Jeff Huang

University of Illinois Urbana-Champaign, John Brown University

Papers

Total Citations

122

H-Index

About

Jeff Huang is a leading researcher in human-robot interaction and runtime verification, with a focus on making robotic systems more accessible and reliable. His work bridges the gap between technical robotics and everyday users, particularly through his pioneering research on leveraging implicit human feedback strategies. In his highly cited 2014 paper, "Learning something from nothing," Huang demonstrated how robots can learn behaviors from non-technical users by interpreting subtle, natural human cues rather than requiring explicit programming—a breakthrough that has shaped modern approaches to interactive robot training. His foundational paper "ROSRV: Runtime Verification for Robots" (97 citations) introduced critical methods for ensuring robot safety during operation, addressing a core challenge in deploying autonomous systems. Huang's contributions have been instrumental in advancing both the usability and dependability of robotic systems, with his work cited by researchers worldwide. His research continues to influence how we design robots that can learn from and safely interact with humans in real-world environments.