Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization (2212.06331v2)

Published 13 Dec 2022 in cs.CV

Abstract: LiDAR mapping is important yet challenging in self-driving and mobile robotics. To tackle such a global point cloud registration problem, DeepMapping converts the complex map estimation into a self-supervised training of simple deep networks. Despite its broad convergence range on small datasets, DeepMapping still cannot produce satisfactory results on large-scale datasets with thousands of frames. This is due to the lack of loop closures and exact cross-frame point correspondences, and the slow convergence of its global localization network. We propose DeepMapping2 by adding two novel techniques to address these issues: (1) organization of training batch based on map topology from loop closing, and (2) self-supervised local-to-global point consistency loss leveraging pairwise registration. Our experiments and ablation studies on public datasets (KITTI, NCLT, and Nebula) demonstrate the effectiveness of our method.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (58)
  1. Li Ding and Chen Feng. Deepmapping: Unsupervised map estimation from multiple point clouds. In CVPR, pages 8650–8659, 2019.
  2. Visual localization within lidar maps for automated urban driving. In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 176–183. IEEE, 2014.
  3. L3-net: Towards learning based lidar localization for autonomous driving. In CVPR, pages 6389–6398, 2019.
  4. Locus: A multi-sensor lidar-centric solution for high-precision odometry and 3d mapping in real-time. IEEE Robotics and Automation Letters, 6(2):421–428, 2020.
  5. Point-plane slam for hand-held 3d sensors. In 2013 IEEE international conference on robotics and automation, pages 5182–5189. IEEE, 2013.
  6. LaMAR: Benchmarking Localization and Mapping for Augmented Reality. In ECCV, 2022.
  7. Monoslam: Real-time single camera slam. PAMI, 29(6):1052–1067, 2007.
  8. Parallel tracking and mapping for small ar workspaces. In 2007 6th IEEE and ACM international symposium on mixed and augmented reality, pages 225–234. IEEE, 2007.
  9. Kinectfusion: real-time 3d reconstruction and interaction using a moving depth camera. In Proceedings of the 24th annual ACM symposium on User interface software and technology, pages 559–568, 2011.
  10. Lsd-slam: Large-scale direct monocular slam. In ECCV, pages 834–849. Springer, 2014.
  11. Rtab-map as an open-source lidar and visual simultaneous localization and mapping library for large-scale and long-term online operation. Journal of Field Robotics, 36(2):416–446, 2019.
  12. Orb-slam3: An accurate open-source library for visual, visual–inertial, and multimap slam. IEEE Transactions on Robotics, 37(6):1874–1890, 2021.
  13. Lidar slam with plane adjustment for indoor environment. IEEE Robotics and Automation Letters, 6(4):7073–7080, 2021.
  14. Ji Zhang and Sanjiv Singh. Loam: Lidar odometry and mapping in real-time. In Robotics: Science and Systems, volume 2, pages 1–9. Berkeley, CA, 2014.
  15. Lego-loam: Lightweight and ground-optimized lidar odometry and mapping on variable terrain. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 4758–4765. IEEE, 2018.
  16. Lio-sam: Tightly-coupled lidar inertial odometry via smoothing and mapping. In 2020 IEEE/RSJ international conference on intelligent robots and systems (IROS), pages 5135–5142. IEEE, 2020.
  17. Lamp: Large-scale autonomous mapping and positioning for exploration of perceptually-degraded subterranean environments. In 2020 IEEE International Conference on Robotics and Automation (ICRA), pages 80–86. IEEE, 2020.
  18. isam: Incremental smoothing and mapping. IEEE Transactions on Robotics, 24(6):1365–1378, 2008.
  19. g22{}^{2}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPTo: A general framework for graph optimization. In 2011 IEEE International Conference on Robotics and Automation, pages 3607–3613. IEEE, 2011.
  20. 3dfeat-net: Weakly supervised local 3d features for point cloud registration. In ECCV, pages 607–623, 2018.
  21. Keypoint matching for point cloud registration using multiplex dynamic graph attention networks. IEEE Robotics and Automation Letters, 6(4):8221–8228, 2021.
