Papers
45
Total Citations
1,246
H-Index
18
About
Guoquan Huang is a leading robotics researcher whose work sits at the intersection of state estimation, simultaneous localization and mapping (SLAM), and multi-sensor fusion. Based at the University of Delaware, Huang has made foundational contributions to visual-inertial navigation, LiDAR-inertial-camera odometry, and cooperative multi-robot localization. His LIC-Fusion 2.0 framework (162 citations) exemplifies his expertise in tightly integrating heterogeneous sensor modalities — cameras, IMUs, and LiDARs — to achieve robust 6DOF pose estimation for real-world robotic platforms. His influential work on observability-consistent EKF estimators has advanced theoretically principled approaches to multi-robot cooperative localization, while his MIMC-VINS system demonstrates resilient navigation across diverse sensor configurations. Huang has also pushed the boundaries of deep learning for robotics, proposing an unsupervised architecture for loop closure detection (146 citations) that balances reliability and computational efficiency. His research on graph-based SLAM sparsification, LiDAR-IMU calibration, and IMU intrinsic self-calibration further reflects a commitment to making autonomous navigation systems both scalable and practically deployable. Collectively, his body of work has garnered hundreds of citations, cementing his reputation as a pivotal figure in modern robot perception and navigation research.
Research Focus
Key Achievements
Top Papers
- 1
- 2Lightweight Unsupervised Deep Loop Closure146 citations · 2018
- 3
- 4Communication-constrained multi-AUV cooperative SLAM108 citations · 2015
- 5
- 6Observability-Aware Intrinsic and Extrinsic Calibration of LiDAR-IMU Systems76 citations · 2022
- 7A Linear-Complexity EKF for Visual-Inertial Navigation with Loop Closures39 citations · 2019
- 8
- 9Online IMU Intrinsic Calibration: Is It Necessary?38 citations · 2020
- 10An Online Sparsity-Cognizant Loop-Closure Algorithm for Visual Navigation32 citations · 2014