Zipeng Yang

Fudan University, Hebei University of Technology

Papers

Total Citations

H-Index

About

Zipeng Yang is a researcher at the forefront of robotic manipulation, specializing in the integration of deep reinforcement learning and multimodal sensing to advance autonomous grasping. His most impactful work, "Robotic Pushing and Grasping Knowledge Learning via Attention Deep Q-learning Network" (2020), has garnered 9 citations and introduces a novel attention-based deep Q-learning framework that enables robots to learn coordinated pushing and grasping strategies directly from visual input. This contribution addresses a critical challenge in unstructured environments, allowing robots to adaptively rearrange clutter for more reliable object acquisition. Yang further extends this line of inquiry with his 2025 design of an improved visual-tactile sensor for robotic grasping, demonstrating a commitment to fusing tactile feedback with vision to enhance dexterous manipulation. By pioneering attention mechanisms in reinforcement learning for robotic tasks, Yang has laid groundwork for more intelligent, sensor-rich systems. His work is particularly relevant for students and researchers exploring the intersection of computer vision, tactile sensing, and autonomous decision-making in robotics, offering practical insights into building robust, learning-driven grasping solutions.