Zhengming Ding

Papers

Total Citations

H-Index

About

Zhengming Ding is a leading researcher at the intersection of robotics, computer vision, and multimodal perception. His work focuses on enabling robots to perceive and interact with their environment through the fusion of multiple sensory modalities, particularly vision and touch. Ding’s major contributions include pioneering lifelong visual-tactile spectral clustering for robotic object perception, a framework that allows robots to continuously learn and cluster objects using both visual and tactile data—a critical step toward more adaptive, human-like robotic manipulation. His research on polyline generative navigable space segmentation advances autonomous visual navigation by treating navigable space detection as a scene decomposition problem, enabling robots to traverse unknown environments more safely and efficiently. With over 18 citations on his visual-tactile clustering work and growing recognition for his navigation research, Ding is establishing himself as an influential voice in embodied AI. His work not only pushes the boundaries of robotic perception but also lays the groundwork for robots that can learn and adapt in real-world, unstructured settings—making him a key figure to watch in the field of intelligent robotics.