Guoxuan Zhang

About

Guoxuan Zhang is a roboticist whose research bridges the critical gap between perception and locomotion in autonomous systems. His work spans two complementary domains: the development of dynamic quadruped robots and the advancement of vision-based simultaneous localization and mapping (SLAM). His highly cited survey on quadruped robots (86 citations) provides a comprehensive roadmap for joint configuration, dynamic locomotion control, and mobile manipulation, highlighting their emerging roles in emergency response, military reconnaissance, and infrastructure inspection. In parallel, Zhang has made foundational contributions to monocular SLAM, particularly in corridor and indoor environments. His innovative use of vanishing points for loop closure—enabling absolute directional landmarks—and his vertical and floor line-based SLAM systems (26 and 25 citations, respectively) address the persistent challenge of place recognition in feature-sparse settings. Earlier work on anticipatory Bayes filters further demonstrates his interest in improving sensor models for robot localization. By integrating perceptual cues with robust control strategies, Zhang’s research continues to shape how robots navigate and interact with complex, real-world environments.

Research Focus

Key Achievements

Top Papers

1. 1
   A survey of the development of quadruped robots: Joint configuration, dynamic locomotion control method and mobile manipulation approach

   86 citations · 2021
2. 2
   Loop closure through vanishing points in a line-based monocular SLAM

   26 citations · 2012
3. 3
   A vertical and floor line-based monocular SLAM system for corridor environments

   25 citations · 2012
4. 4
   Loop Closure in a Line-based SLAM

   3 citations · 2012
5. 5
   Integration of a prediction mechanism with a sensor model: An anticipatory Bayes filter

   2 citations · 2009

Key Collaborators

Contact & Links