{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:53:28Z","timestamp":1782492808468,"version":"3.54.5"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010029","name":"Taishan Scholar Foundation of Shandong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010029","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133410","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T23:35:00Z","timestamp":1782257700000},"page":"133410","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["A teleoperation-guided incremental preference learning approach for wheel mobile robots"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6580-1675","authenticated-orcid":false,"given":"Pengpeng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9745-4150","authenticated-orcid":false,"given":"Weihua","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bindi","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133410_b0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111693","article-title":"A semantic SLAM-based method for navigation and landing of UAVs in indoor environments","volume":"293","author":"Yang","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133410_b0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111925","article-title":"Deep-learning based autonomous-exploration for UAV navigation","volume":"297","author":"Zhao","year":"2024","journal-title":"Knowledge-Based Systems"},{"issue":"2","key":"10.1016\/j.eswa.2026.133410_b0015","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1109\/LRA.2020.3048668","article-title":"Reinforcement learning-based visual navigation with information-theoretic regularization","volume":"6","author":"Wu","year":"2021","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.eswa.2026.133410_b0020","doi-asserted-by":"crossref","first-page":"10368","DOI":"10.1109\/TASE.2024.3522665","article-title":"Memorize my movement: Efficient sensorimotor navigation with self-motion-based spatial cognition","volume":"22","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"issue":"1","key":"10.1016\/j.eswa.2026.133410_b0025","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1109\/LRA.2024.3511437","article-title":"Deep reinforcement learning-based mapless navigation for mobile robot in unknown environment with local optima","volume":"10","author":"Hu","year":"2025","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"6","key":"10.1016\/j.eswa.2026.133410_b0030","doi-asserted-by":"crossref","first-page":"8907","DOI":"10.1109\/TII.2024.3378829","article-title":"Toward learning-based visuomotor navigation with neural radiance fields","volume":"20","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.133410_b0035","doi-asserted-by":"crossref","first-page":"4236","DOI":"10.1109\/TRO.2025.3582817","article-title":"Help me through: Imitation learning based active view planning to avoid SLAM tracking failures","volume":"41","author":"Naveed","year":"2025","journal-title":"IEEE Transactions on Robotics"},{"issue":"1","key":"10.1016\/j.eswa.2026.133410_b0040","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1109\/TIE.2025.3589442","article-title":"Deep multimodal imitation learning-based framework for robot-assisted medical examination","volume":"73","author":"Si","year":"2026","journal-title":"IEEE Transactions on Industrial Electronics"},{"issue":"3","key":"10.1016\/j.eswa.2026.133410_b0045","doi-asserted-by":"crossref","first-page":"1841","DOI":"10.1109\/TIV.2024.3436587","article-title":"Hierarchical generative adversarial imitation learning with mid-level input generation for autonomous driving on urban environments","volume":"10","author":"Couto","year":"2025","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"10.1016\/j.eswa.2026.133410_b0050","doi-asserted-by":"crossref","first-page":"4301","DOI":"10.1109\/TRO.2024.3431988","article-title":"Efficient deep learning of robust policies from MPC using imitation and tube-guided data augmentation","volume":"40","author":"Tagliabue","year":"2024","journal-title":"IEEE Transactions on Robotics"},{"issue":"1","key":"10.1016\/j.eswa.2026.133410_b0055","doi-asserted-by":"crossref","first-page":"2908","DOI":"10.1109\/TIV.2023.3309962","article-title":"Imitation learning of nonlinear model predictive control for emergency collision avoidance","volume":"9","author":"Kim","year":"2024","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"10.1016\/j.eswa.2026.133410_b0060","doi-asserted-by":"crossref","unstructured":"Lee, S. W., Kang, X., & Kuo, Y. L. (2025). Diff-DAgger: Uncertainty estimation with diffusion policy for robotic manipulation. In Proceedings