CLC number: TP399
On-line Access: 2022-02-28
Received: 2020-07-18
Revision Accepted: 2022-04-22
Crosschecked: 2020-11-18
Cited: 0
Clicked: 5417
Citations: Bibtex RefMan EndNote GB/T7714
Wei WEI, Xiaorui ZHU, Yi WANG. Novel robust simultaneous localization and mapping for long-term autonomous robots[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2000358 @article{title="Novel robust simultaneous localization and mapping for long-term autonomous robots", %0 Journal Article TY - JOUR
用于长期自主机器人的新型鲁棒同时定位与建图方法1哈尔滨工业大学(深圳)机电工程与自动化学院,中国深圳市,518055 2岭南大数据研究院,中国珠海市,519000 摘要:自主移动机器人的基本任务是同时定位与建图(SLAM)。此外,长期鲁棒性是SLAM的一个重要属性。当车辆或机器人快速旋转或在某些场景中(例如低纹理环境、长走廊、隧道或其他重复的结构环境)转向时,大多数SLAM系统可能会失效。本文提出一种新颖的鲁棒视觉惯性激光雷达(LiDaR)导航(VILN)SLAM系统,包括立体视觉-惯性LiDaR里程计和视觉-LiDaR闭环。所提出的VILN SLAM系统即使在偶尔会降低LiDaR或视觉测量性能的复杂场景中也可以长期稳定地运行。大量实验结果表明,与最先进的SLAM系统相比,VILN SLAM系统在各种场景下的鲁棒性都有了很大提高。 关键词组: Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article
Reference[1]Banerjee N, Connolly RC, Lisin D, et al., 2019. View management for lifelong visual maps. IEEE/RSJ Int Conf on Intelligent Robots and Systems, p.7871-7878. doi: 10.1109/IROS40897.2019.8968245 [2]Davison AJ, Reid ID, Molton ND, et al., 2007. MonoSLAM: real-time single camera SLAM. IEEE Trans Patt Anal Mach Intell, 29(6):1052-1067. doi: 10.1109/TPAMI.2007.1049 [3]Deschaud JE, 2018. IMLS-SLAM: scan-to-model matching based on 3D data. IEEE Int Conf on Robotics and Automation, p.2480-2485. doi: 10.1109/ICRA.2018.8460653 [4]Engel J, Schöps T, Cremers D, 2014. LSD-SLAM: large-scale direct monocular SLAM. Proc 13th European Conf on Computer Vision, p.834-849. doi: 10.1007/978-3-319-10605-2_54 [5]Engel J, Koltun V, Cremers D, 2018. Direct sparse odometry. IEEE Trans Patt Anal Mach Intell, 40(3):611-625. doi: 10.1109/TPAMI.2017.2658577 [6]Forster C, Pizzoli M, Scaramuzza D, 2014. SVO: fast semi-direct monocular visual odometry. IEEE Int Conf on Robotics and Automation, p.15-22. doi: 10.1109/ICRA.2014.6906584 [7]Forster C, Carlone L, Dellaert F, et al., 2017. On-manifold preintegration for real-time visual-inertial odometry. IEEE Trans Robot, 33(1):1-21. doi: 10.1109/TRO.2016.2597321 [8]Geiger A, Lenz P, Stiller C, et al., 2013. Vision meets robotics: the KITTI dataset. Int J Robot Res, 32(11):1231-1237. doi: 10.1177/0278364913491297 [9]Grisetti G, Stachniss C, Burgard W, 2007. Improved techniques for grid mapping with Rao-Blackwellized particle filters. IEEE Trans Robot, 23(1):34-46. doi: 10.1109/TRO.2006.889486 [10]Hemann G, Singh S, Kaess M, 2016. Long-range GPS-denied aerial inertial navigation with lidar localization. IEEE/RSJ Int Conf on Intelligent Robots and Systems, p.1659-1666. doi: 10.1109/IROS.2016.7759267 [11]Hess W, Kohler D, Rapp H, et al., 2016. Real-time loop closure in 2D LIDAR SLAM. IEEE Int Conf on Robotics and Automation, p.1271-1278. doi: 10.1109/ICRA.2016.7487258 [12]Kerl C, Sturm J, Cremers D, 2013. Dense visual SLAM for RGB-D cameras. IEEE/RSJ Int Conf on Intelligent Robots and Systems, p.2100-2106. doi: 10.1109/IROS.2013.6696650 [13]Kim G, Park B, Kim A, 2019. 