← All datasets & code
TDL-GNSS
Tightly Coupled Deep Learning Framework for GNSS Positioning
- Developed by
- Runzhi Hu
- Repository
- ebhrz/TDL-GNSS
- GitHub
- 112 stars · 16 forks
Summary
A framework that puts deep networks inside the GNSS processing chain, so models for signal quality, weighting and error mitigation can be trained end to end.
Key innovations
- Deep learning tightly coupled with conventional SPP, RTK and PPP processing
- End-to-end trainable pipeline for positioning in urban canyons
- Built on the pyrtklib and TASGNSS ecosystem
Impact
- 112 GitHub stars and 16 forks
- Published with pyrtklib in IEEE T-ITS (2025)
Cite this work
R. Hu, P. Xu, Y. Zhong and W. Wen, "pyrtklib: An Open-Source Package for Tightly Coupled Deep Learning and GNSS Integration for Positioning in Urban Canyons," IEEE Transactions on Intelligent Transportation Systems, 26(7), 2025. DOI