Runnan Liu
Papers
1
Total Citations
5
H-Index
1
About
Runnan Liu is a researcher at the forefront of autonomous vehicle navigation and sensor fusion, with a particular focus on enhancing dead reckoning and localization systems. His most notable contribution is the development of a "Trainable Quaternion Extended Kalman Filter with Multi-Head Attention," a novel approach that integrates deep learning with classical Bayesian estimation to improve the robustness of autonomous ground vehicle positioning. This work, published in 2022, has already garnered 5 citations, signaling its growing influence in the optimal control and mobile robotics communities. By addressing the challenge of obtaining adequate and reliable state estimates in dynamic environments, Liu bridges the gap between traditional filter-based methods and modern attention mechanisms. His research is critical for advancing the reliability of self-driving systems, where precise localization is paramount. Liu’s innovative fusion of quaternion algebra with trainable architectures marks him as a promising young scholar in the field, with his work poised to impact both theoretical estimation theory and practical autonomous vehicle deployment.
Research Focus
Key Achievements
Top Papers
- 1