Yihe Chang
Papers
1
Total Citations
8
H-Index
1
About
Yihe Chang is a rising researcher in the intersection of robotics, computer vision, and deep reinforcement learning. Their work focuses on developing autonomous systems for infrastructure inspection, particularly in the challenging domain of crack detection and segmentation. Chang’s most-cited paper, “Robotic inspection for autonomous crack segmentation and exploration using deep reinforcement learning” (2025, 8 citations), introduces a novel framework that integrates deep reinforcement learning with robotic control to enable autonomous navigation and precise crack identification in real-world environments. This contribution addresses a critical bottleneck in civil infrastructure maintenance—moving beyond static image analysis to dynamic, adaptive inspection strategies. By training robots to explore and segment cracks without human intervention, Chang’s research promises to reduce inspection costs and improve safety in hazardous settings. Though early in their career, the work has already garnered attention for its practical implications in smart infrastructure and autonomous robotics. Chang’s interdisciplinary approach, merging reinforcement learning with robotic perception, positions them as a key innovator in the next generation of intelligent inspection systems.
Research Focus
Key Achievements
Top Papers
- 1