Haijiang Zhu

Beijing University of Chemical Technology

Papers

Total Citations

H-Index

About

Haijiang Zhu is a researcher at the forefront of intelligent robotics and computer vision, with a focus on enabling autonomous systems to perceive and navigate complex environments. His work spans three critical areas: visual simultaneous localization and mapping (SLAM), small object detection in aerial imagery, and path planning for industrial inspection robots. In his 2021 study on visual SLAM, Zhu addressed the challenge of blurred image detection, proposing a robust method that enhances localization accuracy in degraded visual conditions—a foundational contribution for real-world robotic navigation. More recently, his 2024 work on V10Drone introduced an improved YOLOv10 architecture integrated with Kolmogorov-Arnold Networks (KAN) for small object detection in drone-captured images, tackling the persistent problem of detecting tiny targets in high-resolution aerial scenes. This lightweight, efficient model holds promise for both military and civilian drone applications. Zhu has also advanced industrial robotics through a 2023 paper on path planning for inspection robots in large storage tanks, where he developed a method to overcome local minima issues and produce smoother trajectories. With over a dozen citations across these key works, Zhu’s research is steadily building a reputation for practical, performance-driven solutions that bridge perception and motion planning.