Yifan Liang
Papers
3
Total Citations
69
H-Index
3
About
Yifan Liang is a robotics researcher specializing in autonomous navigation, localization, and exploration for mobile robots. Their work centers on solving fundamental challenges in enabling robots to operate effectively in unknown or GPS-denied environments. Liang’s most impactful contribution is a LiDAR-based single-shot global localization solution that uses a novel cross-section shape context descriptor, a method that has garnered 52 citations for its ability to achieve robust place recognition without prior pose estimates. This work addresses a critical bottleneck in robotics: reliable localization in large-scale, unstructured spaces. Additionally, Liang has advanced autonomous exploration frameworks by improving the efficiency of reduced approximated generalized Voronoi graphs (RA-GVGs), as demonstrated in their 2020 publications. These contributions streamline next-best-view selection and path planning, enabling robots to map unknown indoor environments more quickly and with less computational overhead. By refining graph-based exploration techniques, Liang’s research bridges the gap between theoretical path planning and practical, real-world deployment. Their work is particularly valuable for applications in search-and-rescue, warehouse automation, and field robotics, where reliable autonomy in uncharted terrain is essential.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3