Learning to Localize Using a LiDAR Intensity Map

Ioan Andrei Barsan, Shenlong Wang, Andrei Pokrovsky, Raquel Urtasun
; Proceedings of The 2nd Conference on Robot Learning, PMLR 87:605-616, 2018.

Abstract

In this paper we propose a real-time, calibration-agnostic and effective localization system for self-driving cars. Our method learns to embed the online LiDAR sweeps and intensity map into a joint deep embedding space. Localization is then conducted through an efficient convolutional matching between the embeddings. Our full system can operate in real-time at 15Hz while achieving centimeter level accuracy across different LiDAR sensors and environments. Our experiments illustrate the performance of the proposed approach over a large-scale dataset consisting of over 4000km of driving.

Cite this Paper


BibTeX
@InProceedings{pmlr-v87-barsan18a, title = {Learning to Localize Using a LiDAR Intensity Map}, author = {Barsan, Ioan Andrei and Wang, Shenlong and Pokrovsky, Andrei and Urtasun, Raquel}, booktitle = {Proceedings of The 2nd Conference on Robot Learning}, pages = {605--616}, year = {2018}, editor = {Aude Billard and Anca Dragan and Jan Peters and Jun Morimoto}, volume = {87}, series = {Proceedings of Machine Learning Research}, address = {}, month = {29--31 Oct}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v87/barsan18a/barsan18a.pdf}, url = {http://proceedings.mlr.press/v87/barsan18a.html}, abstract = {In this paper we propose a real-time, calibration-agnostic and effective localization system for self-driving cars. Our method learns to embed the online LiDAR sweeps and intensity map into a joint deep embedding space. Localization is then conducted through an efficient convolutional matching between the embeddings. Our full system can operate in real-time at 15Hz while achieving centimeter level accuracy across different LiDAR sensors and environments. Our experiments illustrate the performance of the proposed approach over a large-scale dataset consisting of over 4000km of driving. } }
Endnote
%0 Conference Paper %T Learning to Localize Using a LiDAR Intensity Map %A Ioan Andrei Barsan %A Shenlong Wang %A Andrei Pokrovsky %A Raquel Urtasun %B Proceedings of The 2nd Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2018 %E Aude Billard %E Anca Dragan %E Jan Peters %E Jun Morimoto %F pmlr-v87-barsan18a %I PMLR %J Proceedings of Machine Learning Research %P 605--616 %U http://proceedings.mlr.press %V 87 %W PMLR %X In this paper we propose a real-time, calibration-agnostic and effective localization system for self-driving cars. Our method learns to embed the online LiDAR sweeps and intensity map into a joint deep embedding space. Localization is then conducted through an efficient convolutional matching between the embeddings. Our full system can operate in real-time at 15Hz while achieving centimeter level accuracy across different LiDAR sensors and environments. Our experiments illustrate the performance of the proposed approach over a large-scale dataset consisting of over 4000km of driving.
APA
Barsan, I.A., Wang, S., Pokrovsky, A. & Urtasun, R.. (2018). Learning to Localize Using a LiDAR Intensity Map. Proceedings of The 2nd Conference on Robot Learning, in PMLR 87:605-616

Related Material