Zixuan Huang

Carnegie Mellon University, University of Glasgow, University of Michigan–Ann Arbor, Wuhan University

Papers

Total Citations

H-Index

About

Zixuan Huang is a robotics researcher whose work sits at the intersection of manipulation, navigation, and perception. His primary research areas include cloth manipulation, robotic path planning, and model-predictive control (MPC) for articulated and deformable objects. Huang’s most cited work, “Mesh-based Dynamics with Occlusion Reasoning for Cloth Manipulation” (2022, 37 citations), addresses the critical challenge of self-occlusion in unfolding crumpled or folded cloth by leveraging pose estimation to reason about occluded regions—a key step toward enabling robots to handle deformable objects in real-world settings. He further advances manipulation with “Subgoal Diffuser” (2024, 9 citations), a coarse-to-fine subgoal generation framework that guides MPC for robust manipulation under unexpected disturbances. In navigation, his “Bio-inspired hybrid path planning” (2025, 10 citations) introduces efficient, smooth, and collision-free trajectories for complex environments. Huang also explores visual localization in crowded scenes with “Human Tide, Clear Sight” (2025), enhancing robustness for IoT and autonomous systems. His work demonstrates a clear focus on bridging perception, planning, and control to create more adaptive and intelligent robotic systems.