DEEP LIDAR ODOMETRY

Abstract. Most existing lidar odometry estimation strategies are formulated under a standard framework that includes feature selection, and pose estimation through feature matching. In this work, we present a novel pipeline called LO-Net for lidar odometry estimation from 3D lidar scanning data using deep convolutional networks. The network is trained in an end-to-end manner, it infers 6-DoF poses from the encoded sequential lidar data. Based on the new designed mask-weighted geometric constraint loss, the network automatically learns effective feature representation for the lidar odometry estimation problem, and implicitly exploits the sequential dependencies and dynamics. Experiments on benchmark datasets demonstrate that LO-Net has similar accuracy with the geometry-based approach.

[1]  Noah Snavely,et al.  Unsupervised Learning of Depth and Ego-Motion from Video , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Sen Wang,et al.  DeepVO: Towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[4]  Roberto Cipolla,et al.  Geometric Loss Functions for Camera Pose Regression with Deep Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Adam Herout,et al.  CNN for IMU assisted odometry estimation using velodyne LiDAR , 2017, 2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC).

[6]  Wei Xu,et al.  Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency , 2017, ArXiv.

[7]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[8]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[9]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[11]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[12]  Edwin Olson,et al.  Fast iterative alignment of pose graphs with poor initial estimates , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[13]  Roland Siegwart,et al.  Comparing ICP variants on real-world data sets , 2013, Auton. Robots.

[14]  Jörg Stückler,et al.  Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry , 2018, ECCV.

[15]  Ji Wan,et al.  Multi-view 3D Object Detection Network for Autonomous Driving , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Jean-Emmanuel Deschaud,et al.  IMLS-SLAM: Scan-to-Model Matching Based on 3D Data , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Kurt Konolige,et al.  g 2 o: A general Framework for (Hyper) Graph Optimization , 2011 .

[18]  Tom Duckett,et al.  A multilevel relaxation algorithm for simultaneous localization and mapping , 2005, IEEE Transactions on Robotics.

[19]  Ryan M. Eustice,et al.  Ford Campus vision and lidar data set , 2011, Int. J. Robotics Res..

[20]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[21]  Wei Xu,et al.  LEGO: Learning Edge with Geometry all at Once by Watching Videos , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[22]  Yuan Wang,et al.  PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud , 2018, ArXiv.

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[24]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[25]  Frank Moosmann,et al.  Interlacing Self-Localization, Moving Object Tracking and Mapping for 3D Range Sensors , 2013 .

[26]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[27]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[28]  Roberto Cipolla,et al.  PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[29]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[30]  Ji Zhang,et al.  LOAM: Lidar Odometry and Mapping in Real-time , 2014, Robotics: Science and Systems.

[31]  Wolfram Burgard,et al.  Deep Auxiliary Learning for Visual Localization and Odometry , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[32]  Ji Zhang,et al.  Low-drift and real-time lidar odometry and mapping , 2017, Auton. Robots.

[33]  Adam Herout,et al.  Collar Line Segments for fast odometry estimation from Velodyne point clouds , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[34]  Zhichao Yin,et al.  GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.