CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure

被引:111
作者
Dellenbach, Pierre [1 ,2 ]
Deschaud, Jean-Emmanuel [1 ]
Jacquet, Bastien [2 ]
Goulette, Francois [1 ]
机构
[1] PSL Univ, Ctr Robot, MINES ParisTech, F-75006 Paris, France
[2] Comp Vis Team, Kitware, F-69100 Villeurbanne, France
来源
2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022) | 2022年
关键词
D O I
10.1109/ICRA46639.2022.9811849
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Multi-beam LiDAR sensors are increasingly used in robotics, particularly with autonomous cars for localization and perception tasks, both relying on the ability to build a precise map of the environment. For this, we propose a new real-time LiDAR-only odometry method called CT-ICP (for Continuous-Time ICP), completed into a full SLAM with a novel loop detection procedure. The core of this method, is the introduction of the combined continuity in the scan matching, and discontinuity between scans. It allows both the elastic distortion of the scan during the registration for increased precision, and the increased robustness to high frequency motions from the discontinuity. We build a complete SLAM on top of this odometry, using a fast pure LiDAR loop detection based on elevation image 2D matching, providing a pose graph with loop constraints. To show the robustness of the method, we tested it on seven datasets: KITTI, KITTI-raw, KITTI-360, KITTI-CARLA, ParisLuco, Newer College, and NCLT in driving and high-frequency motion scenarios. Both the CT-ICP odometry and the loop detection are made available online. CT-ICP is currently first, among those giving access to a public code, on the KITTI odometry leaderboard, with an average Relative Translation Error (RTE) of 0.59% and an average time per scan of 60ms on a CPU with a single thread.
引用
收藏
页码:5580 / 5586
页数:7
相关论文
共 34 条
  • [1] Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces
    Alcantarilla, Pablo F.
    Nuevo, Jesus
    Bartoli, Adrien
    [J]. PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2013, 2013,
  • [2] Alismail H, 2014, IEEE INT CONF ROBOT, P6096, DOI 10.1109/ICRA.2014.6907757
  • [3] Behley J, 2018, ROBOTICS: SCIENCE AND SYSTEMS XIV
  • [4] A METHOD FOR REGISTRATION OF 3-D SHAPES
    BESL, PJ
    MCKAY, ND
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (02) : 239 - 256
  • [5] Bosse M, 2009, IEEE INT CONF ROBOT, P4244
  • [6] Caesar H, 2020, PROC CVPR IEEE, P11618, DOI 10.1109/CVPR42600.2020.01164
  • [7] University of Michigan North Campus long-term vision and lidar dataset
    Carlevaris-Bianco, Nicholas
    Ushani, Arash K.
    Eustice, Ryan M.
    [J]. INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2016, 35 (09) : 1023 - 1035
  • [8] Chen X., 2020, P ROBOTICS SCI SYSTE, P5586
  • [9] Chen XYL, 2019, IEEE INT C INT ROBOT, P4530, DOI 10.1109/IROS40897.2019.8967704
  • [10] What's in My LiDAR Odometry Toolbox?
    Dellenbach, Pierre
    Deschaud, Jean-Emmanuel
    Jacquet, Bastien
    Goulette, Francois
    [J]. 2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2021, : 4429 - 4436