Max Robotics — Global Service Robot Directory + US Certification

About

Shengjin Wang is a leading researcher at the intersection of computer vision, robotics, and human-computer interaction, with a focus on creating intelligent systems that perceive and act in the physical world. His work spans geometry-aware depth completion, language-guided robotic grasping, and brain-computer interfaces. Wang’s most cited paper, "GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs" (2022, 37 citations), introduces a novel framework that leverages dynamic graph convolutional networks to improve depth estimation, a critical capability for autonomous navigation and 3D scene understanding. In "VL-Grasp: a 6-Dof Interactive Grasp Policy for Language-Oriented Objects in Cluttered Indoor Scenes" (2023, 34 citations), he tackles the challenge of human-robot interaction by enabling robots to grasp objects based on natural language commands, combining vision and language understanding with robust grasp prediction. Earlier, Wang contributed to neural engineering with "Improving the P300-based brain-computer interface with transfer learning" (2017, 8 citations), addressing the practical hurdle of inter-subject variability in BCI systems. His applied work includes the "Multimodal Based Automatic Feeding Robotic Device" (2022), designed to assist individuals with disabilities. With over 80 total citations, Wang’s research is shaping the future of assistive and interactive robotics.