The broader/commercial opportunity of this Small Business Technology Transfer (STTR) Phase I project is to address the emerging demand for intuitive human-machine interfaces. Interest in virtual and augmented reality (VR/AR) technologies has increased substantially, but current VR/AR interface algorithms are often inefficient and hamper many gesture-based interfaces, due to limitations in current machine learning algorithms. This limits the performance and widespread adoption of new VR/AR technologies. The technology developed here will enable intuitive interactions with VR/AR that will greatly expand the scope of commercial applications and shorten the development timelines for new products. This Small Business Technology Transfer (STTR) Phase I project will develop a prototype musculoskeletal technology for decoding movement from muscle activity. Traditional machine-learning-based gesture recognition approaches for virtual and augmented reality (VR/AR) interfaces cannot fulfill the demand for more natural and intuitive interactions, due to the reliance on only motion observation. Current gesture recognition technologies are often not generalizable to novel or perturbed movements. The goal of this project is to develop a backend technology for real-time and accurate decoding of intended arm and hand movement from muscle activity, which overcomes both of those limitations. This project will lead to a new tool for continuous real-time computer interface with multidimensional hand gestures or movements.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.
