Summary of Towards End-to-end Gps Localization with Neural Pseudorange Correction, by Xu Weng et al.
Towards End-to-End GPS Localization with Neural Pseudorange Correction
by Xu Weng, KV Ling, Haochen Liu, Kun Cao
First submitted to arxiv on: 19 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed E2E-PrNet framework is an end-to-end GPS localization system that trains a neural network for pseudorange correction using the final task loss calculated with ground truth receiver states. Unlike previous data-driven methods, this approach eliminates the need for intermediate labels and instead uses gradients of the loss to learnable parameters backpropagated through a Differentiable Nonlinear Least Squares (DNLS) optimizer. This framework outperforms both baseline weighted least squares and state-of-the-art end-to-end data-driven approaches when tested with GPS data collected by Android phones. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The E2E-PrNet framework is a new way to correct pseudorange errors in GPS localization. It’s like a special kind of computer program that can learn from examples to improve its accuracy. The program uses a combination of machine learning and mathematical optimization techniques to find the best solution. This approach works better than previous methods when tested with real-world data collected by Android phones. |
Keywords
* Artificial intelligence * Machine learning * Neural network * Optimization
