Chenglong Xu

Papers

Total Citations

H-Index

About

Chenglong Xu is a researcher focused on advancing simultaneous localization and mapping (SLAM) and active object recognition for mobile robotics. His work addresses critical challenges in real-time performance and positioning accuracy, particularly through parallel computing innovations. Xu’s most-cited paper, "Unified Optimization for Multiple Active Object Recognition Tasks with Feature Decision Tree" (2021, 4 citations), introduces a novel framework that integrates multiple recognition tasks into a single optimization process, enhancing efficiency in dynamic environments. His earlier study, "An Acceleration Method Using CUDA based on ORB-SLAM2" (2019, 2 citations), tackles the poor real-time performance and low position accuracy of mobile robots by leveraging CUDA parallel computing to accelerate ORB feature extraction and matching—a key bottleneck in SLAM systems. This work demonstrates his ability to bridge hardware acceleration with algorithmic design, offering practical solutions for autonomous navigation. While his citation counts are modest, Xu’s contributions are foundational for researchers exploring GPU-accelerated robotics and multi-task perception systems. His focus on unifying optimization and parallel processing positions him as a promising voice in the field, with potential for broader impact as autonomous systems demand greater speed and accuracy.