Max Robotics — Global Service Robot Directory + US Certification

About

Yinzhen Xu is a leading researcher in robotic dexterous manipulation and generalist humanoid robotics, whose work bridges the gap between simulation and real-world dexterity. Their major contributions center on enabling robots to grasp and manipulate objects with human-like versatility. Xu spearheaded the creation of **DexGraspNet**, a large-scale simulation dataset for dexterous grasping that has become a foundational resource for the field, amassing over 85 citations. Building on this, they developed **UniDexGrasp**, a universal framework that learns diverse, high-quality grasp proposals from point cloud observations, achieving remarkable generalization across hundreds of object categories—including unseen ones—and earning 94 citations. Most recently, Xu contributed to **GR00T N1**, an open foundation model for generalist humanoid robots, aiming to unify perception and control for embodied intelligence. Their work has been recognized for its practical impact, with UniDexGrasp and DexGraspNet collectively cited over 180 times, establishing Xu as a key figure in advancing robotic dexterity toward human-level capability.