Papers
2
Total Citations
69
H-Index
2
About
Chengbo He is a researcher at the forefront of intelligent infrastructure and advanced robotics control. His work bridges computer vision and automation, with key contributions in two distinct areas: automated pavement distress detection and robust robotic manipulation. In his highly cited 2022 study, He optimized the YOLOv5s deep learning model for the automatic identification of road cracks and potholes—a critical task for preventing structural damage and traffic accidents. This work, garnering 51 citations, addresses the challenge of detecting diverse distress types under complex real-world conditions. Simultaneously, He tackles the precision control of robotic systems. His 2023 paper introduces a Non-Singular Terminal Sliding Mode Controller paired with a Nonlinear Disturbance Observer (NDO–NTSMC) for n-degree-of-freedom manipulators. This method, with 18 citations, significantly enhances trajectory tracking accuracy by mitigating model uncertainties and external interference. By advancing both the safety of transportation networks and the reliability of automated machinery, He demonstrates a versatile impact, making his research essential reading for engineers developing smarter, more resilient autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1A pavement distresses identification method optimized for YOLOv5s51 citations · 2022
- 2