{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T16:06:05Z","timestamp":1777910765524,"version":"3.51.4"},"reference-count":41,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T00:00:00Z","timestamp":1659398400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100018594","name":"Central University Basic Research Fund of China","doi-asserted-by":"publisher","award":["DUT20LAB303"],"award-info":[{"award-number":["DUT20LAB303"]}],"id":[{"id":"10.13039\/501100018594","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant Nos.U1913201"],"award-info":[{"award-number":["Grant Nos.U1913201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Transactions of the Institute of Measurement and Control"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Light detection and ranging (LiDAR) odometry plays a crucial role in autonomous mobile robots and unmanned ground vehicles (UGVs). This paper presents a deep learning\u2013based odometry system using two successive three-dimensional (3D) point clouds to estimate their scene flow and then predict their relative pose. The network consumes continuous 3D point clouds directly and outputs their scene flow and uncertain mask in a coarse-to-fine fashion. A pose estimation layer without trainable parameters is designed to compute the pose with the scene flow. We also introduce a scan-to-map optimization algorithm to enhance the robustness and accuracy of the system. Our experiments on the KITTI odometry data set and our campus data set demonstrate the effectiveness of the proposed deep learning\u2013based point cloud odometry.<\/jats:p>","DOI":"10.1177\/01423312221105165","type":"journal-article","created":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T08:36:10Z","timestamp":1659429370000},"page":"274-286","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":6,"title":["A 3D LiDAR odometry for UGVs using coarse-to-fine deep scene flow estimation"],"prefix":"10.1177","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1531-3494","authenticated-orcid":false,"given":"Chi","family":"Li","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Dalian University of Technology, China"}]},{"given":"Fei","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Dalian University of Technology, China"}]},{"given":"Sen","family":"Wang","sequence":"additional","affiliation":[{"name":"Edinburgh Centre for Robotics, Heriot-Watt University, UK"}]},{"given":"Yan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Dalian University of Technology, China"}]}],"member":"179","published-online":{"date-parts":[[2022,8,2]]},"reference":[{"key":"bibr1-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1987.4767965"},{"key":"bibr2-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00639"},{"key":"bibr3-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"bibr4-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197366"},{"key":"bibr5-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00905"},{"key":"bibr6-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"bibr7-01423312221105165","unstructured":"Grupp M. (2017) EVO: Python package for the evaluation of odometry and SLAM. Available at: https:\/\/github.com\/MichaelGrupp\/evo"},{"key":"bibr8-01423312221105165","first-page":"7500709","volume":"70","author":"He G","year":"2021","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"bibr9-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1177\/0142331215586615"},{"key":"bibr10-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00425"},{"key":"bibr11-01423312221105165","first-page":"6980","volume":"1412","author":"Kingma DP","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"bibr12-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00867"},{"key":"bibr13-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"bibr14-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341206"},{"key":"bibr15-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2005.02.004"},{"key":"bibr16-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00062"},{"key":"bibr17-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00655"},{"key":"bibr18-01423312221105165","author":"Magnusson M","year":"2009","journal-title":"The three-dimensional normal-distributions transform: An efficient representation for registration, surface analysis, and loop detection"},{"key":"bibr19-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"bibr20-01423312221105165","unstructured":"Nicolai A, Skeele R, Eriksen C, et al. (2016) Deep learning for laser based odometry estimation. In: RSS workshop limits and potentials of deep learning in robotics, vol. 184, p. 1. Available at: http:\/\/research.engr.oregonstate.edu\/rdml\/sites\/research.engr.oregonstate.edu.rdml\/files\/final_deep_learning_lidar_odometry.pdf"},{"key":"bibr21-01423312221105165","doi-asserted-by":"crossref","unstructured":"Ouyang B, Raviv D. (2020) Occlusion guided scene flow estimation on 3D point clouds. arXiv preprint arXiv:2011.14880.","DOI":"10.1109\/CVPRW53098.2021.00315"},{"key":"bibr22-01423312221105165","first-page":"8026","volume-title":"Advances in neural information processing systems","author":"Paszke A","year":"2019"},{"key":"bibr23-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_32"},{"key":"bibr24-01423312221105165","first-page":"5099","volume-title":"Advances in neural information processing systems","author":"Qi CR","year":"2017"},{"key":"bibr25-01423312221105165","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.021"},{"key":"bibr26-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353455"},{"key":"bibr27-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912460895"},{"key":"bibr28-01423312221105165","first-page":"6411","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Thomas H","year":"2019"},{"key":"bibr29-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/ICARSC.2018.8374163"},{"key":"bibr30-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01565"},{"key":"bibr31-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917734298"},{"key":"bibr32-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967756"},{"key":"bibr33-01423312221105165","unstructured":"Wu W, Wang Z, Li Z, et al. (2019) PointPWC-Net: A coarse-to-fine network for supervised and self-supervised scene flow estimation on 3D point clouds. Arxiv Preprint Arxiv:1911.12408."},{"key":"bibr34-01423312221105165","unstructured":"Xu Y, Huang Z, Lin KY, et al. (2020) SelfVoxeLo: Self-supervised LiDAR odometry with voxelbased deep neural networks. Arxiv Preprint Arxiv:2010.09343."},{"key":"bibr35-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"bibr36-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01184"},{"key":"bibr37-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1177\/0142331220933430"},{"key":"bibr38-01423312221105165","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.007"},{"key":"bibr39-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413771"},{"key":"bibr40-01423312221105165","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_47"},{"key":"bibr41-01423312221105165","unstructured":"Zhou QY, Park J, Koltun V. (2018) Open3D: A modern library for 3D data processing. arXiv:1801.09847."}],"container-title":["Transactions of the Institute of Measurement and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01423312221105165","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/01423312221105165","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01423312221105165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T15:06:01Z","timestamp":1777647961000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/01423312221105165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,2]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1177\/01423312221105165"],"URL":"https:\/\/doi.org\/10.1177\/01423312221105165","relation":{},"ISSN":["0142-3312","1477-0369"],"issn-type":[{"value":"0142-3312","type":"print"},{"value":"1477-0369","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,2]]}}}