Lingxiao Zheng
Papers
1
Total Citations
3
H-Index
1
About
Lingxiao Zheng is a researcher focused on advancing state estimation and perception for autonomous systems, with particular expertise in visual-inertial odometry (VIO) and probabilistic robotics. Their most notable contribution, "Information sparsification for visual-inertial odometry by manipulating Bayes tree" (2021), introduces a novel method to reduce computational complexity in VIO by selectively pruning redundant information from the Bayes tree—a key structure in factor graph-based SLAM. This work, which has garnered 3 citations, addresses a critical bottleneck in real-time navigation for drones, augmented reality, and mobile robots, enabling more efficient long-duration operation without sacrificing accuracy. Zheng’s approach stands out for its theoretical elegance in balancing sparsity and estimation consistency, offering a practical solution for resource-constrained platforms. While early in their career, Zheng’s research signals a strong commitment to bridging algorithmic efficiency and real-world deployment, making them a promising voice in the robotics and computer vision communities. Their work is particularly relevant for students and researchers exploring scalable SLAM and sensor fusion techniques.
Research Focus
Key Achievements
Top Papers
- 1