Zheming Fan
Papers
1
Total Citations
2
H-Index
1
About
Zheming Fan is a researcher at the forefront of robotic manipulation, specializing in the intersection of computer vision, 3D deep learning, and reinforcement learning. His work addresses the complex, real-world challenge of automated cable and wire handling—a critical bottleneck in manufacturing and logistics. Fan’s most cited study, "Untying cable by combining 3D deep neural network with deep reinforcement learning" (2022), introduces a pioneering three-stage framework that integrates SegNet for cable recognition, a 3D-VAE-GAN for voxel model reconstruction, and deep reinforcement learning for untangling actions. This work, with 2 citations, lays foundational groundwork for enabling robots to perceive and manipulate deformable, self-occluding objects—a notoriously difficult problem in robotics. By bridging 3D scene understanding with decision-making, Fan’s contributions promise to automate tedious manual tasks in factories and schools, advancing the frontier of intelligent robotic systems. His research is particularly notable for its practical focus on untethering robots from controlled environments, pushing toward more adaptive and autonomous industrial automation.
Research Focus
Key Achievements
Top Papers
- 1