{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T14:06:24Z","timestamp":1771164384362,"version":"3.50.1"},"reference-count":43,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Field Robotics"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    OpenStreetMap (OSM) has gained popularity recently in autonomous navigation due to its public accessibility, lower maintenance costs, and broader geographical coverage. However, existing methods often struggle with noisy OSM data and incomplete sensor observations, leading to inaccuracies in trajectory planning. These challenges are particularly evident in complex driving scenarios, such as at intersections or facing occlusions. To address these challenges, we propose a robust and explainable two\u2010stage framework to learn an Orientation Field (OrField) for robot navigation by integrating LiDAR scans and OSM routes. In the first stage, we introduce a novel representation, OrField, which can provide orientations for each grid on the map, reasoning jointly from noisy LiDAR scans and OSM routes. To generate a robust OrField, we train a deep neural network by encoding a versatile initial OrField and output an optimized OrField. Based on OrField, we propose two trajectory planners for OSM\u2010guided robot navigation, called Field\u2010RRT* and Field\u2010Bezier, respectively, in the second stage by improving the Rapidly Exploring Random Tree (RRT) algorithm and Bezier curve to estimate the trajectories. Thanks to the robustness of OrField which captures both global and local information, Field\u2010RRT* and Field\u2010Bezier can generate accurate and reliable trajectories even in challenging conditions. We validate our approach through experiments on the SemanticKITTI data set and our own campus data set. The results demonstrate the effectiveness of our method, achieving superior performance in complex and noisy conditions. Our code for network training and real\u2010world deployment is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/IMRL\/OriField\">https:\/\/github.com\/IMRL\/OriField<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1002\/rob.70060","type":"journal-article","created":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T10:22:25Z","timestamp":1756722145000},"page":"717-738","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Orientation Field for OSM\u2010Guided Autonomous Navigation"],"prefix":"10.1002","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5383-3780","authenticated-orcid":false,"given":"Yuming","family":"Huang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City (SKL\u2010IOTSC), Faculty of Science and Technology University of Macau Macau China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City (SKL\u2010IOTSC), Faculty of Science and Technology University of Macau Macau China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems Singapore Management University Singapore Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maani","family":"Ghaffari","sequence":"additional","affiliation":[{"name":"Department of Naval Architecture and Marine Engineering University of Michigan Ann Arbor Michigan USA"},{"name":"Department of Robotics University of Michigan Ann Arbor Michigan USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dezhen","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Robotics Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Masdar City UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng\u2010Zhong","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City (SKL\u2010IOTSC), Faculty of Science and Technology University of Macau Macau China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Kong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City (SKL\u2010IOTSC), Faculty of Science and Technology University of Macau Macau China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,9,1]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106125"},{"key":"e_1_2_9_3_1","doi-asserted-by":"crossref","unstructured":"Behley J. M.Garbade A.Milioto et al.2019. \u201cSemantickitti: A Dataset for Semantic Scene Understanding of Lidar Sequences.\u201d InProceedings of the IEEE\/CVF International Conference on Computer Vision 9297\u20139307. IEEE.","DOI":"10.1109\/ICCV.2019.00939"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"e_1_2_9_5_1","unstructured":"Chai Y. B.Sapp M.Bansal andD.Anguelov.2019. \u201cMultipath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction.\u201d InProceedings of the Conference on Robot Learning 86\u201399. Proceedings of Machine Learning Research 100. PMLR."},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64559-5_16"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793868"},{"key":"e_1_2_9_9_1","unstructured":"Dellaert F. andGTSAM Contributors.2022. \u201cborglab\/gtsam.\u201d Georgia Tech Borg Lab. Version 4.2a8.https:\/\/doi.org\/10.5281\/zenodo.5794541."},{"key":"e_1_2_9_10_1","unstructured":"Deo N. andM. M.Trivedi.2020. \u201cTrajectory Forecasts in Unknown Environments Conditioned on Grid\u2010Based Plans.\u201d arXiv.https:\/\/doi.org\/10.48550\/arXiv.2001.00735."},{"key":"e_1_2_9_11_1","first-page":"1","volume-title":"Conference on Robot Learning","author":"Dosovitskiy A.","year":"2017"},{"key":"e_1_2_9_12_1","unstructured":"Fan H. F.Zhu C.Liu et al.2018. \u201cBaidu Apollo Em Motion Planner.