Use of Eye-Tracking to Detect Variations in Mental Workload While Learning to Operate a Physically-Coupled Robot
Event Type
TimeWednesday, October 6th5:00pm - 6:00pm EDT
LocationHarborside CDE
DescriptionCollaborative robots are becoming more usable, versatile, and even becoming operable in close proximity with humans in a variety of industrial settings. However, the mental workload and motor-skill learning associated with operating these devices needs to be understood. We are presenting our in-progress work aimed at investigating the sensitivity of eye-tracking as a potential measure of work-load over the course of learning to use a physically-coupled robot for an object-manipulation task. Our hypothesis is that pupil diameter and blink rate will be elevated, and eye-hand span and target-locking score will be reduced, during initial practice of difficult task conditions. This work is also expected to help identify which eye-tracking measures can best characterize individual rates of adaptation to novel motor tasks. In the long term, this work can facilitate the development of adaptive-learning algorithms that modulate task difficulty to maintain a learner in an optimal state of workload and motor-learning.