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

David Shorten; Ashley Williamson; Saket Srivastava; John C. Murray

doi:10.1145/3243250.3243272

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

David Shorten, Ashley Williamson, Saket Srivastava, John C. Murray

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

24 Citations (Scopus)

Abstract

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.

Original language	English
Title of host publication	Proceedings of 2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018
Publisher	Association for Computing Machinery
Pages	89-97
Number of pages	9
ISBN (Electronic)	9781450364829
DOIs	https://doi.org/10.1145/3243250.3243272
Publication status	Published - 15 Aug 2018
Externally published	Yes
Event	24th International Conference on Pattern Recognition and Artificial Intelligence - Beijing, China Duration: 20 Aug 2018 → 24 Aug 2018 https://ieeexplore.ieee.org/xpl/conhome/8527858/proceeding

Conference

Conference	24th International Conference on Pattern Recognition and Artificial Intelligence
Abbreviated title	PRAI 2018
Country/Territory	China
City	Beijing
Period	20/08/18 → 24/08/18
Internet address	https://ieeexplore.ieee.org/xpl/conhome/8527858/proceeding

Access to Document

10.1145/3243250.3243272Licence: Unspecified

Cite this

@inproceedings{1d5d977082254fcea07d0823db5bb405,

title = "Localisation of Drone Controllers from RF Signals using a Deep Learning Approach",

abstract = "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.",

keywords = "Convolutional Neural Network., Deep Learning, Drone, Radio, RF, Security, Surveillance, UAS",

author = "David Shorten and Ashley Williamson and Saket Srivastava and Murray, \{John C.\}",

note = "Publisher Copyright: {\textcopyright} 2018 Copyright is held by the owner/author(s).; 24th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018 ; Conference date: 20-08-2018 Through 24-08-2018",

year = "2018",

month = aug,

day = "15",

doi = "10.1145/3243250.3243272",

language = "English",

pages = "89--97",

booktitle = "Proceedings of 2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018",

publisher = "Association for Computing Machinery",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/8527858/proceeding",

}

Shorten, D, Williamson, A, Srivastava, S & Murray, JC 2018, Localisation of Drone Controllers from RF Signals using a Deep Learning Approach. in Proceedings of 2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018., 3243272, Association for Computing Machinery, pp. 89-97, 24th International Conference on Pattern Recognition and Artificial Intelligence, Beijing, China, 20/08/18. https://doi.org/10.1145/3243250.3243272

Localisation of Drone Controllers from RF Signals using a Deep Learning Approach. / Shorten, David; Williamson, Ashley; Srivastava, Saket et al.
Proceedings of 2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018. Association for Computing Machinery, 2018. p. 89-97 3243272.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Localisation of Drone Controllers from RF Signals using a Deep Learning Approach

AU - Shorten, David

AU - Williamson, Ashley

AU - Srivastava, Saket

AU - Murray, John C.

PY - 2018/8/15

Y1 - 2018/8/15

N2 - 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.

AB - 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.

KW - Convolutional Neural Network.

KW - Deep Learning

KW - Drone

KW - Radio

KW - RF

KW - Security

KW - Surveillance

KW - UAS

UR - https://www.scopus.com/pages/publications/85056691844

UR - https://dl.acm.org/doi/proceedings/10.1145/3243250

U2 - 10.1145/3243250.3243272

DO - 10.1145/3243250.3243272

M3 - Conference contribution

AN - SCOPUS:85056691844

SP - 89

EP - 97

BT - Proceedings of 2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018

PB - Association for Computing Machinery

T2 - 24th International Conference on Pattern Recognition and Artificial Intelligence

Y2 - 20 August 2018 through 24 August 2018

ER -

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

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this