Designing An Augmented Reality Based Interface For Wearable Exoskeletons

Abstract

Full-body, powered wearable exoskeletons combine the capabilities of machines and humans to maximize productivity. Powered exoskeletons can ease industrial workers in manipulating heavy loads in a manner that is difficult to automate. However, introduction of exoskeletons may result in unexpected work hazards, due to the mismatch between user-intended and executed actions thereby creating difficulties in sensing the physical operational envelope, need for increased clearance, and maneuverability limitations. To control such hazards, this paper presents a rearview human localization augmented reality (AR) platform to enhance spatial awareness of people behind the exoskeleton users. This platform leverages a computer vision algorithm called Monocular 3D Pedestrian Localization and Uncertainty Estimation (MonoLoco) for identifying humans and estimating their distance from a video camera feed and off-the-shelf AR goggles for visualizing the surrounding. Augmenting rear view awareness of humans can help exoskeleton users to avoid accidental collisions that can lead to severe injuries.