Accelerating Skill Acquisition in Complex Psychomotor Tasks via an Intelligent Extended Reality Tutoring System

点击翻译按钮获取中文摘要

Manufacturing, medical laboratory, construction, and many other jobs require workers to learn complex physical “psychomotor” tasks that combine both perceptual and motor skills. These are often taught using an apprenticeship model on real jobsites, which raises both productivity and safety risks for workers. Further, relatively little is known about how to assess trainees’ skill levels in these tasks and to adapt training practices based on those assessments. This project tackles these problems by developing a new generation of intelligent tutoring systems that combine extended reality (XR), artificial intelligence (AI) and Internet-of-things (IoT) technologies to support training and assessment of complex skills required by modern, highly automated manufacturing facilities. The high level idea is that new sources of data captured by XR headsets, wearable devices, cameras, and IoT sensors can be used to build models of psychomotor skill development and new methods for providing personalized, just-in-time coaching guidance. Through partnerships with manufacturing consulting firms, local community colleges, and K-12 schools, the project will enhance the skill development of a diverse population of learners and professionals and expand interest in advanced manufacturing careers. The project team brings together expertise in engineering, cognitive psychology, learning sciences, game design, and XR, to make fundamental contributions to both learning science and learning technologies around just-in-time, personalized, context-aware provision of learning scaffolds for manufacturing workers learning new skills. On the learning side, the project team will examine the stages of expertise development for specific psychomotor tasks, and the effectiveness of adaptive interventions on learners’ engagement, performance gains, and accuracy. A virtual reality (VR) game in an advanced manufacturing scenario will be used to collect ecologically valid baseline data and prepare more novice learners for real-world task performance. On the technology side, the project team will build and validate an intelligent XR tutoring system to accelerate the learning of psychomotor tasks with high complexity that arises from task structures and human information processing requirements. The innovative aspects of the technology include data-driven activity understanding (e.g., task step identification and error detection) and user modeling (e.g., cognitive load detection), through novel multimodal AI architectures designed to process and fuse data captured from augmented reality (AR) headsets, wearables that capture physiological data, cameras, IoT sensors, and manufacturing machines. Both learning and technology innovations will be validated through extensive laboratory studies; together, the work will lead to an intelligent feedback algorithm to dynamically adapt the nature, frequency, and depth of feedback to the expertise of the learner to facilitate optimal learning and speed-to-competence.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.