Xiaodong Guo
Papers
1
Total Citations
2
H-Index
1
About
Xiaodong Guo is a leading researcher in multimodal perception and real-time scene understanding for field robotics. His work focuses on fusing complementary sensor modalities—particularly RGB and thermal imaging—to achieve robust semantic segmentation in unstructured, wild environments. Guo’s most cited paper, “Cross-modal State Space Modeling for Real-time RGB-thermal Wild Scene Semantic Segmentation” (2025), introduces an innovative state space modeling framework that dramatically reduces the computational overhead of Transformer-based multi-source data processing. This breakthrough enables field robots to perform high-accuracy, real-time segmentation without sacrificing efficiency, addressing a critical bottleneck in autonomous outdoor navigation. By pioneering lightweight cross-modal architectures, Guo’s contributions are paving the way for practical deployment of intelligent robots in agriculture, search-and-rescue, and environmental monitoring. His work has already garnered early citations, signaling strong interest from the robotics and computer vision communities. Guo’s research stands at the intersection of efficiency and robustness, offering scalable solutions for machines that must perceive and act in the wild.
Research Focus
Key Achievements
Top Papers
- 1