Xiuxian Guan
Papers
5
Total Citations
30
H-Index
4
About
Xiuxian Guan is an emerging researcher at the intersection of autonomous robotics, navigation systems, and distributed machine learning for robotic IoT. His work focuses primarily on developing efficient navigation frameworks for air-ground robots (AGRs) — versatile platforms capable of both flying and driving — with a particular emphasis on handling occlusion-prone and dynamically complex environments such as forests, large buildings, and disaster zones. Guan's most notable contributions include AGRNav, OMEGA, and HE-Nav, a trio of navigation systems that collectively address the challenge of predicting unobserved obstacles, enabling collision-free path planning while minimizing energy consumption. These systems leverage cutting-edge techniques including 3D semantic occupancy networks and state space models, pushing the boundaries of what AGRs can achieve in real-world deployment scenarios. Together, these papers have garnered 22 citations since 2024, a strong indicator of rapid community recognition. Beyond navigation, Guan investigates distributed inference and training of deep neural network models on resource-constrained robotic IoT systems, as demonstrated in his work on ROG and related distributed inference frameworks. His research bridges theoretical machine learning with practical robotics engineering, making his contributions especially relevant to students and engineers working on next-generation autonomous systems operating in unstructured, high-stakes environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3New Problems in Distributed Inference for DNN Models on Robotic IoT6 citations · 2024
- 4
- 5