of the 2025 IEEE International Conference on Robotics and Automation (ICRA) (pp. 4845\u20134852). https:\/\/doi.org\/10.1109\/ICRA55743.2025.11127730.","DOI":"10.1109\/ICRA55743.2025.11127730"},{"issue":"3","key":"10.1016\/j.eswa.2026.133410_b0065","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1109\/LRA.2025.3536297","article-title":"Greedy-DAgger: A student rollout efficient imitation learning algorithm","volume":"10","author":"Torok","year":"2025","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.eswa.2026.133410_b0070","doi-asserted-by":"crossref","unstructured":"Lima, R., Saha, S., Vakharia, V., Vatsal, V., & Das, K. (2024). Augmenting robot teleoperation with shared autonomy via model predictive control. In Proceedings of the IEEE Conference on Telepresence (Telepresence) (pp. 42\u201348). https:\/\/doi.org\/10.1109\/Telepresence63209.2024.10841639.","DOI":"10.1109\/Telepresence63209.2024.10841639"},{"key":"10.1016\/j.eswa.2026.133410_b0075","doi-asserted-by":"crossref","unstructured":"Saparia, S., Schimpe, A., & Ferranti, L. (2021). Active safety system for semi-autonomous teleoperated vehicles. In Proceedings of the IEEE Intelligent Vehicles Symposium Workshops (IV Workshops) (pp. 141\u2013147). https:\/\/doi.org\/10.1109\/IVWorkshops54471.2021.9669239.","DOI":"10.1109\/IVWorkshops54471.2021.9669239"},{"issue":"2","key":"10.1016\/j.eswa.2026.133410_b0080","doi-asserted-by":"crossref","first-page":"1634","DOI":"10.1109\/LRA.2025.3643275","article-title":"A shared-control teleoperation system based on potential-field-constraint prediction","volume":"11","author":"Li","year":"2026","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"3","key":"10.1016\/j.eswa.2026.133410_b0085","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1109\/THMS.2022.3155716","article-title":"Shared control in robot teleoperation with improved potential fields","volume":"52","author":"Gottardi","year":"2022","journal-title":"IEEE Transactions on Human-Machine Systems"},{"key":"10.1016\/j.eswa.2026.133410_b0090","doi-asserted-by":"crossref","first-page":"15953","DOI":"10.1109\/TASE.2025.3572103","article-title":"A telerobotic shared control architecture for learning and generalizing skills in unstructured environments","volume":"22","author":"Shao","year":"2025","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"issue":"12","key":"10.1016\/j.eswa.2026.133410_b0095","doi-asserted-by":"crossref","first-page":"16654","DOI":"10.1109\/TIE.2024.3401185","article-title":"Dynamic movement primitives-based human action prediction and shared control for bilateral robot teleoperation","volume":"71","author":"Lu","year":"2024","journal-title":"IEEE Transactions on Industrial Electronics"},{"issue":"11","key":"10.1016\/j.eswa.2026.133410_b0100","doi-asserted-by":"crossref","first-page":"6252","DOI":"10.1109\/TFUZZ.2024.3443713","article-title":"Imitation learning and teleoperation shared control with unit tangent fuzzy movement primitives","volume":"32","author":"Wen","year":"2024","journal-title":"IEEE Transactions on Fuzzy Systems"},{"key":"10.1016\/j.eswa.2026.133410_b0105","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Zhou, Z., Mao, F., Wu, W., Zhao, S., & Ju, L. (2025). FlexRLHF: A flexible placement and parallelism framework for efficient RLHF training. In Proceedings of the 2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (pp. 358\u2013369). https:\/\/doi.org\/10.1109\/IPDPS64566.2025.00039.","DOI":"10.1109\/IPDPS64566.2025.00039"},{"key":"10.1016\/j.eswa.2026.133410_b0110","doi-asserted-by":"crossref","unstructured":"Hu, T., Zhu, W., & Yan, Y. (2025). Reward hacking in reinforcement learning and RLHF: A multidisciplinary examination of vulnerabilities, mitigation strategies, and alignment challenges. In Proceedings of the 2025 5th Intelligent Cybersecurity Conference (ICSC) (pp. 272\u2013275). https:\/\/doi.org\/10.1109\/ICSC65596.2025.11140447.","DOI":"10.1109\/ICSC65596.2025.11140447"},{"key":"10.1016\/j.eswa.2026.133410_b0115","doi-asserted-by":"crossref","unstructured":"Zhao, J., Lei, Y., Zheng, W., Lai, S., Ding, H., & Zhao, C. (2025). Optimizing RLHF reward models with fairness constraints. In Proceedings of the 2025 5th International Conference on Computer Science and Blockchain (CCSB) (pp. 218\u2013221). https:\/\/doi.org\/10.1109\/CCSB66722.2025.11154240.","DOI":"10.1109\/CCSB66722.2025.11154240"},{"key":"10.1016\/j.eswa.2026.133410_b0120","doi-asserted-by":"crossref","unstructured":"Zhu, K., Wang, Y., Sun, Y., Chen, Q., Liu, J., Zhang, G., & Wang, J. (2025). Continual SFT matches multimodal RLHF with negative supervision. In