Yaohua Liu

University of Science and Technology of China, Guilin University of Electronic Technology, Chinese Academy of Sciences

Papers

Total Citations

H-Index

About

Yaohua Liu is a leading researcher in multisensor information fusion and MEMS-based inertial navigation, with a focus on enhancing the accuracy and reliability of low-cost sensors for autonomous robotics. His major contributions lie in developing hybrid deep learning architectures that address the complex, non-linear, and time-varying noise inherent in MEMS gyroscopes. Notably, his work on the attention-Conv-LSTM network introduced a novel stochastic noise elimination method, achieving significant improvements in signal denoising for self-localization systems. Liu also pioneered the LGC-Net, a lightweight neural network that compensates for gyroscope errors in real-time, enabling effective attitude estimation without heavy computational overhead—a critical advancement for resource-constrained robots. His comprehensive review of multisensor information fusion technology has become a foundational reference, synthesizing decades of progress in military, navigation, and image processing applications. With over 24 citations across his most-cited works, Liu’s research bridges the gap between theoretical fusion models and practical, deployable systems, making him a key figure in advancing low-cost, high-performance inertial measurement units for next-generation autonomous systems.