Guoxuan Chi

Beijing University of Posts and Telecommunications, Tsinghua University

Papers

Total Citations

H-Index

About

Guoxuan Chi is a researcher at the forefront of autonomous driving perception and intelligent robotics. His work bridges the gap between classical control theory and modern neuro-symbolic AI, with a primary focus on lane topology extraction and robot servo control. Chi’s most influential contribution is the development of **Chameleon**, a novel fast-slow neuro-symbolic framework for lane topology extraction in mapless autonomous driving. This system, which has already garnered 5 citations since its 2025 publication, addresses the complex reasoning challenge of determining lane relationships—such as whether a left turn is possible—by combining neural perception with symbolic logic. Earlier, Chi demonstrated his versatility in robotics with his 2018 study on **Fuzzy ARTMAP neural networks for robot vision servo systems**, a work that has accumulated 6 citations. This research tackled the difficulty of modeling visual servo systems mathematically by leveraging adaptive resonance theory and computer vision. Chi’s work is notable for its practical impact on real-world autonomous navigation, offering a path toward more interpretable and robust driving systems. His research continues to push the boundaries of how machines perceive and reason about complex environments.