Papers
1
Total Citations
16
H-Index
1
About
Haoyuan Pei is a researcher whose work sits at the intersection of computer vision, robotics, and deep learning, with a particular focus on indoor scene understanding and automated map segmentation. His most cited contribution, "MapSegNet: A Fully Automated Model Based on the Encoder-Decoder Architecture for Indoor Map Segmentation" (2021), introduces a novel deep convolutional neural network that tackles the challenging problem of parsing indoor maps into meaningful spatial units like individual rooms. This work, which has garnered 16 citations, addresses a critical bottleneck in robotics and autonomous navigation: the need for efficient, automated environment mapping. By leveraging an encoder-decoder architecture, Pei’s model enables robots to segment complex indoor layouts without manual intervention, directly improving their ability to perceive and navigate human-centric spaces. His research sits at the forefront of applying neural networks to practical robotics challenges, offering a scalable solution that bridges the gap between raw sensor data and actionable spatial intelligence. Pei’s contributions are particularly valuable for students and researchers exploring the integration of deep learning with robotic perception, demonstrating how targeted architectural innovations can yield robust, real-world performance in map understanding tasks.
Research Focus
Key Achievements
Top Papers
- 1