Max Robotics — Global Service Robot Directory + US Certification

About

Ling Tong is a rising star in robotic manipulation, whose research focuses on enabling robots to perceive and grasp objects reliably in cluttered, unstructured environments. Her core contributions lie at the intersection of computer vision and robotic grasping, where she has pioneered deep learning methods that integrate semantic understanding with grasp detection. Her most influential work, "SISG-Net" (29 citations), introduced a simultaneous instance segmentation and grasp detection framework, allowing robots to identify and grasp individual objects even in dense clutter. She further advanced the field by addressing the critical challenge of background variability with her "Background-Adaptive Grasping Network" and the accompanying cross-background dataset (25 citations), which significantly improves robot adaptability to changing industrial and household scenes. Tong has also tackled the notoriously difficult problem of grasping weakly textured objects, such as transparent and reflective materials, through her "SG-Grasp" system (25 citations). Her latest work, "HFNet" (2025), pushes the boundaries of precision in unstructured environments through hierarchical RGB-D feature fusion. With over 86 total citations in just two years, Ling Tong is establishing herself as a key innovator in making robotic grasping robust enough for real-world manufacturing and service applications.