FMCW Radar Sensing for Indoor Drones Using Variational Auto-Encoders

Ali Safa; Tim Verbelen; Ozan Catal; Toon Van De Maele; Matthias Hartmann; Bart Dhoedt; Andre Bourdoux

doi:10.1109/RadarConf2351548.2023.10149738

FMCW Radar Sensing for Indoor Drones Using Variational Auto-Encoders

Ali Safa, Tim Verbelen, Ozan Catal, Toon Van De Maele, Matthias Hartmann, Bart Dhoedt, Andre Bourdoux

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

5 Citations (Scopus)

Abstract

This paper investigates unsupervised learning of low-dimensional representations from FMCW radar data, which can be used for multiple downstream tasks in a drone navigation context. To this end, we release a first-of-its-kind dataset of raw radar ADC data recorded from a radar mounted on a flying drone in an indoor environment, together with ground truth detection targets. We show that, by utilizing our learned representations, we match the performance of conventional radar processing techniques while training our models on different input modalities such as range-doppler maps, range-azimuth maps, or raw ADC samples of only two consecutively transmitted chirps.

Original language	English
Title of host publication	2023 Ieee Radar Conference, Radarconf23
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	6
ISBN (Electronic)	9781665436694
DOIs	https://doi.org/10.1109/RadarConf2351548.2023.10149738
Publication status	Published - 2023
Externally published	Yes
Event	2023 IEEE Radar Conference, RadarConf23 - San Antonia, United States Duration: 1 May 2023 → 5 May 2023

Publication series

Name	Proceedings of the IEEE Radar Conference
Volume	2023-May
ISSN (Print)	1097-5764
ISSN (Electronic)	2375-5318

Conference

Conference	2023 IEEE Radar Conference, RadarConf23
Country/Territory	United States
City	San Antonia
Period	1/05/23 → 5/05/23

Keywords

Deep learning
Drone navigation
Indoor sensing
Variational autoencoder
Velocity and angle estimation

Access to Document

10.1109/RadarConf2351548.2023.10149738

Cite this

Safa, A., Verbelen, T., Catal, O., Van De Maele, T., Hartmann, M., Dhoedt, B., & Bourdoux, A. (2023). FMCW Radar Sensing for Indoor Drones Using Variational Auto-Encoders. In 2023 Ieee Radar Conference, Radarconf23 (Proceedings of the IEEE Radar Conference; Vol. 2023-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RadarConf2351548.2023.10149738

@inproceedings{876bf42c3efd4a3bad1d346d41007783,

title = "FMCW Radar Sensing for Indoor Drones Using Variational Auto-Encoders",

abstract = "This paper investigates unsupervised learning of low-dimensional representations from FMCW radar data, which can be used for multiple downstream tasks in a drone navigation context. To this end, we release a first-of-its-kind dataset of raw radar ADC data recorded from a radar mounted on a flying drone in an indoor environment, together with ground truth detection targets. We show that, by utilizing our learned representations, we match the performance of conventional radar processing techniques while training our models on different input modalities such as range-doppler maps, range-azimuth maps, or raw ADC samples of only two consecutively transmitted chirps.",

keywords = "Deep learning, Drone navigation, Indoor sensing, Variational autoencoder, Velocity and angle estimation",

author = "Ali Safa and Tim Verbelen and Ozan Catal and {Van De Maele}, Toon and Matthias Hartmann and Bart Dhoedt and Andre Bourdoux",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Radar Conference, RadarConf23 ; Conference date: 01-05-2023 Through 05-05-2023",

year = "2023",

doi = "10.1109/RadarConf2351548.2023.10149738",

language = "English",

series = "Proceedings of the IEEE Radar Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 Ieee Radar Conference, Radarconf23",

address = "United States",

}

Safa, A, Verbelen, T, Catal, O, Van De Maele, T, Hartmann, M, Dhoedt, B & Bourdoux, A 2023, FMCW Radar Sensing for Indoor Drones Using Variational Auto-Encoders. in 2023 Ieee Radar Conference, Radarconf23. Proceedings of the IEEE Radar Conference, vol. 2023-May, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE Radar Conference, RadarConf23, San Antonia, United States, 1/05/23. https://doi.org/10.1109/RadarConf2351548.2023.10149738

FMCW Radar Sensing for Indoor Drones Using Variational Auto-Encoders. / Safa, Ali; Verbelen, Tim; Catal, Ozan et al.
2023 Ieee Radar Conference, Radarconf23. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings of the IEEE Radar Conference; Vol. 2023-May).

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

TY - GEN

T1 - FMCW Radar Sensing for Indoor Drones Using Variational Auto-Encoders

AU - Safa, Ali

AU - Verbelen, Tim

AU - Catal, Ozan

AU - Van De Maele, Toon

AU - Hartmann, Matthias

AU - Dhoedt, Bart

AU - Bourdoux, Andre

PY - 2023

Y1 - 2023

N2 - This paper investigates unsupervised learning of low-dimensional representations from FMCW radar data, which can be used for multiple downstream tasks in a drone navigation context. To this end, we release a first-of-its-kind dataset of raw radar ADC data recorded from a radar mounted on a flying drone in an indoor environment, together with ground truth detection targets. We show that, by utilizing our learned representations, we match the performance of conventional radar processing techniques while training our models on different input modalities such as range-doppler maps, range-azimuth maps, or raw ADC samples of only two consecutively transmitted chirps.

AB - This paper investigates unsupervised learning of low-dimensional representations from FMCW radar data, which can be used for multiple downstream tasks in a drone navigation context. To this end, we release a first-of-its-kind dataset of raw radar ADC data recorded from a radar mounted on a flying drone in an indoor environment, together with ground truth detection targets. We show that, by utilizing our learned representations, we match the performance of conventional radar processing techniques while training our models on different input modalities such as range-doppler maps, range-azimuth maps, or raw ADC samples of only two consecutively transmitted chirps.

KW - Deep learning

KW - Drone navigation

KW - Indoor sensing

KW - Variational autoencoder

KW - Velocity and angle estimation

UR - http://www.scopus.com/inward/record.url?scp=85163748664&partnerID=8YFLogxK

U2 - 10.1109/RadarConf2351548.2023.10149738

DO - 10.1109/RadarConf2351548.2023.10149738

M3 - Conference contribution

AN - SCOPUS:85163748664

T3 - Proceedings of the IEEE Radar Conference

BT - 2023 Ieee Radar Conference, Radarconf23

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Radar Conference, RadarConf23

Y2 - 1 May 2023 through 5 May 2023

ER -

FMCW Radar Sensing for Indoor Drones Using Variational Auto-Encoders

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this