CageDroneRF: A Large-Scale RF Benchmark and Toolkit for Drone Perception

2026-01-06

arXiv.org

AI Summary

Existing RF-based drone perception datasets are limited in scale and scenario diversity, hindering the development of robust and generalizable detection and recognition models. To address this, this work presents a large-scale benchmark that integrates real-world and synthetically generated RF data, encompassing multiple operational drone models under complex electromagnetic environments. The authors introduce a label-consistent signal augmentation technique that precisely controls signal-to-noise ratio, injects interference, and enables adaptive bounding box transformation under frequency shifts. Accompanied by an open-source toolchain, the benchmark supports standardized data generation, augmentation, and multi-task evaluation—including classification, open-set recognition, and object detection—thereby substantially enhancing data diversity and task generality while promoting reproducibility and comparability in RF-based drone perception research.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

We present CageDroneRF (CDRF), a large-scale benchmark for Radio-Frequency (RF) drone detection and identification built from real-world captures and systematically generated synthetic variants. CDRF addresses the scarcity and limited diversity of existing RF datasets by coupling extensive raw recordings with a principled augmentation pipeline that (i) precisely controls Signal-to-Noise Ratio (SNR), (ii) injects interfering emitters, and (iii) applies frequency shifts with label-consistent bounding-box transformations for detection. This dataset spans a wide range of contemporary drone models, many unavailable in current public datasets, and acquisition conditions, derived from data collected at the Rowan University campus and within a controlled RF-cage facility. CDRF is released with interoperable open-source tools for data generation, preprocessing, augmentation, and evaluation that also operate on existing public benchmarks. CDRF enables standardized benchmarking for classification, open-set recognition, and object detection, supporting rigorous comparisons and reproducible pipelines. By releasing this comprehensive benchmark and tooling, CDRF aims to accelerate progress toward robust, generalizable RF perception models.

Problem

• RF drone detection
• dataset scarcity
• data diversity
• benchmarking
• radio-frequency perception

Innovation

• RF drone detection
• synthetic data augmentation
• signal-to-noise ratio control
• label-consistent frequency shift
• open-source benchmark toolkit