Max Robotics — Global Service Robot Directory + US Certification

About

Mengyuan Ding is a robotics researcher whose work focuses on enabling robots to understand and manipulate complex, multi-object environments through visual relationship detection. Her primary research areas include robotic grasping, graph neural networks, and visual manipulation relationship detection—critical for teaching robots to interact with the world safely and efficiently. Ding’s major contribution lies in developing graph-based models that capture both local and global object interactions, moving beyond traditional pairwise relationship detection. Her 2022 paper, "Visual Manipulation Relationship Detection based on Gated Graph Neural Network for Robotic Grasping," with 20 citations, introduced a gated graph neural network to model interaction effects between objects, reducing redundant operations. She further advanced this with dual graph attention networks in 2025, integrating object-level and relational-level dependencies for multi-view scenarios. Ding has also explored robot self-recognition through facial expression sensorimotor learning, drawing on human cognitive principles. Her work has accumulated over 30 citations, establishing her as an emerging voice in intelligent robotic manipulation and cognitive robotics.