A TCN-BiLSTM and ANR-IEKF Hybrid Framework for Sustained Vehicle Positioning During GNSS Outages
Senhao Niu, Jie Li, Chenjun Hu, Junlong Li, Debiao Zhang, Kaiqiang Feng · 2025
Read A TCN-BiLSTM and ANR-IEKF Hybrid Framework for Sustained Vehicle Positioning During GNSS Outages by Senhao Niu, Jie Li, Chenjun Hu, Junlong Li, Debiao Zhang, Kaiqiang Feng (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12788135.txt.
Description
Senhao Niu and five colleagues design a navigation system that keeps vehicles located when satellite signals vanish, in a paper from two thousand twenty-five. Urban canyons block GNSS signals frequently in city streets. Inertial systems drift with no correction to hold them true. That drift puts autonomous driving at risk each time it strikes.
Their hybrid pairs deep learning with an adaptive Kalman filter. A temporal convolutional and bidirectional memory network fabricates pseudo-satellite measurements from inertial data in the gaps. An iterated extended Kalman filter with regulated noise then fuses those estimates as they come in. The filter keeps re-estimating its own noise statistics as it goes, for robustness. The team reports sustained positioning through the gaps in signal. The approach is aimed at the messy, stop-start signal world of real city streets.
Catalog record
| CREATOR | Senhao Niu, Jie Li, Chenjun Hu, Junlong Li, Debiao Zhang, Kaiqiang Feng |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |