Qingfeng Li

Papers

Total Citations

H-Index

About

Qingfeng Li is a researcher advancing the intersection of computer vision and robotics, with key contributions in affordance detection, 3D pose estimation, and robotic grasping. His work focuses on enabling robots to perceive and interact with complex environments more effectively. In his 2022 paper on affordance detection, Li introduced a multi-scale fusion and global semantic encoding framework that improves how robots identify interaction possibilities with objects, achieving 7 citations. He also developed an edge computing-based system for 3D pose estimation and calibration of robot arms (2020, 7 citations), addressing real-time processing challenges in industrial settings, particularly during the COVID-19 pandemic. Additionally, his 2021 work on object pose estimation for robotic grasping uses multi-view keypoint detection to handle cluttered and occluded objects (6 citations), a critical advancement for manufacturing automation. Li’s research directly tackles practical bottlenecks in Industry 4.0, from slow detection speeds to calibration accuracy, making his work valuable for both academic study and industrial application. His contributions are shaping the future of intelligent robotic systems.