Yiguang Liu

Papers

Total Citations

H-Index

About

Yiguang Liu is a leading researcher in robotics and computational intelligence, with a primary focus on mobile robot localization and sensor fusion. His most influential work introduces Quasi Monte Carlo Localization (QMCL), a groundbreaking approach that overcomes the inefficiencies of traditional Monte Carlo methods by employing low-discrepancy sequences for particle initialization. This innovation dramatically reduces the sample set size required for accurate robot pose estimation, enabling faster and more reliable localization in dynamic environments. With over 3 citations on this foundational paper, Liu's contributions have shaped modern probabilistic robotics, particularly in real-time applications where computational efficiency is critical. His work bridges theoretical advances in quasi-random sampling with practical deployment challenges, earning recognition for improving the robustness of autonomous navigation systems. Liu's research continues to influence fields from autonomous vehicles to service robotics, where his methods are cited as key enablers for scalable, real-time localization. His achievements underscore a career dedicated to solving fundamental problems in robot perception and decision-making.