Shao-Hung Chan
National Taiwan University, University of Southern California
Papers
6
Total Citations
157
H-Index
5
About
Shao-Hung Chan is a leading researcher in multi-robot coordination and autonomous navigation, with a focus on fusing perception systems for robust indoor localization. His seminal 2018 paper on "Robust 2D Indoor Localization Through Laser SLAM and Visual SLAM Fusion" (98 citations) introduced a novel architecture that combines laser-based and monocular visual SLAM to achieve reliable positioning in challenging indoor environments—a foundational contribution to mobile robotics. Chan has since advanced the field through distributed deep reinforcement learning for visual navigation (27 citations), enabling robots to directly map complex scenes to motor commands. His recent work on multi-robot geometric task-and-motion planning (MR-GTAMP), published in 2022–2023, addresses collaborative manipulation tasks where multiple robots must coordinate to move objects in cluttered spaces, using mixed-integer programming to solve complex synchronization problems. Chan also developed the multi-layer environmental affordance map (10 citations), which integrates perception and inference for social-friendly navigation and event detection. His research consistently bridges theoretical planning algorithms with practical deployment, earning recognition for its impact on service robotics and multi-agent systems.
Research Focus
Key Achievements
Top Papers
- 1Robust 2D Indoor Localization Through Laser SLAM and Visual SLAM Fusion98 citations · 2018
- 2Distributed Deep Reinforcement Learning based Indoor Visual Navigation27 citations · 2018
- 3
- 4
- 5A MIP-Based Approach for Multi-Robot Geometric Task-and-Motion Planning8 citations · 2022
- 6