摘要

本文提出了一种基于增量体素的激光惯性里程计（LIO）方法，用于快速跟踪旋转和固态激光雷达。为了实现快速的跟踪速度，我们既没有使用复杂的基于树的结构来划分空间点云，也没有使用严格的k最近邻(k-NN)查询计算点匹配。相反，我们使用增量体素(iVox)作为我们的点云空间数据结构（增量体素是对传统体素的修改、支持增量插入和并行近似k-NN查找）。我们把线性iVox和PHC（伪希尔伯特曲线）iVox作为我们算法两种可选的底层数据结构。实验结果表明，仅仅使用现代的CPU，iVox在固态激光雷达中的每次扫描中可以达到1000~2000hz，而32线激光雷达则超过了200hz，同时仍保持相同水平的精度。

1 简介

2 相关工作

3 IVox:Incremental Sparse Voxels

A. IVox的数据结构

B. k-NN搜索

C. 增量地图

4 IVox-PHC

A. iVox-PHC的底层结构

B. iVox-PHC的k-NN搜索

C. iVox-PHC和iVox的复杂度

5 实验

6 结论

7 参考文献

[1] C. Le Gentil, T. Vidal-Calleja, and S. Huang, “IN2LAAMA: Inertial LiDAR localization autocalibration and mapping,” IEEE Trans. Robot., vol. 37, no. 1, pp. 275–290, Feb. 2021.
[2] M. Yokozuka, K. Koide, S. Oishi, and A. Banno, “LiTAMIN: LiDARbased tracking and mapping by stabilized ICP for geometry approximation with normal distributions,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst. 2020, pp. 5143–5150.
[3] G. Xiang et al., “Fully automatic large-scale point cloud mapping for low-speed self-driving vehicles in unstructured environments,” in Proc. IEEE Intell. Veh. Symp., 2021, pp. 881–888.
[4] P. Wei, X. Wang, and Y. Guo, “3D-LIDAR feature based localization for autonomous vehicles,” in Proc. IEEE 16th Int. Conf. Automat. Sci. Eng., 2020, pp. 288–293.
[5] X. Zheng and J. Zhu, “Efficient LiDAR odometry for autonomous driving,” IEEE Robot. Automat. Lett. vol. 6, no. 4, pp. 8458–8465, Oct. 2021, arXiv:2104.10879.
[6] J. Zhang and S. Singh, “LOAM: LiDAR odometry and mapping in realtime,” in Robot.: Sci. Syst., vol. 2, no. 9, pp. 1–9, 2014.
[7] T. Shan and B. Englot, “LeGO-LOAM: Lightweight and ground-optimized LiDAR odometry and mapping on variable terrain,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2018, pp. 4758–4765.
[8] Z. Liu and F. Zhang, “BALM: Bundle adjustment for LiDAR mapping,” IEEE Robot. Automat. Lett., vol. 6, no. 2, pp. 3184–3191, Apr. 2021.
[9] Z. Liu, F. Zhang, and X. Hong, “Low-cost retina-like robotic LiDARs based on incommensurable scanning,” IEEE/ASME Trans. Mechatronics, vol. 27, no. 1, pp. 58–68, Feb. 2022.
[10] D. Wang, C. Watkins, and H. Xie, “MEMS mirrors for LiDAR: A review,” Micromachines, vol. 11, no. 5, p. 456, 2020.
[11] K. Li, M. Li, and U. D. Hanebeck, “Towards high-performance solidstate-LiDAR-inertial odometry andmapping,” IEEE Robot. Automat. Lett., vol. 6, no. 3, pp. 5167–5174, Jul. 2021.
[12] D. V. Nam and K. Gon-Woo, “Solid-state LiDAR based-SLAM: A concise review and application,” in Proc. IEEE Int. Conf. Big Data Smart Comput., 2021, pp. 302–305.
[13] P. Geneva, K. Eckenhoff, Y. Yang, and G. Huang, “Lips: LiDAR-inertial 3D plane SLAM,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2018, pp. 123–130.
