Yijia He

University of Chinese Academy of Sciences, Institute of Automation

Papers

Total Citations

H-Index

About

Yijia He is a robotics researcher specializing in sensor fusion, visual SLAM (Simultaneous Localization and Mapping), and autonomous navigation for ground robots. His work addresses fundamental challenges in mobile robot localization, particularly the limitations of monocular visual odometry, which suffers from scale ambiguity and failure under changing lighting conditions. He’s most notable contribution is a novel camera-odometer calibration and fusion framework using graph-based optimization (2017, 16 citations), which integrates wheel encoder data with visual information to provide metric-scale, robust localization. This approach significantly improves accuracy in indoor environments where pure vision-based methods struggle. He further advanced visual SLAM by developing a monocular system that leverages both points and lines, with a specialized parameterization for ground features (2021, 10 citations), enhancing performance in structured indoor scenes. His earlier work on pedestrian localization within distributed vision systems (2016) tackled the challenge of dynamic obstacle avoidance for global path planning. With a cumulative citation count exceeding 28, He’s research has practical implications for service robots, autonomous ground vehicles, and industrial automation, offering reliable solutions for real-world deployment in complex, human-populated environments.