Papers
1
Total Citations
3
H-Index
1
About
Yiran Guo is a researcher at the forefront of robotic perception and autonomous navigation, with a primary focus on semantic visual SLAM (Simultaneous Localization and Mapping). Their most cited work, "Semantic Visual SLAM Algorithm Based on Improved DeepLabV3+ Model and LK Optical Flow" (2024), addresses a critical challenge in indoor robotics: dynamic objects that degrade localization accuracy and prevent the construction of semantically meaningful maps. By integrating an enhanced DeepLabV3+ semantic segmentation model with Lucas-Kanade optical flow, Guo’s algorithm significantly improves pose estimation robustness in cluttered, moving environments—a breakthrough for applications in service robots and augmented reality. This contribution has already garnered 3 citations shortly after publication, signaling growing impact. Guo’s research bridges computer vision and robotics, enabling systems to not only map their surroundings but also understand them at an object level. Their work is particularly notable for combining deep learning with classical optical flow techniques, offering a computationally efficient solution for real-time operation. As dynamic environments become the norm for autonomous systems, Guo’s innovations are poised to influence next-generation SLAM frameworks, making them a rising voice in the field of intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1