Papers
2
Total Citations
16
H-Index
2
About
Kunhua Liu’s research bridges the frontiers of rehabilitation robotics and computer vision, with a focus on enhancing human-machine interaction and visual data integrity. In a pivotal 2019 study, Liu investigated the dynamic stability of lower limb exoskeleton robots during stair climbing, using a human motion capture system to reconstruct 3D postures. This work, which has garnered 13 citations, directly addresses a critical challenge in assistive robotics: maintaining system stability as the center of gravity shifts during complex movements, offering foundational insights for safer, more responsive rehabilitation devices. More recently, Liu introduced Edge-guided GAN, a novel deep learning approach for depth image inpainting that leverages edge information from Canny detection to fill large missing regions—a task where traditional color-guided or single-depth methods often fail. Although published in 2021 and currently with 3 citations, this work demonstrates a creative synthesis of generative adversarial networks and geometric priors, promising advances in autonomous navigation and 3D scene understanding. By tackling both the physical stability of assistive robots and the visual completeness of depth sensors, Liu’s research exemplifies a dual commitment to practical rehabilitation engineering and robust perception systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2