Zhiyong Yu

About

Zhiyong Yu is a researcher whose work lies at the intersection of robotics, computer vision, and deep learning, with a particular focus on semantic understanding of indoor environments. His most cited paper, "Research on Distance Transform and Neural Network Lidar Information Sampling Classification-Based Semantic Segmentation of 2D Indoor Room Maps" (2021, 18 citations), addresses a critical challenge in mobile robotics: enabling robots to semantically parse 2D LiDAR maps. Yu’s key contribution is a novel hybrid approach that combines distance transform watershed-based pre-segmentation with a carefully designed neural network for LiDAR information sampling and classification. This method allows for more accurate and efficient labeling of room structures, directly impacting how robots navigate and interact with indoor spaces. By bridging classical geometric techniques with modern deep learning, Yu’s work offers a practical pathway for improving autonomous systems’ spatial awareness. His research is particularly valuable for students and engineers working on SLAM, robotic perception, and environment understanding, demonstrating how thoughtful integration of traditional and neural methods can yield robust, real-world solutions.

Research Focus

Key Achievements

Top Papers

1. 1
   Research on Distance Transform and Neural Network Lidar Information Sampling Classification-Based Semantic Segmentation of 2D Indoor Room Maps

   18 citations · 2021

Key Collaborators

Contact & Links