  22. Lo-net: Deep real-time lidar odometry. In CVPR, pages 8473–8482, 2019.
  23. Overlapnet: Loop closing for lidar-based slam. arXiv preprint arXiv:2105.11344, 2021.
  24. Posenet: A convolutional network for real-time 6-dof camera relocalization. In ICCV, pages 2938–2946, 2015.
  25. Go-icp: A globally optimal solution to 3d icp point-set registration. PAMI, 38(11):2241–2254, 2015.
  26. Registration of 3d point sets using correntropy similarity matrix. arXiv preprint arXiv:2107.09725, 2021.
  27. Deep closest point: Learning representations for point cloud registration. In CVPR, pages 3523–3532, 2019.
  28. Deep global registration. In CVPR, 2020.
  29. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 32(11):1231–1237, 2013.
  30. University of michigan north campus long-term vision and lidar dataset. The International Journal of Robotics Research, 35(9):1023–1035, 2016.
  31. Nebula: Quest for robotic autonomy in challenging environments; team costar at the darpa subterranean challenge. arXiv preprint arXiv:2103.11470, 2021.
  32. Method for registration of 3-d shapes. In Sensor fusion IV: control paradigms and data structures, volume 1611, pages 586–606. Spie, 1992.
  33. Point registration via efficient convex relaxation. ACM Transactions on Graphics (TOG), 35(4):1–12, 2016.
  34. Globally consistent registration of terrestrial laser scans via graph optimization. ISPRS journal of photogrammetry and remote sensing, 109:126–138, 2015.
  35. A generative model for the joint registration of multiple point sets. In ECCV, pages 109–122. Springer, 2014.
  36. Global structure-from-motion by similarity averaging. In CVPR, pages 864–872, 2015.
  37. Very large-scale global sfm by distributed motion averaging. In CVPR, pages 4568–4577, 2018.
  38. Robust reconstruction of indoor scenes. In CVPR, pages 5556–5565, 2015.
  39. Learning multiview 3d point cloud registration. In CVPR, pages 1759–1769, 2020.
  40. Aggregating local descriptors into a compact image representation. In CVPR, pages 3304–3311. IEEE, 2010.
  41. Pointnetvlad: Deep point cloud based retrieval for large-scale place recognition. In CVPR, pages 4470–4479, 2018.
  42. Pointnet: Deep learning on point sets for 3d classification and segmentation. In CVPR, pages 652–660, 2017.
  43. Netvlad: Cnn architecture for weakly supervised place recognition. In CVPR, pages 5297–5307, 2016.
  44. Self-supervised visual place recognition by mining temporal and feature neighborhoods. arXiv preprint arXiv:2208.09315, 2022.
  45. Orb-slam: a versatile and accurate monocular slam system. IEEE transactions on robotics, 31(5):1147–1163, 2015.
  46. Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras. IEEE transactions on robotics, 33(5):1255–1262, 2017.
  47. Deepslam: A robust monocular slam system with unsupervised deep learning. IEEE Transactions on Industrial Electronics, 68(4):3577–3587, 2020.
  48. Keypoint design and evaluation for place recognition in 2d lidar maps. Robotics and Autonomous Systems, 57(12):1211–1224, 2009.
  49. Efficient large-scale 3d mobile mapping and surface reconstruction of an underground mine. In Field and service robotics, pages 479–493. Springer, 2014.
  50. Robust place recognition for 3d range data based on point features. In 2010 IEEE International Conference on Robotics and Automation, pages 1400–1405. IEEE, 2010.
  51. A tutorial on quantitative trajectory evaluation for visual (-inertial) odometry. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 7244–7251. IEEE, 2018.
  52. Hregnet: A hierarchical network for large-scale outdoor lidar point cloud registration. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16014–16023, 2021.
  53. Geometric transformer for fast and robust point cloud registration. In CVPR, pages 11143–11152, 2022.
  54. Kiss-icp: In defense of point-to-point icp simple, accurate, and robust registration if done the right way. IEEE Robotics and Automation Letters, 2023.
  55. A survey on map-based localization techniques for autonomous vehicles. IEEE Transactions on Intelligent Vehicles, 2022.
  56. Darpa subterranean challenge: Multi-robotic exploration of underground environments. In International Conference on Modelling and Simulation for Autonomous Systems, pages 274–290. Springer, 2019.
  57. Locus 2.0: Robust and computationally efficient lidar odometry for real-time 3d mapping. IEEE Robotics and Automation Letters, 2022.
  58. Pytorch distributed: Experiences on accelerating data parallel training. arXiv preprint arXiv:2006.15704, 2020.
Citations (13)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now