Proceedings of the 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 14615\u201314624). https:\/\/doi.org\/10.1109\/CVPR52734.2025.01362.","DOI":"10.1109\/CVPR52734.2025.01362"},{"key":"10.1016\/j.eswa.2026.133410_b0125","doi-asserted-by":"crossref","unstructured":"Kumar, A., Perrault, A., & Williamson, D. S. (2025). Using RLHF to align speech enhancement approaches to mean-opinion quality scores. In Proceedings of ICASSP 2025\u20142025 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 1\u20135). https:\/\/doi.org\/10.1109\/ICASSP49660.2025.10888446.","DOI":"10.1109\/ICASSP49660.2025.10888446"},{"key":"10.1016\/j.eswa.2026.133410_b0130","doi-asserted-by":"crossref","unstructured":"Sivan, D., Kumar, K. S., Raj, V., & Jose, R. (2024). Reinforcement learning from human feedback (RLHF). In Generative AI and LLMs: Natural language processing and generative adversarial networks (pp. 135\u2013154). De Gruyter.","DOI":"10.1515\/9783111425078-007"},{"issue":"7","key":"10.1016\/j.eswa.2026.133410_b0135","doi-asserted-by":"crossref","first-page":"4600","DOI":"10.1109\/TSMC.2021.3098451","article-title":"Proximal policy optimization with policy feedback","volume":"52","author":"Gu","year":"2022","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"8","key":"10.1016\/j.eswa.2026.133410_b0140","doi-asserted-by":"crossref","first-page":"9181","DOI":"10.1109\/TITS.2024.3375890","article-title":"A novel confined attention mechanism driven Bi-GRU model for traffic flow prediction","volume":"25","author":"Chauhan","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"11","key":"10.1016\/j.eswa.2026.133410_b0145","doi-asserted-by":"crossref","first-page":"18122","DOI":"10.1109\/TITS.2024.3424808","article-title":"Knowledge distillation-based spatio-temporal MLP model for real-time traffic flow prediction","volume":"25","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2026.133410_b0150","doi-asserted-by":"crossref","unstructured":"Kaji, H. (2024). User clustering for pairwise comparison with missing values using Bradley-Terry model and consensus clustering. In Proceedings of the 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 3930\u20133936). https:\/\/doi.org\/10.1109\/SMC54092.2024.10831435.","DOI":"10.1109\/SMC54092.2024.10831435"},{"issue":"11","key":"10.1016\/j.eswa.2026.133410_b0155","doi-asserted-by":"crossref","first-page":"6898","DOI":"10.1109\/TIV.2024.3391007","article-title":"Attention-based value classification reinforcement learning for collision-free robot navigation","volume":"9","author":"Sun","year":"2024","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"issue":"1","key":"10.1016\/j.eswa.2026.133410_b0160","doi-asserted-by":"crossref","first-page":"3667","DOI":"10.1109\/TTE.2024.3429186","article-title":"Comprehensive analysis of adaptive soft actor-critic reinforcement learning-based control framework for autonomous driving in varied scenarios","volume":"11","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Transportation Electrification"},{"key":"10.1016\/j.eswa.2026.133410_b0165","doi-asserted-by":"crossref","DOI":"10.3389\/frobt.2025.1625968","article-title":"Adaptive mapless mobile robot navigation using deep reinforcement learning based improved TD3 algorithm","volume":"12","author":"Nasti","year":"2025","journal-title":"Frontiers in Robotics and AI"},{"issue":"6","key":"10.1016\/j.eswa.2026.133410_b0170","doi-asserted-by":"crossref","first-page":"8181","DOI":"10.1109\/TII.2024.3369712","article-title":"Value distribution DDPG with dual-prioritized experience replay for coordinated control of coal-fired power generation systems","volume":"20","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.133410_b0175","unstructured":"Schulman, J., Levine, S., Moritz, P., Jordan, M., & Abbeel, P. (2015). Trust region policy optimization. In Proceedings of the International Conference on Machine Learning (ICML) (pp. 1889\u20131897)."}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426023195?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426023195?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:44:07Z","timestamp":1782492247000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426023195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":35,"alternative-id":["S0957417426023195"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133410","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A teleoperation-guided incremental preference learning approach for wheel mobile robots","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133410","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133410"}}