Loop closure with a low power millimeter wave radar sensor using an autoencoder

Pieter Meiresone, David Van Hamme, Wilfried Philips
Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), PMLR 233:153-157, 2024.

Abstract

In this paper, we will consider place recognition, more commonly know as loop closure, with a low resolution single-chip millimeter wave (mmWave) radar in indoor environments. It is an essential part in simultaneous localization and mapping (SLAM) systems to avoid drift. By using a novel method to create descriptors or latent codes with an autoencoder in combination with exploiting the temporal similarity between our latent codes, we are able to successfully extract loop closures with a radar-only system without requiring ground truth. Our proposed method is validated in an industrial IoT lab on an Unmanned Aerial Vehicle (UAV) and on a cargo bike in a parking building.

Cite this Paper

BibTeX
@InProceedings{pmlr-v233-meiresone24a, title = {Loop closure with a low power millimeter wave radar sensor using an autoencoder}, author = {Meiresone, Pieter and Hamme, David Van and Philips, Wilfried}, booktitle = {Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL})}, pages = {153--157}, year = {2024}, editor = {Lutchyn, Tetiana and Ramírez Rivera, Adín and Ricaud, Benjamin}, volume = {233}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jan}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v233/meiresone24a/meiresone24a.pdf}, url = {https://proceedings.mlr.press/v233/meiresone24a.html}, abstract = {In this paper, we will consider place recognition, more commonly know as loop closure, with a low resolution single-chip millimeter wave (mmWave) radar in indoor environments. It is an essential part in simultaneous localization and mapping (SLAM) systems to avoid drift. By using a novel method to create descriptors or latent codes with an autoencoder in combination with exploiting the temporal similarity between our latent codes, we are able to successfully extract loop closures with a radar-only system without requiring ground truth. Our proposed method is validated in an industrial IoT lab on an Unmanned Aerial Vehicle (UAV) and on a cargo bike in a parking building.} }
Endnote
%0 Conference Paper %T Loop closure with a low power millimeter wave radar sensor using an autoencoder %A Pieter Meiresone %A David Van Hamme %A Wilfried Philips %B Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}) %C Proceedings of Machine Learning Research %D 2024 %E Tetiana Lutchyn %E Adín Ramírez Rivera %E Benjamin Ricaud %F pmlr-v233-meiresone24a %I PMLR %P 153--157 %U https://proceedings.mlr.press/v233/meiresone24a.html %V 233 %X In this paper, we will consider place recognition, more commonly know as loop closure, with a low resolution single-chip millimeter wave (mmWave) radar in indoor environments. It is an essential part in simultaneous localization and mapping (SLAM) systems to avoid drift. By using a novel method to create descriptors or latent codes with an autoencoder in combination with exploiting the temporal similarity between our latent codes, we are able to successfully extract loop closures with a radar-only system without requiring ground truth. Our proposed method is validated in an industrial IoT lab on an Unmanned Aerial Vehicle (UAV) and on a cargo bike in a parking building.
APA
Meiresone, P., Hamme, D.V. & Philips, W.. (2024). Loop closure with a low power millimeter wave radar sensor using an autoencoder. Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), in Proceedings of Machine Learning Research 233:153-157 Available from https://proceedings.mlr.press/v233/meiresone24a.html.

Related Material