Papers
15
Total Citations
465
H-Index
10
About
Xingxing Zuo is a robotics researcher specializing in state estimation, multi-sensor fusion, and 3D scene understanding, with a particular focus on enabling robust autonomous navigation across diverse platforms. His most influential contribution, LIC-Fusion 2.0 (162 citations), advances the fusion of LiDAR, inertial, and camera sensors through a sliding-window filter framework, delivering highly accurate 6DOF pose estimation for real-world robotic systems. Complementing this, his work on observability-aware LiDAR-IMU calibration (76 citations) introduced principled continuous-time batch-optimization methods to ensure reliable sensor intrinsic and extrinsic calibration — a foundational requirement for any multi-sensor system. Zuo has also made meaningful contributions to ground robot pose estimation, developing manifold-based optimization techniques for nonholonomic platforms (56 citations) and addressing the unique challenges of skid-steering robots. His research into online IMU intrinsic calibration rigorously examined when such calibration is truly necessary in visual-inertial systems. More recently, Zuo has expanded into neural scene representations, contributing to 3D Gaussian Splatting for holistic scene understanding. With over 440 cumulative citations, his work bridges rigorous probabilistic estimation theory with practical robotics deployment, making him a notable voice in mobile robotics and autonomous systems research.
Research Focus
Key Achievements
Top Papers
- 1
- 2Observability-Aware Intrinsic and Extrinsic Calibration of LiDAR-IMU Systems76 citations · 2022
- 3
- 4
- 5Online IMU Intrinsic Calibration: Is It Necessary?38 citations · 2020
- 6Visual-Inertial SLAM with Tightly-Coupled Dropout-Tolerant GPS Fusion20 citations · 2022
- 7
- 8
- 9Visual-Based Kinematics and Pose Estimation for Skid-Steering Robots11 citations · 2022
- 10Caltech Aerial RGB-Thermal Dataset in the Wild11 citations · 2024