Lingzhu Xiang
Papers
9
Total Citations
153
H-Index
6
About
Lingzhu Xiang is a robotics researcher whose work spans legged and wheeled-legged locomotion, robot manipulation, autonomous navigation, and the application of machine learning to physical robotic systems. With a career trajectory moving from foundational sensing and mapping challenges to cutting-edge learned locomotion, Xiang has made notable contributions across the full robotics stack. Early work addressed practical sensing limitations, including the development of an ultra-tiny line laser range sensor, and tackled robust navigation through dynamic-environment graph SLAM solutions. Xiang's 2017 contribution to goal-directed manipulation through axiomatic scene estimation (35 citations) demonstrated a commitment to enabling robots to interpret and act upon high-level human intent. A major hardware milestone came with the design of Max, a wheeled-legged quadruped robot enabling multimodal agile locomotion (34 citations), showcasing strong mechatronics expertise. Most prominently, Xiang's research on applying reinforcement learning and generative pre-trained models to produce lifelike agility in quadrupedal robots has attracted significant attention, with the 2024 publication already accumulating 48 citations. Collectively, Xiang's portfolio reflects a researcher bridging classical robotics engineering with modern AI-driven control, advancing the frontier of agile, autonomous robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Goal-directed robot manipulation through axiomatic scene estimation35 citations · 2017
- 3Max: A Wheeled-Legged Quadruped Robot for Multimodal Agile Locomotion34 citations · 2023
- 4Robust graph SLAM in dynamic environments with moving landmarks12 citations · 2015
- 5Development of a low-cost ultra-tiny line laser range sensor9 citations · 2016
- 6
- 7
- 8
- 9