BatStation: Toward In-Situ Radar Sensing on 5G Base Stations with Zero-Shot Template Generation

2025-09-08

AI Summary

In 5G coexistence scenarios, radar sensing faces challenges including spectrum sharing constraints, strong uplink interference, and requirements for lightweight deployment. To address these, this paper proposes BatStation—a lightweight, in-situ radar sensing framework integrated directly into 5G base stations. BatStation introduces a novel uplink resource-grid-based signal separation mechanism, combined with time-frequency grid reshaping and zero-shot template correlation analysis, enabling radar pulse detection, classification, and high-precision localization without fine-tuning on real-world measurements. Its core innovation is a zero-shot template generation method, trained exclusively on synthetic data and deployable without domain adaptation. Experimental evaluation under live 5G traffic shows PUCCH and PUSCH detection rates of 97.02% and 79.23%, respectively; classification accuracy of 97.00%; median frequency and time localization errors of 2.68–6.20 MHz and 24.6–32.4 μs; and GPU/CPU inference latencies of only 0.11 ms and 0.94 ms.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The coexistence between incumbent radar signals and commercial 5G signals necessitates a versatile and ubiquitous radar sensing for efficient and adaptive spectrum sharing. In this context, leveraging the densely deployed 5G base stations (BS) for radar sensing is particularly promising, offering both wide coverage and immediate feedback to 5G scheduling. However, the targeting radar signals are superimposed with concurrent 5G uplink transmissions received by the BS, and practical deployment also demands a lightweight, portable radar sensing model. This paper presents BatStation, a lightweight, in-situ radar sensing framework seamlessly integrated into 5G BSs. BatStation leverages uplink resource grids to extract radar signals through three key components: (i) radar signal separation to cancel concurrent 5G transmissions and reveal the radar signals, (ii) resource grid reshaping to align time-frequency resolution with radar pulse characteristics, and (iii) zero-shot template correlation based on a portable model trained purely on synthetic data that supports detection, classification, and localization of radar pulses without fine-tuning using experimental data. We implement BatStation on a software-defined radio (SDR) testbed and evaluate its performance with real 5G traffic in the CBRS band. Results show robust performance across diverse radar types, achieving detection probabilities of 97.02% (PUCCH) and 79.23% (PUSCH), classification accuracy up to 97.00%, and median localization errors of 2.68-6.20 MHz (frequency) and 24.6-32.4 microseconds (time). Notably, BatStation achieves this performance with a runtime latency of only 0.11/0.94 ms on GPU/CPU, meeting the real-time requirement of 5G networks.

Problem

• Enabling radar sensing on 5G base stations despite signal interference
• Separating radar signals from concurrent 5G uplink transmissions efficiently
• Detecting and classifying radar pulses without experimental data fine-tuning

Innovation

• Radar signal separation from 5G uplink transmissions
• Resource grid reshaping for radar pulse alignment
• Zero-shot template correlation with synthetic data training