Zhengjie Huang

Papers

Total Citations

H-Index

About

Zhengjie Huang is a robotics researcher whose work focuses on enabling robots to detect and recover from failures autonomously during real-world tasks. His key research areas include robot introspection, manipulation, and autonomous error recovery. Huang’s major contribution is the development of a novel framework for online robot introspection using wrench-based action grammars, which allows robots to monitor their own actions in real time and identify when something has gone wrong—without relying on external sensors or prior task models. This work, published in 2017 and cited over 20 times, addresses a critical gap in the sense-plan-act paradigm by introducing a feedback loop that checks action execution. By formalizing the relationship between force/torque signals and action outcomes, Huang’s research helps robots become more robust and adaptive in unstructured environments. His approach has significant implications for industrial automation, assistive robotics, and autonomous systems operating in unpredictable settings. Huang’s work stands out for its principled, data-driven methodology that bridges theory and practical deployment, making it a valuable reference for researchers working on robot autonomy and failure detection.