Tse-An Liu

Papers

Total Citations

H-Index

About

Tse-An Liu is a researcher advancing the robustness of autonomous robot navigation through innovations in visual-inertial SLAM (Simultaneous Localization and Mapping). His primary research focuses on integrating deep learning with inertial measurement data to overcome critical limitations in traditional visual SLAM systems, particularly in challenging environments plagued by image blur, illumination variation, and low-texture scenes. Liu's most impactful contribution is the development of InertialNet, an end-to-end network architecture that learns to fuse visual and inertial cues for more reliable camera orientation estimation and motion trajectory tracking. His foundational 2019 paper, "InertialNet: Toward Robust SLAM via Visual Inertial Measurement," has garnered 9 citations, establishing a new direction for resilient SLAM. He further refined this approach in his 2023 follow-up, demonstrating continued commitment to solving the robustness bottleneck that hinders real-world deployment of autonomous systems. By directly addressing the fragility of purely visual methods, Liu's work is paving the way for more dependable navigation in drones, mobile robots, and augmented reality platforms, making him a notable emerging voice in the field of robotic perception and sensor fusion.