A Novel CPS System for Evaluating a Neural-Machine Interface for Artificial Legs (ACM)
This paper presents a novel cyber physical system (CPS) that senses signals from two physical systems -- a human neuromuscular control system and a mechanical prosthesis -- to drive a cyber virtual reality (VR) system for the purpose of evaluating a neural-machine interface (NMI) for artificial legs. Novel cyber techniques are proposed to tackle two fundamental challenges in this CPS system: inherent computation complexity for accurately identifying user‘s intended movements and real-time 3D rendering of a virtual avatar and environment on the cyber system. A neuromuscular-mechanical fusion algorithm is developed to decipher user intent. The decisions are then fed into the virtual reality cyber system to drive real-time motion of an avatar emulating exactly intended movements of the user. The algorithms for intent recognition and 3D VR rendering are specifically tailored to multi-core GPUs. The designed CPS system is tested on human subjects wearing prostheses. The results have shown that fusion of neuromuscular control and mechanical information improves the accuracy for user intent classification, compared to the interface based on either neuromuscular or mechanical information alone. Additionally, we find orders of magnitude speedup of GPUs over general purpose PCs, making the real-time application possible. Our prototype implementation demonstrates the feasibility of using neuromuscular-mechanical fusion to drive virtual reality in real time, which can be an effective evaluation and training tool for leg amputees to neurally control their artificial legs.
Paper available at ACM.