More Datasets

Dataset-28: Multi-Modal RF Sensor and Radar Dataset for UAV Tracking

2025
2025, 3.3 GHz, Drone, Localization, Rural, Student Challenge Dataset, Trajectory
KRSE3: TDOA-Based Source Localization

Lead Experimenter

Cole Dickerson, North Carolina State University

Link to Dataset

The dataset includes position estimates from the Fortem TrueView R20 radar and Keysight N6841A RF sensors, as well as ground-truth data collected by the UAV. The dataset can be accessed here [link].

Equipment and Software Used

Keysight N6841A RF Sensors, Fortem TrueView R20 Radar, Keysight Geolocation Software

Description

This dataset contains measurements from UAV tracking experiments conducted across 33 AADM ( AERPAW Autonomous Data Mule) flights at the Lake Wheeler field site. These experiments were designed to evaluate multi-modal UAV detection and tracking performance using passive Keysight N6841A RF sensors and a Fortem TrueView R20 radar. In addition to the AADM missions, three supplementary flights were performed specifically to optimize RF sensor placement, geometry, and signal reception. The combined dataset provides ground-truth trajectories, RF sensor position estimates, and radar measurements for UAVs operating under diverse flight patterns.

Publications

  1. C. Dickerson, S. Kearney, S. Manjur, I. Guvenc, S. Gurbuz, A. Gurbuz, O. Ozdemir, and M. Sichitiu, “Fusion of Cellular ISAC and Passive RF Sensing for UAV Detection and Tracking,” in Proc. IEEE Asilomar Conf. Signals, Systems, and Computers, Pacific Grove, CA, USA, 2025, Session: UAV Intrusion Detection Using Mobile Communications Networks.

Representative Results

Representative experimental results from our UAV sensing study are shown here. These figures illustrate the UAV flight trajectory at the AERPAW test site, RF sensor geolocation estimates, and the resulting tracking errors for both RF sensing and radar measurements.

Potential use cases for this dataset include:

  • Benchmarking RF-based UAV localization algorithms
  • Evaluating tracking and filtering methods
  • Developing multi-sensor fusion approaches
  • Validating theoretical localization bounds in real flight conditions