Tran Vu

Papers

Total Citations

H-Index

About

Tran Vu is a leading researcher in ultra-wideband (UWB) ranging and robotic navigation, with a focus on data-driven error mitigation in challenging environments. His most cited work, "DeepCIR: Insights into CIR-based Data-driven UWB Error Mitigation" (2022, 10 citations), introduces a novel deep learning framework that leverages channel impulse response (CIR) data to correct UWB range errors in cluttered, non-line-of-sight (NLOS) conditions. This contribution addresses a critical bottleneck in off-the-shelf UWB sensors, which often produce unreliable readings in real-world deployments. By demonstrating how neural networks can extract robust features from raw CIR signals, Vu's research enables more accurate and resilient localization for autonomous robots, drones, and IoT systems. His work bridges the gap between theoretical signal processing and practical sensor calibration, offering a scalable solution that reduces reliance on expensive hardware. With growing citation impact, Vu's findings are shaping next-generation UWB systems, making them viable for safety-critical applications like warehouse automation and search-and-rescue missions. His interdisciplinary approach—combining deep learning, wireless communications, and robotics—positions him as a rising authority in intelligent sensing technologies.