacturing environments? What are the impacts of integrating synthetic actors and wearable physiological monitoring on cognitive workload and task performance in learning transfer for complex manufacturing tasks? How does real-time adaptive instruction driven by AI and biometric feedback influence human workers' safety, efficiency, and satisfaction in collaborative robotic training settings? The insights gained are expected to enhance training methodologies, ultimately fostering a more capable and adaptable workforce equipped to navigate the future of complex manufacturing environments.<br/><br/>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.
