Papers
1
Total Citations
2
H-Index
1
About
Hongrui Tang is a researcher at the forefront of integrating semantic understanding with robotic perception, specializing in Visual SLAM (Simultaneous Localization and Mapping) and deep learning for autonomous systems. His most-cited work, "DeepLabV3+-Based Semantic Annotation Refinement for SLAM in Indoor Environments," addresses a critical bottleneck in robotics: the struggle of monocular SLAM systems to reconstruct accurate 3D scenes in semantically sparse or ambiguous indoor settings. By leveraging a refined DeepLabV3+ architecture, Tang developed a method to automatically enhance semantic annotations, effectively bridging the gap between raw visual data and high-level scene comprehension. This contribution directly improves robotic operational efficiency in complex environments, offering a scalable alternative to labor-intensive manual labeling. With his work already garnering early citations in the rapidly evolving field of embodied AI, Tang is establishing himself as a key voice in the next generation of perception systems. His research not only advances the technical robustness of SLAM but also paves the way for more intelligent, context-aware navigation in real-world applications.
Research Focus
Key Achievements
Top Papers
- 1