Shishun Zhang

National University of Defense Technology

Papers

Total Citations

H-Index

About

Shishun Zhang is a researcher at the forefront of dexterous manipulation and robotic learning, with a focus on enabling high-degree-of-freedom (high-DOF) robotic hands to perform complex reaching and grasping tasks. His most cited work, "Learning Cross-Hand Policies of High-DOF Reaching and Grasping" (2024), introduces a novel framework that allows policies trained on one robotic hand to transfer seamlessly to another, dramatically reducing the need for hand-specific retraining. This contribution addresses a critical bottleneck in robotic dexterity—generalization across different hardware—and has already garnered attention for its potential to accelerate real-world deployment. While his citation count is still growing, Zhang’s research stands out for its emphasis on cross-hand policy learning, a niche that promises to make robotic manipulation more adaptable and scalable. His work is particularly valuable for students and researchers interested in reinforcement learning, sim-to-real transfer, and the intersection of biomechanics and robotics. As the field moves toward more versatile autonomous systems, Zhang’s contributions are poised to shape how robots learn to interact with the physical world.