Max Robotics — Global Service Robot Directory + US Certification

About

Xuanju Dang is a leading researcher in robotic manipulation, focusing on the intersection of computer vision, deep learning, and control systems to enable intelligent, safe, and efficient robot grasping in unstructured environments. His most impactful work, "Light-Weight Convolutional Neural Networks for Generative Robotic Grasping" (2024, 29 citations), introduces a quantized grasp quality generative neural network that achieves high-performance grasping with remarkable computational efficiency, addressing a critical bottleneck for real-world picking tasks. Dang has also made significant contributions to human-robot safety with his "Novel Sliding Mode Momentum Observer for Collaborative Robot Collision Detection" (2022, 18 citations), which eliminates the need for additional sensors while maintaining sensitivity to collisions. His innovative "Taylor Neural Network for Unseen Object Instance Segmentation in Hierarchical Grasping" (2024, 7 citations) tackles the challenge of grasping unknown, cluttered objects by combining instance segmentation with hierarchical grasp planning. Further advancing the field, his "Fast UOIS" method (2024, 4 citations) optimizes the trade-off between efficiency and accuracy for segmenting unseen objects in industrial settings. Dang’s work consistently bridges theoretical advances with practical robotic applications, making him a key figure in developing next-generation autonomous manipulation systems.