Max Robotics — Global Service Robot Directory + US Certification

About

Dexing Shan is a rising researcher at the intersection of robotic perception, manipulation, and human-robot interaction. His work centers on enabling robots to intelligently perceive and interact with unstructured environments, with key contributions in few-shot semantic segmentation for robotic grasping, multi-modal sensor fusion, and adaptive control for rehabilitation exoskeletons. Shan’s most cited paper, “Unseen Object Few-Shot Semantic Segmentation for Robotic Grasping” (2022, 15 citations), tackles the challenge of segmenting novel objects in cluttered scenes—a critical step toward generalizable robotic manipulation. He further advances this line of work with “Joint Segmentation and Grasp Pose Detection with Multi-Modal Feature Fusion Network” (2023, 7 citations), which integrates RGB and depth data for more robust grasp planning. Beyond manipulation, Shan has innovated in rehabilitation robotics, developing a fuzzy adaptive impedance controller for pneumatic artificial muscle exoskeletons (2024, 5 citations), and in soft sensing, designing a novel PEBA-silicone composite magneto-sensitive airbag sensor for simultaneous force and motion detection (2025, 3 citations). His diverse portfolio—spanning deep learning, sensor design, and control theory—reflects a commitment to building safer, more capable robots that work alongside humans.