{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T22:05:21Z","timestamp":1784153121998,"version":"3.55.0"},"reference-count":38,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","award":["YDZJ202401593ZYTS"],"award-info":[{"award-number":["YDZJ202401593ZYTS"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Field Robotics"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Accurate power consumption prediction is critical for ensuring long\u2010term autonomy of autonomous wheeled vehicles (AWVs) in unstructured off\u2010road environments. However, this task remains challenging due to the complex vehicle\u2010terrain interactions. Existing methods, predominantly relying on single\u2010modality data or pure physical models, fail to achieve the required prediction accuracy and cross\u2010domain generalization capability for practical deployment. To address these limitations, we propose Power\u2010aware Vision and State Fusion (PaVSF), a parameter\u2010aware multimodal fusion model. Our model conditions multi\u2010scale visual representations on vehicle operational states and adaptively fuses them with power signals. A physics consistency loss based on power conservation principles is integrated to regularize the learning process, enabling end\u2010to\u2010end power consumption regression. Experimental results demonstrate that our model significantly outperforms the self\u2010constructed BasicModel, reducing the MAE and RMSE of power consumption prediction by 76.16% (to 6.33\u2009W) and 74.89% (to 8.68\u2009W), respectively. Ablation study validates the necessity of each core component. Furthermore, the model exhibits exceptional generalization and robustness, as evidenced by low prediction errors in steady\u2010state intervals across real\u2010world unseen and heterogeneous terrains, with MAE values of 8.90\u2009W on transition terrain in familiar states and 7.50\u2009W on unmowed lawn terrain in unfamiliar states. This work presents a deployable solution for power consumption prediction in off\u2010road navigation. The code and related resources are available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/ShilongXu\/PaVSF\">https:\/\/github.com\/ShilongXu\/PaVSF<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1002\/rob.70179","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T12:16:11Z","timestamp":1770984971000},"page":"3019-3042","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PaVSF: A Multimodal Fusion Power Consumption Prediction Model for Autonomous Wheeled Vehicles in Off\u2010Road Environments"],"prefix":"10.1002","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9324-620X","authenticated-orcid":false,"given":"Dongxuan","family":"Xie","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering Changchun University of Technology Changchun Jilin China"},{"name":"Northeast Industries Group Co. Ltd. Changchun Jilin China"},{"name":"School of Vehicle and Mobility Tsinghua University Beijing Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2476-9656","authenticated-orcid":false,"given":"Shilong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Changchun University of Technology Changchun Jilin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2675-8245","authenticated-orcid":false,"given":"Youkang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Changchun University of Technology Changchun Jilin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanjian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northeast Industries Group Co. Ltd. Changchun Jilin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6632-9077","authenticated-orcid":false,"given":"Nan","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of CNC Equipment Reliability, Ministry of Education, School of Mechanical and Aerospace Engineering Jilin University Changchun Jilin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9818-0879","authenticated-orcid":false,"given":"Xiangkun","family":"He","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen Guangdong China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"crossref","unstructured":"Anjum M. U. M.Khalid andU.Manzoor.2024. \u201cEnergy Profiling for Wheeled Mobile Robots With LuGre Friction Model in a Realistic Simulation Framework.\u201d InIEEE International Conference on Industrial Technology (ICIT) 1\u20107. IEEE.https:\/\/doi.org\/10.1109\/ICIT58233.2024.10540789.","DOI":"10.1109\/ICIT58233.2024.10540789"},{"key":"e_1_2_7_3_1","doi-asserted-by":"crossref","unstructured":"Baroughi R. M. H.Attar andF.Rastegari.2023. \u201cA Comprehensive Simulation of Electric Vehicle Energy Consumption: Incorporating Route Planning and Machine Learning\u2010Based Predictions.\u201d In2nd International Engineering Conference on Electrical Energy and Artificial Intelligence (EICEEAI) 1\u20104. IEEE.https:\/\/doi.org\/10.1109\/EICEEAI60672.2023.10590474.","DOI":"10.1109\/EICEEAI60672.2023.10590474"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3243854"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2963544"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.4070847"},{"key":"e_1_2_7_7_1","doi-asserted-by":"crossref","unstructured":"Eder M. andG.Steinbauer\u2010Wagner.2023. \u201cPredicting Energy Consumption and Traversal Time of Ground Robots for Outdoor Navigation on Multiple Types of Terrain.\u201d InIEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) 1\u20108. IEEE.https:\/\/doi.org\/10.1109\/IROS55552.2023.10341716.","DOI":"10.1109\/IROS55552.2023.10341716"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2015.2413355"},{"key":"e_1_2_7_9_1","doi-asserted-by":"crossref","unstructured":"Gruning V. J.Pentzer S.Brennan andK.Reichard.2020. \u201cEnergy\u2010Aware Path Planning for Skid\u2010Steer Robots Operating on Hilly Terrain.