Stacy Patterson

Papers

Total Citations

H-Index

About

Stacy Patterson is a leading researcher at the intersection of robotics, signal processing, and machine learning, with a core focus on scalable tactile sensing. Her major contributions lie in pioneering the application of compressed sensing and compressed learning to robotic tactile skins. Recognizing that high-resolution tactile arrays are essential for safe human-robot interaction and dexterous manipulation, Patterson identified a critical bottleneck: the data deluge from thousands of sensing elements. Her work provides a theoretical and practical framework to compress tactile data directly during acquisition, potentially in-hardware, dramatically reducing bandwidth and power requirements without sacrificing classification accuracy. This breakthrough enables the creation of more scalable, high-resolution robotic skins. Her most-cited paper, "Compressed Learning for Tactile Object Recognition" (2018, 17 citations), establishes this foundational framework, demonstrating how to efficiently recognize objects from compressed tactile signals. Through this innovative work, Patterson is solving a key hardware-software co-design challenge, paving the way for robots that can perceive the world with a sense of touch approaching human capability.