Papers
7
Total Citations
122
H-Index
6
About
Peiyu Guan is a leading researcher in autonomous robotics, specializing in multi-sensor fusion, visual SLAM (simultaneous localization and mapping), and robotic manipulation. His work addresses critical challenges in robot perception and control, particularly for dynamic and complex environments. Guan’s most impactful contributions include the development of a Visual-Gyroscope-Wheel Odometry system that integrates ground plane constraints for robust indoor robot localization, achieving 25 citations. He also pioneered a real-time semantic visual SLAM approach combining points and objects (PO-SLAM), cited 24 times, which enhances both localization accuracy and environmental understanding. In person-following robotics, Guan proposed a robust visual approach using deep learning detectors and Kalman filters, earning 21 citations for its effectiveness in disturbing environments. His recent work on pixel-wise grasp detection via twin deconvolution and multi-dimensional attention (2023, 20 citations) advances robotic manipulation by addressing checkerboard artifacts in neural networks. Guan’s research consistently demonstrates high impact, with over 120 total citations across his top papers. Notably, his sparse geometric 3D LiDAR odometry approach (15 citations) and leader-following framework for quadruped robots (12 citations) showcase his versatility in tackling both wheeled and legged robotic systems. Guan’s work is essential reading for researchers in autonomous navigation, semantic perception, and robot-environment interaction.
Research Focus
Key Achievements
Top Papers
- 1
- 2A real-time semantic visual SLAM approach with points and objects24 citations · 2020
- 3
- 4
- 5A Novel Sparse Geometric 3-D LiDAR Odometry Approach15 citations · 2020
- 6
- 7