Voxelized GICP for Fast and Accurate 3D Point Cloud Registration

This paper proposes the voxelized generalized iterative closest point (VGICP) algorithm for fast and accurate three-dimensional point cloud registration. The proposed approach extends the generalized iterative closest point (GICP) approach with voxelization to avoid costly nearest neighbor search while retaining its accuracy. In contrast to the normal distributions transform (NDT), which calculates voxel distributions from point positions, we estimate voxel distributions by aggregating the distribution of each point in the voxel. The voxelization approach allows us to efficiently process the optimization in parallel, and the proposed algorithm can run at 30 Hz on a CPU and 120 Hz on a GPU. Through evaluations in simulated and real environments, we confirmed that the accuracy of the proposed algorithm is comparable to GICP, but is substantially faster than existing methods. This will enable the development of real-time 3D LIDAR applications that require extremely fast evaluations of the relative poses between LIDAR frames.

[1]  Andreas Birk,et al.  Beyond points: Evaluating recent 3D scan-matching algorithms , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[2]  Takashi Tsubouchi,et al.  A 3-D Scan Matching using Improved 3-D Normal Distributions Transform for Mobile Robotic Mapping , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Davide Scaramuzza,et al.  A Tutorial on Quantitative Trajectory Evaluation for Visual(-Inertial) Odometry , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  Giorgio Grisetti,et al.  NICP: Dense normal based point cloud registration , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[5]  Pavel Krsek,et al.  The Trimmed Iterative Closest Point algorithm , 2002, Object recognition supported by user interaction for service robots.

[6]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Joachim Hertzberg,et al.  Evaluation of 3D registration reliability and speed - A comparison of ICP and NDT , 2009, 2009 IEEE International Conference on Robotics and Automation.

[8]  Achim J. Lilienthal,et al.  Fast and accurate scan registration through minimization of the distance between compact 3D NDT representations , 2012, Int. J. Robotics Res..

[9]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

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

[11]  Ashish Kapoor,et al.  AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles , 2017, FSR.

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

[13]  Brendan Englot,et al.  LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[14]  Aleksandr V. Segal,et al.  Generalized-ICP , 2009, Robotics: Science and Systems.

[15]  Peter Biber,et al.  The normal distributions transform: a new approach to laser scan matching , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[16]  Federico Tombari,et al.  SHOT: Unique signatures of histograms for surface and texture description , 2014, Comput. Vis. Image Underst..