[14] N. Rufus, U. K. R. Nair, A. S. B. Kumar, V. Madiraju, and K. M. Krishna, “SROM: Simple real-time odometry and mapping using LiDAR data for autonomous vehicles,” in Proc. IEEE Intell. Veh. Symp., 2020, pp. 1867–1872.
[15] W. Wang, J. Liu, C. Wang, B. Luo, and C. Zhang, “DV-LOAM: Direct visual LiDAR odometry and mapping,” Remote Sens., vol. 13, no. 16, 2021, Art. no. 3340.
[16] S. Hening, C. A. Ippolito, K. S. Krishnakumar, V. Stepanyan, and M. Teodorescu, “3D LiDAR SLAM integration with GPS/INS for UAVs in urban GPS-degraded environments,” in Proc. AIAA Inf. Syst.-AIAA Infotech, Aerosp., 2017, Art. no. 0448.
[17] C. Qian et al., “An integrated GNSS/INS/LiDAR-SLAM positioning method for highly accurate forest stem mapping,” Remote Sens., vol. 9, no. 1, p. 3, 2017.
[18] W. Xu, Y. Cai, D. He, J. Lin, and F. Zhang, “FAST-LIO2: Fast direct LiDAR-inertial odometry,” IEEE Trans. Robot., 2022.
[19] X. Huang, G. Mei, J. Zhang, and R. Abbas, “A comprehensive survey on point cloud registration,” 2021, arXiv:2103.02690.
[20] N. Beckmann, H.-P. Kriegel, R. Schneider, and B. Seeger, “The R*-tree: An efficient and robust access method for points and rectangles,” in Proc. ACM SIGMOD Int. Conf. Manage. Data, 1990, pp. 322–331.
[21] M. Dolatshah, A. Hadian, and B. Minaei-Bidgoli, “Ball*-tree: Efficient spatial indexing for constrained nearest-neighbor search in metric spaces,” 2015, arXiv:1511.00628.
[22] K. Koide, M. Yokozuka, S. Oishi, and A. Banno, “Voxelized GICP for fast and accurate 3D point cloud registration,” in Proc. IEEE Int. Conf. Robot. Automat., 2021, pp. 11054–11059.
[23] Y. Cai, W. Xu, and F. Zhang, “ikd-Tree: An incremental KD tree for robotic applications,” 2021, arXiv:2102.10808.
[24] T. Shan, B. Englot, D. Meyers, W. Wang, C. Ratti, and D. Rus, “LIO-SAM: Tightly-coupled LiDAR inertial odometry via smoothing and mapping,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2020, pp. 5135–5142.
[25] X. Zuo, P. Geneva, W. Lee, Y. Liu, and G. Huang, “LIC-Fusion: LiDARinertial-camera odometry,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2019, pp. 5848–5854.
[26] W. Xu and F. Zhang, “FAST-LIO: A fast, robust LiDAR-inertial odometry package by tightly-coupled iterated Kalman filter,” IEEE Robot. Automat. Lett., vol. 6, no. 2, pp. 3317–3324, Apr. 2021.
[27] Y. Pan, P. Xiao, Y. He, Z. Shao, and Z. Li, “MULLS: Versatile LiDAR SLAM viamulti-metric linear least square,” inProc.IEEEInt. Conf. Robot. Automat.2021, pp. 11633–11640, arXiv:2102.03771.
[28] S. Zhao, Z. Fang, H. Li, and S. Scherer, “A robust laser-inertial odometry and mapping method for large-scale highway environments,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2019, pp. 1285–1292.

