Brayden Hollis

Papers

Total Citations

H-Index

About

Brayden Hollis is a researcher at the forefront of robotic tactile perception, specializing in the intersection of compressed sensing and machine learning for scalable tactile sensing. His major contributions center on developing a novel framework that applies compressed learning principles to tactile object recognition and classification, enabling high-resolution robotic skins to efficiently process touch data. By compressing tactile data during acquisition—potentially directly in hardware—Hollis’s work addresses the critical challenge of managing the vast data streams from large tactile arrays, which are essential for safe human-robot interaction and dexterous manipulation. His most-cited paper, "Compressed Learning for Tactile Object Recognition" (2018, 17 citations), demonstrates the practical application of this framework, while his earlier works from 2016 and 2017 lay the theoretical groundwork for scalable tactile skins. Hollis’s research is pivotal in advancing robot perception, offering a path toward more responsive and intelligent robotic systems capable of operating seamlessly in human-dominated environments. His achievements highlight a commitment to solving fundamental engineering bottlenecks, making him a notable figure in the field of robotic sensing.