\u201d InAmerican Control Conference (ACC) 2094\u20102099. IEEE.https:\/\/doi.org\/10.23919\/ACC45564.2020.9147470.","DOI":"10.23919\/ACC45564.2020.9147470"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-016-9550-8"},{"key":"e_1_2_7_11_1","first-page":"6368","volume-title":"IEEE Transactions on Neural Networks and Learning Systems","author":"He X.","year":"2025"},{"key":"e_1_2_7_12_1","first-page":"267","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"He X.","year":"2024"},{"key":"e_1_2_7_13_1","doi-asserted-by":"crossref","unstructured":"He K. X.Zhang S.Ren andJ.Sun.2016. \u201cDeep Residual Learning for Image Recognition.\u201d InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770\u2010778. IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_7_14_1","unstructured":"Hinton G. O.Vinyals andJ.Dean.2015. \u201cDistilling the Knowledge in a Neural Network.\u201d arxiv preprint arxiv:1503.02531."},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3071319"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/vehicles6030049"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3217603"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3159994"},{"key":"e_1_2_7_19_1","doi-asserted-by":"crossref","unstructured":"Lin T. Y. P.Doll\u00e1r R.Girshick K.He B.Hariharan andS.Belongie.2017. \u201cFeature Pyramid Networks for Object Detection.\u201d InIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 936\u2010944. IEEE.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_7_20_1","doi-asserted-by":"crossref","unstructured":"Mei Y. Y. H.Lu Y. C.Hu andC. S. G.Lee.2005. \u201cA Case Study of Mobile Robot's Energy Consumption and Conservation Techniques.\u201d In12th International Conference on Advanced Robotics (ICAR) 492\u2010497. IEEE.https:\/\/doi.org\/10.1109\/ICAR.2005.1507454.","DOI":"10.1109\/ICAR.2005.1507454"},{"key":"e_1_2_7_21_1","doi-asserted-by":"crossref","unstructured":"Miller N. N.Goulet andB.Ayalew.2024. \u201cEnergy\u2010aware Mission Planning for Unmanned Ground Vehicle Fleets.\u201dSAE Technical Paper 2024\u201001\u20104071.https:\/\/doi.org\/10.4271\/2024-01-4071.","DOI":"10.4271\/2024-01-4071"},{"key":"e_1_2_7_22_1","unstructured":"Oliveira R. L.Ott andF.Ramos.2016. \u201cActive Perception for Modelling Energy Consumption in Off\u2010road Navigation.\u201d InAustralasian Conference on Robotics and Automation (ACRA). Australia."},{"key":"e_1_2_7_23_1","volume-title":"Field and Service Robotics. Springer Tracts in Advanced Robotics","author":"Otsu K.","year":"2016"},{"key":"e_1_2_7_24_1","doi-asserted-by":"crossref","unstructured":"Pentzer J. K.Reichard andS.Brennan.2016. \u201cEnergy\u2010Based Path Planning for Skid\u2010Steer Vehicles Operating in Areas With Mixed Surface Types.\u201d InAmerican Control Conference (ACC) 2110\u20102115. IEEE.https:\/\/doi.org\/10.1109\/ACC.2016.7525230.","DOI":"10.1109\/ACC.2016.7525230"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21459"},{"key":"e_1_2_7_26_1","doi-asserted-by":"crossref","unstructured":"Quann M. L.Ojeda W.Smith D.Rizzo M.Castanier andK.Barton.2018. \u201cGround Robot Terrain Mapping and Energy Prediction in Environments with 3\u2010D Topography.\u201d InAnnual American Control Conference (ACC) 3532\u20103537. IEEE.https:\/\/doi.org\/10.23919\/ACC.2018.8430767.","DOI":"10.23919\/ACC.2018.8430767"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21927"},{"key":"e_1_2_7_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967717"},{"key":"e_1_2_7_29_1","doi-asserted-by":"crossref","unstructured":"Sakayori G. andG.Ishigami.2017. \u201cEnergy Efficient Slope Traversability Planning for Mobile Robot in Loose Soil.\u201d InIEEE International Conference on Mechatronics (ICM) 99\u2010104. IEEE.https:\/\/doi.org\/10.1109\/ICMECH.2017.7921087.","DOI":"10.1109\/ICMECH.2017.7921087"},{"key":"e_1_2_7_30_1","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2021.1959396"},{"key":"e_1_2_7_31_1","doi-asserted-by":"crossref","unstructured":"Tiwari K. X.Xiao andN. Y.Chong.2018. \u201cEstimating Achievable Range of Ground Robots Operating on Single Battery Discharge for Operational Efficacy Amelioration.\u201d InIEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) 3991\u20103998. IEEE.https:\/\/doi.org\/10.1109\/IROS.2018.8593845.","DOI":"10.1109\/IROS.2018.8593845"},{"key":"e_1_2_7_32_1","unstructured":"Visca M.2023. \u201cDeep Learning for the Energy\u2010Aware Guidance of Robots in Natural Environments.\u201d Doctoral diss. University of Surrey."},{"key":"e_1_2_7_33_1","doi-asserted-by":"crossref","unstructured":"Visca M. R.Powell Y.Gao andS.Fallah.2022a. \u201cMeta\u2010Conv1D Energy\u2010Aware Path Planner for Mobile Robots in Unstructured Terrains.\u201d In7th International Conference on Robotics and Automation Engineering (ICRAE) 150\u2010157. IEEE.https:\/\/doi.org\/10.1109\/ICRAE56463.2022.10056177.","DOI":"10.1109\/ICRAE56463.2022.10056177"},{"key":"e_1_2_7_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3209259"},{"key":"e_1_2_7_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/drones8090419"},{"key":"e_1_2_7_36_1","doi-asserted-by":"publisher","DOI":"10.3390\/machines12010031"},{"key":"e_1_2_7_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3130630"},{"key":"e_1_2_7_38_1","doi-asserted-by":"publisher","DOI":"10.1108\/RIA-05-2023-0060"},{"key":"e_1_2_7_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3268051"}],"container-title":["Journal of Field Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/rob.70179","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/rob.70179","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/rob.70179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T21:43:21Z","timestamp":1784151801000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/rob.70179"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,13]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1002\/rob.70179"],"URL":"https:\/\/doi.org\/10.1002\/rob.70179","archive":["Portico"],"relation":{},"ISSN":["1556-4959","1556-4967"],"issn-type":[{"value":"1556-4959","type":"print"},{"value":"1556-4967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,13]]},"assertion":[{"value":"2025-10-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}