Tianshuai Hu

Hong Kong University of Science and Technology

Papers

Total Citations

H-Index

About

Tianshuai Hu is a leading researcher in robotic perception and autonomous navigation, with a primary focus on multi-sensor fusion, simultaneous localization and mapping (SLAM), and dense semantic mapping. His most influential contribution is the **FusionPortable** benchmark (2022, 50 citations), a comprehensive multi-sensor dataset that provides diverse campus-scene sequences across multiple robotic platforms. This work directly addresses a critical challenge in robotics—enabling robots to maximize perceptual awareness by combining data from LiDAR, cameras, IMUs, and other sensors, thereby enhancing robustness to environmental disturbances. More recently, Hu introduced **DHP-Mapping** (2024), a dense panoptic mapping system that employs hierarchical world representation and label optimization techniques. This work allows robots to access both abstract and detailed geometric-semantic concepts from maps, a crucial capability for informed decision-making in interactive tasks. By bridging the gap between raw sensor data and actionable environmental understanding, Hu’s research is paving the way for more intelligent, context-aware autonomous systems capable of operating reliably in complex, real-world environments.