Chaoxian Luo

Papers

Total Citations

H-Index

About

Chaoxian Luo is a researcher advancing the frontiers of robot perception and autonomous navigation, with a primary focus on visual SLAM (Simultaneous Localization and Mapping), semantic segmentation, and landmark-based mapping. His most influential work, "Dynamic dense CRF inference for video segmentation and semantic SLAM" (2022), has garnered 21 citations by introducing a novel framework that integrates dense conditional random fields with video segmentation to robustly handle dynamic environments—a critical challenge for real-world robotic systems. This contribution enables robots to maintain accurate spatial understanding even amidst moving objects, directly improving the reliability of autonomous navigation. In his earlier work, "Visual Landmark Learning Via Attention-Based Deep Neural Networks" (2021), Luo demonstrated how attention mechanisms can learn compact, memory-efficient landmark representations from visual data. By contrasting these with dense maps like point clouds or occupancy grids, he highlighted the scalability of landmark maps for large-scale environments—a key advantage for long-term robot localization and navigation. Luo’s research elegantly bridges deep learning and probabilistic inference, offering practical solutions that reduce computational overhead while enhancing perceptual robustness. His work continues to shape the development of efficient, real-time mapping systems for autonomous robots operating in complex, unstructured spaces.