Lingwei Zhang

Papers

Total Citations

H-Index

About

Lingwei Zhang is a pioneering researcher at the intersection of robotics, control theory, and computer vision, whose work is reshaping how robots perceive and interact with the physical world. Their primary research areas span legged locomotion, model predictive control (MPC), and 3D object pose estimation. Zhang’s major contributions include developing an adaptive MPC framework that integrates data-driven error models to bridge the gap between simplified control models and real-world robot dynamics, significantly enhancing quadrupedal locomotion robustness. This work, published in 2024, has already garnered 6 citations for its practical impact on agile robot control. In computer vision, Zhang proposed DONet, a novel method for category-level 6D object pose and size estimation from single depth images, achieving state-of-the-art results without requiring pose-annotated real-world training data—a breakthrough that has also earned 6 citations. Additionally, Zhang introduced a fast online omnidirectional quadrupedal jumping framework combining virtual-model control with minimum jerk trajectory generation, enabling real-time, dynamic jumps with 3 citations. This work pushes the boundaries of robot agility. Zhang’s research is notable for its practical, real-world applicability, bridging theoretical control advances with deployable robotic systems, and their citation record reflects growing influence in both robotics and computer vision communities.