\u201d arXiv.https:\/\/doi.org\/10.48550\/arXiv.1807.08048."},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630703"},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","first-page":"12302","DOI":"10.1109\/IROS58592.2024.10802364","volume-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Gao W.","year":"2024"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"e_1_2_9_16_1","volume-title":"Hd\u2010Maps in Autonomous Driving","author":"Gran C. W.","year":"2019"},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","unstructured":"Gu J. C.Hu T.Zhang et al.2023. \u201cVip3d: End\u2010to\u2010end Visual Trajectory Prediction via 3d Agent Queries.\u201d InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 5496\u20135506. IEEE.","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"Gu J. C.Sun andH.Zhao.2021. \u201cDensetnt: End\u2010to\u2010end Trajectory Prediction From Dense Goal Sets.\u201d InProceedings of the IEEE\/CVF International Conference on Computer Vision 15303\u201315312. IEEE.","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","unstructured":"Guo K. W.Liu andJ.Pan.2022. \u201cEnd\u2010to\u2010end trajectory Distribution Prediction Based on Occupancy Grid Maps.\u201d InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2242\u20132251. IEEE.","DOI":"10.1109\/CVPR52688.2022.00228"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2008.80"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2010.5625092"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS.2018.00035"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593953"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3070508"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"Liu M. H.Cheng L.Chen et al.2024. \u201cLaformer: Trajectory Prediction for Autonomous Driving With Lane\u2010Aware Scene Constraints.\u201d InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2039\u20132049. IEEE.","DOI":"10.1109\/CVPRW63382.2024.00209"},{"key":"e_1_2_9_26_1","unstructured":"Omama M. P.Inani P.Paul et al.2023. \u201cAlt\u2010Pilot: Autonomous Navigation With Language Augmented Topometric Maps.\u201d arXiv.https:\/\/doi.org\/10.48550\/arXiv.2310.02324."},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2961051"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460519"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811591"},{"key":"e_1_2_9_30_1","first-page":"403","volume-title":"International Conference on Intelligent Autonomous Systems","author":"Paz D.","year":"2021"},{"key":"e_1_2_9_31_1","doi-asserted-by":"crossref","unstructured":"Phan\u2010Minh T. E. C.Grigore F. A.Boulton O.Beijbom andE. M.Wolff.2020. \u201cCovernet: Multimodal Behavior Prediction Using Trajectory Sets.\u201d InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 14074\u201314083. IEEE.","DOI":"10.1109\/CVPR42600.2020.01408"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569929"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989169"},{"key":"e_1_2_9_36_1","doi-asserted-by":"crossref","first-page":"7415","DOI":"10.1109\/IROS55552.2023.10341358","volume-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Tsiakas K.","year":"2023"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509799"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811712"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3141876"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064227"},{"key":"e_1_2_9_41_1","doi-asserted-by":"crossref","unstructured":"Yang F. C.Wang C.Cadena andM.Hutter.2023. \u201cIplanner: Imperative Path Planning.\u201d InRobotics: Science and Systems XIX Daegu Republic of Korea July 10\u201314 2023.https:\/\/doi.org\/10.15607\/RSS.2023.XIX.064.","DOI":"10.15607\/RSS.2023.XIX.064"},{"key":"e_1_2_9_42_1","unstructured":"Yu F. andV.Koltun.2016. \u201cMulti\u2010Scale Context Aggregation by Dilated Convolutions.\u201d In4th International Conference on Learning Representations (ICLR) San Juan Puerto Rico May 2\u20104 2016 Conference Track Proceedings. OpenReview."},{"key":"e_1_2_9_43_1","doi-asserted-by":"crossref","unstructured":"Zeng W. W.Luo S.Suo et al.2019. \u201cEnd\u2010to\u2010End Interpretable Neural Motion Planner.\u201d InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 8660\u20138669. IEEE.","DOI":"10.1109\/CVPR.2019.00886"},{"key":"e_1_2_9_44_1","unstructured":"Zhao H. J.Gao T.Lan et al.2021. \u201cTnt: Target\u2010Driven Trajectory Prediction.\u201d InProceedings of the 2020 Conference on Robot Learning 895\u2013904. Proceedings of Machine Learning Research155. PMLR."}],"container-title":["Journal of Field Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/rob.70060","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/rob.70060","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/rob.70060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T13:45:33Z","timestamp":1771163133000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/rob.70060"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1002\/rob.70060"],"URL":"https:\/\/doi.org\/10.1002\/rob.70060","archive":["Portico"],"relation":{},"ISSN":["1556-4959","1556-4967"],"issn-type":[{"value":"1556-4959","type":"print"},{"value":"1556-4967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,1]]},"assertion":[{"value":"2025-03-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}