Yingnan Ma

Papers

Total Citations

H-Index

About

Yingnan Ma is a researcher whose work bridges the gap between simulation and real-world robotics, with a particular focus on robust perception and control. His most-cited paper, "SimFormer: Real-to-Sim Transfer with Recurrent Restoration" (2022), introduces a novel framework that leverages recurrent neural networks to restore simulated data to match real-world distributions, enabling more effective policy transfer from simulation to physical robots. This contribution addresses a critical challenge in robotics—the sim-to-real gap—by improving the fidelity of simulated training environments. While his citation count is still growing, Ma's work is positioned at the intersection of computer vision, reinforcement learning, and robotic manipulation, offering practical solutions for deploying learned policies in dynamic, unstructured environments. His research holds promise for advancing autonomous systems in manufacturing, logistics, and service robotics, where reliable sim-to-real transfer is essential for scalable deployment.