Localisation of Drone Controllers from RF Signals using a Deep Learning Approach

Despite their many uses, small commercial Unmanned Aerial Systems (UASs) or drones pose significant security risks. There is, therefore, a need to find methods of detecting, localising and countering these vehicles. This paper presents work towards autonomously localising drone controllers from the Radio Frequency (RF) signals they emit. An RF sensor array is used to monitor the signal spectrum. A Convolutional Neural Network (CNN) is trained to be able to predict the bearing of the drone controller, relative to the sensor, given its output. The position of the controllers can then be calculated from these bearings, provided that at least two such sensors are deployed a reasonable distance apart. The model is able to achieve a mean absolute error of 3.67° in bearing calculation, which translates into a moderate positional error of 40m at a range of 500m.

[1]  Young-Jun Lee,et al.  Empirical study of drone sound detection in real-life environment with deep neural networks , 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

[2]  Licia Capodiferro,et al.  Drone detection by acoustic signature identification , 2017, IMAWM.

[3]  Alonzo Kelly.  Precision Dilution in Triangulation Based Mobile Robot Position Estimation , 2003 .

[4]  R. Heersink.  An adaptive Bayesian approach towards a robust classifier for UAVs and birds , 2016 .

[5]  Michael Blumenstein,et al.  A study on detecting drones using deep convolutional neural networks , 2017, 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[6]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[7]  Daniel R. Ilgen,et al.  Team performance on monitoring tasks: An examination of decision errors in contexts requiring sustained attention. , 1995 .

[8]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[9]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[10]  Yongdae Kim,et al.  Security Analysis of FHSS-type Drone Controller , 2015, WISA.

[11]  Can Wang,et al.  Small UAV Detection in Videos from a Single Moving Camera , 2017, CCCV.

[12]  Junghyun Park,et al.  Real-time UAV sound detection and analysis system , 2017, 2017 IEEE Sensors Applications Symposium (SAS).

[13]  L. Fuhrmann,et al.  Micro-Doppler analysis and classification of UAVs at Ka band , 2017, 2017 18th International Radar Symposium (IRS).

[14]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[15]  Jin Wei,et al.  Deep learning cognitive radar for micro UAS detection and classification , 2017, 2017 Cognitive Communications for Aerospace Applications Workshop (CCAA).

[16]  Georg Dorffner,et al.  Neural Networks for Time Series Processing , 1996 .

[17]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[18]  François Chollet,et al.  Deep Learning with Python , 2017 .

[19]  Bart Custers,et al.  Drone Technology: Types, Payloads, Applications, Frequency Spectrum Issues and Future Developments , 2016 .

[20]  Waylon Dustin Scheller.  Detecting drones using machine learning , 2017 .

[21]  Peter König,et al.  Data augmentation instead of explicit regularization , 2018, ArXiv.

[22]  Richard Han,et al.  Cost-Effective and Passive RF-Based Drone Presence Detection and Characterization , 2018, GETMBL.

[23]  Ting Yao,et al.  Deep Learning for Video Classification and Captioning , 2016, Frontiers of Multimedia Research.

[24]  Andrew Y. Ng,et al.  Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks , 2017, ArXiv.

[25]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.