[29] M. Yokozuka, K. Koide, S. Oishi, and A. Banno, “LITAMIN2: Ultra light LiDAR-based SLAM using geometric approximation applied with KL-divergence,” in Proc. IEEE Int. Conf. Robot. Automat. 2021, pp. 11619–11625, arXiv:2103.00784.
[30] K. Koide, M. Yokozuka, S. Oishi, and A. Banno, “Globally consistent 3D LiDAR mapping with GPU-accelerated GICP matching cost factors,” IEEE Robot. Automat. Lett., vol. 6, no. 4, pp. 8591–8598, Oct. 2021.
[31] M. Karimi, M. Oelsch, O. Stengel, E. Babaians, and E. Steinbach, “LoLaSLAM: Low-latency LiDAR SLAM using continuous scan slicing,” IEEE Robot. Automat. Lett., vol. 6, no. 2, pp. 2248–2255, Apr. 2021.
[32] C. Qu, S. S. Shivakumar, W. Liu, and C. J. Taylor, “LLOL: Low-latency odometry for spinning LiDARs,” 2021, arXiv:2110.01725.
[33] Q. Li et al., “LO-Net: Deep real-time LiDAR odometry,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 2019, pp. 8473–8482.
[34] C. Choy, W. Dong, and V. Koltun, “Deep global registration,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 2020, pp. 2514–2523.
[35] M.Muglikar,Z.Zhang, andD. Scaramuzza, “Voxelmapfor visual SLAM,” in Proc. IEEE Int. Conf. Robot. Automat., 2020, pp. 4181–4187.
[36] M. Nießner, M. Zollhöfer, S. Izadi, and M. Stamminger, “Real-time 3D reconstruction at scale using voxel hashing,” ACM Trans. Graph., vol. 32, no. 6, pp. 1–11, 2013.
[37] K. Daun, S. Kohlbrecher, J. Sturm, and O. von Stryk, “Large scale 2D laser SLAM using truncated signed distance functions,” in Proc. IEEE Int. Symp. Saf., Secur., Rescue Robot., 2019, pp. 222–228.
[38] M. Teschner, B. Heidelberger, M. Müller, D. Pomerantes, and M. H. Gross, “Optimized spatial hashing for collision detection of deformable objects,” in Proc. Vis., Model., Visual. Conf., 2003, vol. 3, pp. 47–54.
[39] H.-L. Chen and Y.-I. Chang, “Neighbor-finding based on space-filling curves,” Inf. Syst., vol. 30, no. 3, pp. 205–226, 2005.
[40] H.-L. Chen and Y.-I. Chang, “All-nearest-neighbors finding based on the Hilbert curve,” Expert Syst. Appl., vol. 38, no. 6, pp. 7462–7475, 2011.
[41] N. Carlevaris-Bianco, A. K. Ushani, and R. M. Eustice, “University of Michigan North Campus long-term vision and LiDAR dataset,” Int. J. Robot. Res., vol. 35, no. 9, pp. 1023–1035, 2015.
[42] W. Wen et al., “UrbanLoco: A full sensor suite dataset for mapping and localization in urban scenes,” in Proc. IEEE Int. Conf. Robot. Automat., 2020, pp. 2310–2316.
[43] Z. Yan, L. Sun, T. Krajnik, and Y. Ruichek, “EU long-term dataset with multiple sensors for autonomous driving,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2020, pp. 10697–10704.
[44] R. B. Rusu and S. Cousins, “3D is here: Point cloud library (PCL),” in Proc. IEEE Int. Conf. Robot. Automat., 2011, pp. 1–4.
[45] J. Johnson, M. Douze, and H. Jégou, “Billion-scale similarity search with GPUs,” IEEE Trans. Big Data, vol. 7, no. 3, pp. 535–547, Jul. 2017, arXiv:1702.08734.
[46] L. D. Boytsov, Y. Novak, A. Malkov, and E. Nyberg, “Off the beaten path: Let’s replace term-based retrieval with k-NN search,” in Proc. 25th ACM Int. Conf. Inf. Knowl. Manage., S. Mukhopadhyay, C. Zhai, E. F. Bertino, J. Crestani, J. Mostafa Tang, L. Si, X. Zhou, Y. Chang, Y. Li, and P. Sondhi, Eds., Indianapolis, IN, USA, ACM, 2016, pp. 1099–1108. [Online]. Available: https://doi.org/10.1145/2983323.2983815
[47] J. L. Blanco and P. K. Rai, “nanoflann: A C+ header-only fork of FLANN, a library for Nearest Neighbor (NN) with KD-trees,” 2014. [Online]. Available: https://github.com/jlblancoc/nanoflann

Faster-lio论文翻译相关推荐

  1. 目标检测经典论文——Faster R-CNN论文翻译（纯中文版）：Faster R-CNN：通过Region Proposal网络实现实时目标检测

    目标检测经典论文翻译汇总:[翻译汇总] 翻译pdf文件下载:[下载地址] 此版为纯中文版,中英文对照版请稳步:[Faster R-CNN中英文对照版] Faster R-CNN:通过Region Pr ...

