English

Benchmarking Learnt Radio Localisation under Distribution Shift

Machine Learning 2022-10-06 v1 Networking and Internet Architecture Signal Processing

Abstract

Deploying radio frequency (RF) localisation systems invariably entails non-trivial effort, particularly for the latest learning-based breeds. There has been little prior work on characterising and comparing how learnt localiser networks can be deployed in the field under real-world RF distribution shifts. In this paper, we present RadioBench: a suite of 8 learnt localiser nets from the state-of-the-art to study and benchmark their real-world deployability, utilising five novel industry-grade datasets. We train 10k models to analyse the inner workings of these learnt localiser nets and uncover their differing behaviours across three performance axes: (i) learning, (ii) proneness to distribution shift, and (iii) localisation. We use insights gained from this analysis to recommend best practices for the deployability of learning-based RF localisation under practical constraints.

Keywords

Cite

@article{arxiv.2210.01930,
  title  = {Benchmarking Learnt Radio Localisation under Distribution Shift},
  author = {Maximilian Arnold and Mohammed Alloulah},
  journal= {arXiv preprint arXiv:2210.01930},
  year   = {2022}
}
R2 v1 2026-06-28T02:48:57.828Z