{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T09:55:47Z","timestamp":1791971747384,"version":"4.3.4"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T00:00:00Z","timestamp":1788566400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"vor","delay-in-days":39,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"DOI":"10.1038\/s41467-026-77370-x","type":"journal-article","created":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T08:24:33Z","timestamp":1788596673000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Human-guided continual learning for multifaceted improvement of self-driving vehicles"],"prefix":"10.1038","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1545-2793","authenticated-orcid":false,"given":"Haohan","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanxin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2769-4183","authenticated-orcid":false,"given":"Xiaosong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haochen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyue","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6897-4512","authenticated-orcid":false,"given":"Chen","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,5]]},"reference":[{"key":"77370_CR1","doi-asserted-by":"publisher","first-page":"eaaw1975","DOI":"10.1126\/scirobotics.aaw1975","volume":"4","author":"NA Spielberg","year":"2019","unstructured":"Spielberg, N. A. et al. Neural network vehicle models for high-performance automated driving. Sci. Robot. 4, eaaw1975 (2019).","journal-title":"Sci. Robot."},{"key":"77370_CR2","doi-asserted-by":"publisher","first-page":"eaaw0863","DOI":"10.1126\/scirobotics.aaw0863","volume":"4","author":"W Li","year":"2019","unstructured":"Li, W. et al. AADS: Augmented autonomous driving simulation using data-driven algorithms. Sci. Robot. 4, eaaw0863 (2019).","journal-title":"Sci. Robot."},{"key":"77370_CR3","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/s42256-022-00520-5","volume":"4","author":"Y Almalioglu","year":"2022","unstructured":"Almalioglu, Y. et al. Deep learning-based robust positioning for all-weather autonomous driving. Nat. Mach. Intell. 4, 749\u2013760 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"77370_CR4","first-page":"90","volume":"9","author":"P Koopman","year":"2017","unstructured":"Koopman, P. & Wagner, M. Autonomous vehicle safety: an interdisciplinary challenge. IEEE Intell. Transp. Syst. Mag. 9, 90\u201396 (2017).","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"77370_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48526-4","volume":"15","author":"M Abdel-Aty","year":"2024","unstructured":"Abdel-Aty, M. & Ding, S. A matched case-control analysis of autonomous vs human-driven vehicle accidents. Nat. Commun. 15, 4931 (2024).","journal-title":"Nat. Commun."},{"key":"77370_CR6","doi-asserted-by":"publisher","first-page":"532","DOI":"10.2105\/AJPH.2016.303628","volume":"107","author":"J Fleetwood","year":"2017","unstructured":"Fleetwood, J. Public health, ethics, and autonomous vehicles. Am. J. Public Health 107, 532\u2013537 (2017).","journal-title":"Am. J. Public Health"},{"key":"77370_CR7","doi-asserted-by":"publisher","first-page":"110692","DOI":"10.1016\/j.automatica.2022.110692","volume":"152","author":"N Mehdipour","year":"2023","unstructured":"Mehdipour, N. et al. Formal methods to comply with rules of the road in autonomous driving: state of the art and grand challenges. Automatica 152, 110692 (2023).","journal-title":"Automatica"},{"key":"77370_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44694-5","volume":"15","author":"W Yu","year":"2024","unstructured":"Yu, W. et al. Online legal driving behavior monitoring for self-driving vehicles. Nat. Commun. 15, 408 (2024).","journal-title":"Nat. Commun."},{"key":"77370_CR9","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1038\/s41586-023-05732-2","volume":"615","author":"S Feng","year":"2023","unstructured":"Feng, S. et al. Dense reinforcement learning for safety validation of autonomous vehicles. Nature 615, 620\u2013627 (2023).","journal-title":"Nature"},{"key":"77370_CR10","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1038\/s42256-023-00610-y","volume":"5","author":"Z Cao","year":"2023","unstructured":"Cao, Z. et al. Continuous improvement of self-driving cars using dynamic confidence-aware reinforcement learning. Nat. Mach. Intell. 