  2. Faster R-CNN论文翻译

    首发地址 原文:SPPNet论文翻译 译者:邓范鑫 Faster R-CNN是互怼完了的好基友一起合作出来的巅峰之作,本文翻译的比例比较小,主要因为本paper是前述paper的一个简单改进,方法清晰 ...

  3. 卷积神经网络——目标检测之Faster R-CNN论文翻译

    论文连接 https://arxiv.org/abs/1506.01497 相关论文翻译链接 R-CNN:https://blog.csdn.net/itlilyer/article/details/ ...

  4. YOLO9000, Better, Faster, Stronger论文翻译——中英文对照

    文章作者:Tyan 博客:noahsnail.com  |  CSDN  |  简书 声明:作者翻译论文仅为学习,如有侵权请联系作者删除博文,谢谢! 翻译论文汇总:https://github.com ...

  5. Faster R-CNN论文翻译笔记

    百度网盘论文链接,提取码:kk89 https://pan.baidu.com/s/12RDu3WLgH5WcV_Mo3q02xg 或者去arxiv下载<Faster R-CNN: Toward ...

  6. YOLO9000, Better, Faster, Stronger论文翻译——中文版

    文章作者:Tyan 博客:noahsnail.com  |  CSDN  |  简书 声明:作者翻译论文仅为学习,如有侵权请联系作者删除博文,谢谢! 翻译论文汇总:https://github.com ...

  7. Faster R-CNN论文翻译——中文版

    文章作者:Tyan 博客:noahsnail.com  |  CSDN  |  简书 声明:作者翻译论文仅为学习,如有侵权请联系作者删除博文,谢谢! 翻译论文汇总:https://github.com ...

  8. 目标检测经典论文——Faster R-CNN论文翻译：Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Net

    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN:通过Region ...

  9. （目标检测）Faster R-CNN 论文解读+复现

    Faster R-CNN xyang 声明:本篇文章借用了他人理解,如有侵权,请联系,另如需转载,请注明出处 关于最新最全的目标检测论文,可以查看awesome-object-detection &l ...

  10. YOLO 9000论文翻译 | YOLO9000:Better, Faster, Stronger

    文章已迁至:http://www.machunjie.com/translate/27.html 如需交流,请移步新地址,谢谢! YOLO 9000论文翻译 | YOLO9000:Better, Fa ...

最新文章

  1. Python从菜鸟到高手（2）：清空Python控制台
  2. C语言之prinf的用法
  3. 理解 Cinder 架构 - 每天5分钟玩转 OpenStack（45）
  4. 【Opencv实战】图像修复神技？看我一秒修复家里的老照片
  5. autotype安全 fastjson_Fastjson 安全更新，建议升级到 1.2.28 或更新版本
  6. json-server模拟后台接口
  7. weui-react项目实战新心得
  8. vs不识别0b二进制格式_数据背后的二进制
  9. 查询mysql数据库的端口号_查询数据库端口号的命令
  10. springboot+mybatis报错处理
  11. BUCK电感工作模式
  12. 全国信息技术标准化技术委员会汉字内码扩展规范(GBK)
  13. 王牌英雄(Awesomenauts)研究报告
  14. 学会 Arthas，让你 3 年经验掌握 5 年功力！
  15. 面试网答题(如老牛网）
  16. direct wifi 投屏_告别Wifi直接投 AOC无线投屏显示器轻松用
  17. APP移动端自动化测试工具选型“兵器谱”一览(主流开源工具)
  18. Dubbo Admin部署(Dubbo 2.7.X)
  19. C3P0 连接问题 An attempt by a client to checkout a Connection has timed out.
  20. mongodb期末考试总结

热门文章

  1. 华为战略及破局关键——华为产业链深度系列研究（附下载）
  2. 【硬件相关】网卡bond配置
  3. React Native TextInput
  4. 国内composer更新源
  5. word 字体 中英文对照
  6. Linux 内核编译 modules ehci-hcd, ohci-hcd, uhci-hcd not found
  7. 基于Springboot+Vue+Mybatis的小说阅读管理系统
  8. 基于Web的搜索引擎检索系统（Java+Lucene+SqlServer）
  9. 考研核心词汇-易错词
  10. IP被封了，朋友让我帮忙下载……