Publication detail

CNN for IMU Assisted Odometry Estimation using Velodyne LiDAR

VEĽAS, M. ŠPANĚL, M. HRADIŠ, M. HEROUT, A.

Original Title

CNN for IMU Assisted Odometry Estimation using Velodyne LiDAR

English Title

CNN for IMU Assisted Odometry Estimation using Velodyne LiDAR

Type

conference paper

Language

en

Original Abstract

We introduce a novel method for odometry estimation using convolutional neural networks from 3D LiDAR scans. The original sparse data are encoded into 2D matrices for the training of proposed networks and for the prediction. Our networks show significantly better precision in the estimation of translational motion parameters comparing with state of the art method LOAM, while achieving real-time performance. Together with IMU support, high quality odometry estimation and LiDAR data registration is realized. Moreover, we propose alternative CNNs trained for the prediction of rotational motion parameters while achieving results also comparable with state of the art. The proposed method can replace wheel encoders in odometry estimation or supplement missing GPS data, when the GNSS signal absents (e.g. during the indoor mapping). Our solution brings real-time performance and precision which are useful to provide online preview of the mapping results and verification of the map completeness in real time.

English abstract

We introduce a novel method for odometry estimation using convolutional neural networks from 3D LiDAR scans. The original sparse data are encoded into 2D matrices for the training of proposed networks and for the prediction. Our networks show significantly better precision in the estimation of translational motion parameters comparing with state of the art method LOAM, while achieving real-time performance. Together with IMU support, high quality odometry estimation and LiDAR data registration is realized. Moreover, we propose alternative CNNs trained for the prediction of rotational motion parameters while achieving results also comparable with state of the art. The proposed method can replace wheel encoders in odometry estimation or supplement missing GPS data, when the GNSS signal absents (e.g. during the indoor mapping). Our solution brings real-time performance and precision which are useful to provide online preview of the mapping results and verification of the map completeness in real time.

Keywords

ground segmentation, LiDAR, Velodyne, convolutional neural network

Released

27.04.2018

Publisher

Institute of Electrical and Electronics Engineers

Location

Torres Vedras

ISBN

978-1-5386-5221-3

Book

IEEE International Conference on Autonomous Robot Systems and Competitions

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

71

Pages to

77

Pages count

7

URL

Documents

BibTex


@inproceedings{BUT157179,
  author="Martin {Veľas} and Michal {Španěl} and Michal {Hradiš} and Adam {Herout}",
  title="CNN for IMU Assisted Odometry Estimation using Velodyne LiDAR",
  annote="We introduce a novel method for odometry estimation using convolutional neural
networks from 3D LiDAR scans. The original sparse data are encoded into 2D
matrices for the training of proposed networks and for the prediction. Our
networks show significantly better precision in the estimation of translational
motion parameters comparing with state of the art method LOAM, while achieving
real-time performance. Together with IMU support, high quality odometry
estimation and LiDAR data registration is realized. Moreover, we propose
alternative CNNs trained for the prediction of rotational motion parameters while
achieving results also comparable with state of the art. The proposed method can
replace wheel encoders in odometry estimation or supplement missing GPS data,
when the GNSS signal absents (e.g. during the indoor mapping). Our solution
brings real-time performance and precision which are useful to provide online
preview of the mapping results and verification of the map completeness in real
time.",
  address="Institute of Electrical and Electronics Engineers",
  booktitle="IEEE International Conference on Autonomous Robot Systems and Competitions",
  chapter="157179",
  doi="10.1109/ICARSC.2018.8374163",
  edition="NEUVEDEN",
  howpublished="online",
  institution="Institute of Electrical and Electronics Engineers",
  number="4",
  year="2018",
  month="april",
  pages="71--77",
  publisher="Institute of Electrical and Electronics Engineers",
  type="conference paper"
}