Xiang‐Yang Li

Illinois Institute of Technology, Taibah University, University of Science and Technology of China

Papers

Total Citations

H-Index

About

Xiang-Yang Li’s research lies at the intersection of robotics, sensor networks, and distributed machine learning, with a focus on creating intelligent, real-time systems for critical applications. His early work established a foundation for practical robotic sensor networks, developing a real-time rescue system (2011, 6 citations) that integrates rapid event detection with autonomous victim navigation—a key contribution to emergency response technology. This work demonstrated how sensor networks could move from theory to life-saving deployment. More recently, Li has advanced indoor localization by addressing a fundamental challenge in deep learning: weight parameter instability in residual networks. His vision-based algorithm using an improved ResNet (2020, 3 citations) incorporates batch normalization and adaptive techniques to stabilize performance, offering a more reliable approach for indoor positioning—critical for autonomous robots and IoT systems. His latest contribution tackles the communication constraints of distributed online learning. In his 2024 work on communication-efficient regret-optimal distributed online convex optimization (1 citation), Li addresses two critical challenges in robot and IoT networks: minimizing communication overhead while achieving optimal regret bounds. This work promises to enable scalable, real-time collaborative learning in bandwidth-limited environments, pushing the boundaries of what distributed systems can achieve in practical deployments.