Xi Cai

University of Electronic Science and Technology of China

Papers

Total Citations

H-Index

About

Xi Cai is a robotics researcher whose work bridges computer vision and autonomous systems, with a focus on enabling robots to operate reliably in unstructured, real-world environments. His key research areas include semantic segmentation for outdoor navigation, defect detection for construction robotics, and deep reinforcement learning for low-shot learning scenarios. Cai’s most influential contribution is his 2018 paper on road segmentation for all-day outdoor robot navigation, which has garnered 59 citations—a strong indicator of its impact on the field of autonomous mobile robotics. In this work, he addressed the challenge of robust visual perception under varying lighting conditions, a critical problem for field robots. More recently, Cai has explored the application of deep reinforcement learning to low-shot wall defect detection for autonomous decoration robots, a practical innovation that reduces the need for large annotated datasets. This work, published in 2020, demonstrates his ability to tackle real-world industrial challenges with data-efficient methods. Through his research, Cai is advancing the frontier of robots that can perceive and act in complex, human-centric spaces.