Max Robotics — Global Service Robot Directory + US Certification

About

Sangjun Noh is a robotics researcher whose work sits at the intersection of tactile sensing, computer vision, and robotic manipulation. His research spans three key areas: wearable bioelectronic sensors for health monitoring, amodal instance segmentation for robotic perception, and sim-to-real transfer for robotic grasping and assembly. Noh’s most influential contribution is the development of all-3D-printed, flexible bioelectronic tactile sensors using biocompatible nanocomposites, a work that has garnered 67 citations and promises continuous health monitoring through wearable technology. In computer vision, his work on unseen object amodal instance segmentation via hierarchical occlusion modeling (66 citations) has advanced robotic perception in cluttered environments, enabling robots to reason about object shapes beyond visible regions. More recently, Noh has pioneered the integration of large foundation models into robotic manipulation, introducing GraspSAM—a prompt-driven extension of the Segment Anything Model for grasp detection—and PolyFit, a sim-to-real adaptation framework for peg-in-hole assembly of unseen polygon shapes. He has also contributed GraspClutter6D, a large-scale real-world dataset for robust perception in cluttered scenes. Noh’s work consistently pushes toward practical, generalizable robotic systems that can handle novel objects and complex real-world conditions.