Yikun Li

Papers

Total Citations

H-Index

About

Yikun Li is a robotics researcher whose work focuses on the intersection of deep learning and robotic manipulation, particularly in the challenging domain of grasp synthesis. His most cited paper, "Learning to Grasp 3D Objects using Deep Residual U-Nets" (2020, 13 citations), introduces a novel end-to-end 3D Convolutional Neural Network that predicts graspable areas on objects. By leveraging a deep residual U-Net architecture, Li’s approach enables robots to autonomously identify optimal grasping points on complex 3D objects, a critical capability for real-world object manipulation tasks. This contribution addresses a fundamental bottleneck in robotics—how to reliably and efficiently grasp unfamiliar objects—and has implications for industrial automation, assistive robotics, and logistics. While his citation count is still growing, Li’s work represents an important step toward more intelligent and adaptable robotic systems. His research is particularly valuable for students and engineers interested in bridging computer vision and robotics through deep learning, offering a practical framework for end-to-end learning in 3D space.