Tingting Hu

University of Luxembourg, Beijing University of Posts and Telecommunications

Papers

Total Citations

H-Index

About

Tingting Hu’s research lies at the intersection of industrial sensor networks and deep learning for robotics, with a focus on enabling smarter, more autonomous systems. Her work on event notification in CAN-based sensor networks addresses a critical challenge in industrial automation: how to efficiently collect and transmit real-time data for preventive and reactive maintenance. By designing mechanisms that improve communication within complex, robotized environments, she has contributed to the foundational infrastructure of Industry 4.0. In parallel, Hu has advanced the field of visual relocalization, developing a deep learning system that integrates convolutional neural networks (CNNs) with long short-term memory (LSTM) networks to regress 6-DOF robot poses from video streams. Her end-to-end, transfer-learning approach allows robots to localize themselves with minimal supervision, a key capability for autonomous navigation in dynamic settings. While her citation counts (5 and 2, respectively) reflect the early-stage nature of this work, her contributions are notable for their practical orientation—bridging low-level network protocols with high-level AI—and for their potential to impact both industrial maintenance and robotic perception.