5, 145\u2013158 (2023).","journal-title":"Nat. Mach. Intell."},{"key":"77370_CR11","doi-asserted-by":"publisher","first-page":"3005","DOI":"10.1007\/s10462-022-10246-w","volume":"56","author":"E Mosqueira-Rey","year":"2023","unstructured":"Mosqueira-Rey, E. et al. Human-in-the-loop machine learning: a state of the art. Artif. Intell. Rev. 56, 3005\u20133054 (2023).","journal-title":"Artif. Intell. Rev."},{"key":"77370_CR12","doi-asserted-by":"publisher","first-page":"eaah5682","DOI":"10.1126\/scirobotics.aah5682","volume":"1","author":"HE Russell","year":"2016","unstructured":"Russell, H. E. et al. Motor learning affects car-to-driver handover in automated vehicles. Sci. Robot. 1, eaah5682 (2016).","journal-title":"Sci. Robot."},{"key":"77370_CR13","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1109\/TIV.2022.3154426","volume":"7","author":"S Ansari","year":"2022","unstructured":"Ansari, S., Naghdy, F. & Du, H. Human-machine shared driving: challenges and future directions. IEEE Trans. Intell. Veh. 7, 499\u2013519 (2022).","journal-title":"IEEE Trans. Intell. Veh."},{"key":"77370_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, J. & Cho, K. Query-efficient imitation learning for end-to-end autonomous driving. In Proceedings of the AAAI Conference on Artificial Intelligence 2891\u20132897 (AAAI, 2018).","DOI":"10.1609\/aaai.v31i1.10857"},{"key":"77370_CR15","unstructured":"Scheel, O. et al. Urban driver: Learning to drive from real-world demonstrations using policy gradients. In Proceedings of the Conference on Robot Learning 718\u2013728 (PMLR, 2022)."},{"key":"77370_CR16","doi-asserted-by":"publisher","first-page":"7391","DOI":"10.1109\/TNNLS.2022.3142822","volume":"34","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Wu, J. & Lv, C. Efficient deep reinforcement learning with imitative expert priors for autonomous driving. IEEE Trans. Neural Netw. Learn. Syst. 34, 7391\u20137403 (2023).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"77370_CR17","unstructured":"Reddy, S., Dragan, A. D. & Levine, S. Sqil: Imitation learning via reinforcement learning with sparse rewards. In Proc. International Conference on Learning Representations 1\u201314 (ICLR, 2020)."},{"key":"77370_CR18","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1177\/02783649211041652","volume":"41","author":"M Palan","year":"2022","unstructured":"Palan, M. et al. Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferences. Int. J. Rob. Res. 41, 45\u201367 (2022).","journal-title":"Int. J. Rob. Res."},{"key":"77370_CR19","unstructured":"MacGlashan, J. et al. Interactive learning from policy-dependent human feedback. In Proceedings of the International Conference on Machine Learning 2285\u20132294 (PMLR, 2017)."},{"key":"77370_CR20","doi-asserted-by":"crossref","unstructured":"Kendall, A. et al. Learning to drive in a day. In Proceedings of the International Conference on Robotics and Automation 8248\u20138254 (IEEE, 2019).","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"77370_CR21","doi-asserted-by":"publisher","first-page":"7744","DOI":"10.1109\/LRA.2021.3100940","volume":"6","author":"Z Wang","year":"2021","unstructured":"Wang, Z. et al. APPLE: adaptive planner parameter learning from evaluative feedback. IEEE Robot. Autom. Lett. 6, 7744\u20137749 (2021).","journal-title":"IEEE Robot. Autom. Lett."},{"key":"77370_CR22","doi-asserted-by":"crossref","unstructured":"Kelly, M. et al. Hg-dagger: Interactive imitation learning with human experts. In Proceedings of the International Conference on Robotics and Automation 8077\u20138083 (IEEE, 2019).","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"77370_CR23","doi-asserted-by":"publisher","first-page":"77969","DOI":"10.52202\/075280-3406","volume":"36","author":"Z Peng","year":"2023","unstructured":"Peng, Z. et al. