Papers
3
Total Citations
70
H-Index
2
About
Fang Hu is a researcher at the forefront of intelligent robotics, autonomous navigation, and IoT-driven health monitoring. Their most impactful contribution is the development of a novel path-planning framework that integrates Conflict-Based Search (CBS) with the D* Lite algorithm, enabling robots to navigate unknown, dynamic environments safely and efficiently—a work that has garnered 62 citations and is foundational for real-time autonomous systems. During the COVID-19 pandemic, Hu advanced non-contact health monitoring by proposing an IoT-based epidemic surveillance system using an improved Gated Recurrent Unit (GRU) model, which enhances the accuracy of human activity detection and minimizes risks for healthcare providers. More recently, Hu introduced SimCLR-Inception, a hybrid deep learning model for robot vision that combines contrastive representation learning with Inception architectures, achieving robust image recognition with only 2 citations to date but signaling promising directions for self-supervised visual perception. Hu’s work bridges theoretical algorithm design and practical deployment, with a clear focus on safety, adaptability, and real-world impact. Their research continues to shape the next generation of autonomous robots capable of operating in complex, human-centered environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2IoT-Based Epidemic Monitoring via Improved Gated Recurrent Unit Model6 citations · 2021
- 3