Xinkun Zheng

Huazhong University of Science and Technology

Papers

Total Citations

H-Index

About

Xinkun Zheng is an emerging researcher working at the intersection of wireless communications, machine learning, and robotic localization systems. His work spans two key research frontiers: advanced multicarrier communication systems and near-field wireless localization for mobile robotics. Zheng's most recognized contribution lies in applying deep learning techniques to Filter Bank Multicarrier (FBMC) systems for machine-type communications (MTC). His 2023 paper, which has garnered 7 citations, demonstrated how neural network architectures can overcome FBMC's inherent design challenges in transmitting diverse data types — offering a more robust alternative to OFDM-based systems that struggle with synchronization errors in IoT and MTC environments. More recently, Zheng has turned his attention to near-field localization for mobile robots, exploring how virtual large-scale antenna arrays formed through device mobility can extract both angle-of-arrival and range information. His 2025 works investigate single-antenna and multi-access-point collaborative frameworks, pushing localization accuracy into the near-field regime where traditional far-field assumptions break down. Though early in his career, Zheng's research addresses critical challenges in next-generation wireless networks and autonomous systems — positioning him as a promising contributor to 6G communications and intelligent robotics research.