NARRAS: Edge-Triggered Distributed Inference for CSI-Based Localization in Vehicular IoT Networks

2026-06-10

AI Summary

This study addresses the tension between redundant data reporting from distributed antenna arrays and uplink capacity constraints in channel state information (CSI)-based vehicular localization. The authors propose an edge-triggered distributed inference framework, wherein each remote radio unit locally decides whether to report its observations, and a fusion center estimates user positions under a constraint on the average number of active transmitters. The method innovatively integrates differentiable activity penalties with calibrated thresholding to control reporting rates and introduces channel graph regularization to shape the geometry of the latent space, thereby enhancing robustness under sparse reporting conditions. Experiments demonstrate that, at comparable uplink activity levels, the proposed approach achieves higher localization accuracy than existing learning-based and heuristic sparse reporting schemes; notably, channel graph regularization substantially reduces high-percentile localization errors in low-activity scenarios.

Abstract

CSI-based localization with spatially distributed antenna arrays exposes a basic resource trade-off. Each array can provide a rich view of the channel, but forwarding observations from all arrays to a fusion center is wasteful when only a few carry useful information, and the shared uplink supports only a limited number of simultaneous transmissions. We let each array decide locally whether its current observation is worth reporting, subject to a budget on the average number of active transmitters. We refer to this abstraction as Edge-Triggered Distributed Inference (ETDI). It captures a broader class of task-oriented communication problems where resource-constrained devices share an access channel for a common inference task. We instantiate ETDI for CSI-based localization, a common scenario in vehicular IoT networks. Spatially distributed remote antenna arrays (RAAs) encode local channel state information (CSI) from user equipment (UE) transmissions into latent features, and the fusion center estimates the UE position from the subset of reported features. We propose NARRAS, a decentralized reporting policy in which each RAA combines a recurrent summary of its recent observations with a memory of the last latent it transmitted. Training controls an explicit activity budget through differentiable activity penalties and validation-calibrated deterministic thresholds, and uses channel-chart regularization to shape the latent geometry. Experiments show that, at comparable uplink activity, NARRAS improves localization accuracy over learned and heuristic sparse-reporting strategies, while dense full-report models remain useful budget-free references. In low-activity regimes, chart regularization further reduces high-percentile localization errors, suggesting that geometry-aware latent representations are more robust under sparse reporting.

Problem

• CSI-based localization
• distributed inference
• resource-constrained communication
• vehicular IoT networks
• sparse reporting

Innovation

• Edge-Triggered Distributed Inference
• CSI-based localization
• sparse reporting
• channel-chart regularization
• vehicular IoT networks