1-day learning, 1-year localization: long-term LiDAR localization using scan context image. IEEE Robot Autom Lett, 4(2):1948-1955. doi: 10.1109/LRA.2019.2897340 [14]Klein G, Murray D, 2007. Parallel tracking and mapping for small AR workspaces. Proc 6th IEEE and ACM Int Symp on Mixed and Augmented Reality, p.1-10. doi: 10.1109/ISMAR.2007.4538852 [15]Konolige K, Grisetti G, Kümmerle R, et al., 2010. Efficient sparse pose adjustment for 2D mapping. IEEE/RSJ Int Conf on Intelligent Robots and Systems, p.22-29. doi: 10.1109/IROS.2010.5649043 [16]Lee J, Hwang S, Lee K, et al., 2020. AD-VO: scale-resilient visual odometry using attentive disparity map. https://arxiv.org/abs/2001.02090 [17]Maurer CR, Qi RS, Raghavan V, 2003. A linear time algorithm for computing exact Euclidean distance transforms of binary images in arbitrary dimensions. IEEE Trans Patt Anal Mach Intell, 25(2):265-270. doi: 10.1109/TPAMI.2003.1177156 [18]Mur-Artal R, Tardós JD, 2017. ORB-SLAM2: an open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE Trans Robot, 33(5):1255-1262. doi: 10.1109/TRO.2017.2705103 [19]Mur-Artal R, Montiel JMM, Tardós JD, 2015. ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans Robot, 31(5):1147-1163. doi: 10.1109/TRO.2015.2463671 [20]Nair GB, Daga S, Sajnani R, et al., 2020. Multi-object monocular SLAM for dynamic environments. https://arxiv.org/abs/2002.03528 [21]Newcombe RA, Lovegrove SJ, Davison AJ, 2011. DTAM: dense tracking and mapping in real-time. Int Conf on Computer Vision, p.2320-2327. doi: 10.1109/ICCV.2011.6126513 [22]Patel N, Khorrami F, Krishnamurthy P, et al., 2019. Tightly coupled semantic RGB-D inertial odometry for accurate long-term localization and mapping. Proc 19th Int Conf on Advanced Robotics, p.523-528. doi: 10.1109/ICAR46387.2019.8981658 [23]Rusinkiewicz S, Levoy M, 2001. Efficient variants of the ICP algorithm. Proc 3rd Int Conf on 3-D Digital Imaging and Modeling, p.145-152. doi: 10.1109/IM.2001.924423 [24]Shao WZ, Vijayarangan S, Li C, et al., 2019. Stereo visual inertial LiDAR simultaneous localization and mapping. IEEE/RSJ Int Conf on Intelligent Robots and Systems, p.370-377. doi: 10.1109/IROS40897.2019.8968012 [25]Sibley G, Matthies L, Sukhatme G, 2010. Sliding window filter with application to planetary landing. J Field Robot, 27(5):587-608. doi: 10.1002/rob.20360 [26]Sünderhauf N, Neubert P, Protzel P, 2013. Predicting the change—a step towards life-long operation in everyday environments. Proc Challenges and Vision Workshop at RSS, p.1-4. [27]Wagstaff B, Peretroukhin V, Kelly J, 2020. Self-supervised deep pose corrections for robust visual odometry. IEEE Int Conf on Robotics and Automation, p.2331-2337. doi: 10.1109/ICRA40945.2020.9197562 [28]Wang ZJ, Wu Y, Niu QQ, 2020. Multi-sensor fusion in automated driving: a survey. IEEE Access, 8:2847-2868. doi: 10.1109/ACCESS.2019.2962554 [29]Xu YL, Ou YS, Xu TT, 2018. SLAM of robot based on the fusion of vision and LIDAR. IEEE Int Conf on Cyborg and Bionic Systems, p.121-126. doi: 10.1109/CBS.2018.8612212 [30]Zhang J, Singh S, 2015. Visual-lidar odometry and mapping: low-drift, robust, and fast. IEEE Int Conf on Robotics and Automation, p.2174-2181. doi: 10.1109/ICRA.2015.7139486 [31]Zhao HJ, Chiba M, Shibasaki R, et al., 2008. SLAM in a dynamic large outdoor environment using a laser scanner. IEEE Int Conf on Robotics and Automation, p.1455-1462. doi: 10.1109/ROBOT.2008.4543407 [32]Zhao ZR, Mao YJ, Ding Y, et al., 2019. Visual-based semantic SLAM with landmarks for large-scale outdoor environment. Proc 2nd China Symp on Cognitive Computing and Hybrid Intelligence, p.149-154. doi: 10.1109/CCHI.2019.8901910 [33]Zhu XR, Qiu CX, Deng FC, et al., 2017. Cloud-based real-time outsourcing localization for a ground mobile robot in large-scale outdoor environments. J Field Robot, 34(7):1313-1331. doi: 10.1002/rob.21712 Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou
310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE |
Open peer comments: Debate/Discuss/Question/Opinion
<1>