Max Robotics — Global Service Robot Directory + US Certification

About

Fernando Quivira’s research sits at the intersection of neural engineering and assistive robotics, where he develops intelligent algorithms that decode human intent from brain and muscle signals. His major contributions center on creating robust, context-aware brain-computer interfaces (BCIs) and hybrid brain-machine interfaces (hBMIs) that fuse electroencephalographic (EEG) and electromyographic (EMG) data. In his most cited work, “Recursive Bayesian Coding for BCIs” (29 citations), he introduced a probabilistic framework to improve the accuracy of inferring task symbols from brain states—a critical step for real-world BCI control. He further advanced prosthetic control in “Muscle Synergy-based Grasp Classification for Robotic Hand Prosthetics” (24 citations), demonstrating that surface EMG-derived muscle synergies can reliably classify hand postures for daily activities. His 2018 paper on hierarchical graphical models (12 citations) pioneered a novel approach to context-aware hBMIs, enabling seamless fusion of neural and muscular signals during both executed and imagined movements. By combining Bayesian coding, muscle synergy analysis, and hierarchical modeling, Quivira has laid foundational work for more intuitive, adaptive assistive technologies—directly impacting the future of prosthetic control and neural rehabilitation.