Papers
4
Total Citations
255
H-Index
3
About
Rih‐Teng Wu is a leading researcher at the intersection of artificial intelligence, structural health monitoring, and autonomous infrastructure inspection. His work focuses on developing deep learning and reinforcement learning methods to make post-disaster reconnaissance and condition assessment faster, safer, and more scalable. Wu’s most influential contribution is his 2020 paper on deep learning-based multi-class damage detection for autonomous post-disaster reconnaissance, which has garnered 146 citations and provides a critical framework for rapid, automated building damage assessment after earthquakes. He has also advanced the practical deployment of AI by pioneering techniques for pruning deep convolutional neural networks, enabling efficient edge computing for infrastructure condition assessment on resource-constrained devices like drones and robots. His 2019 paper on this topic has been cited 99 times. More recently, Wu has explored robotic inspection using deep reinforcement learning for autonomous crack segmentation and navigation. His work is pivotal in moving infrastructure monitoring from labor-intensive manual inspections to intelligent, autonomous systems that enhance resilience and reduce human risk.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4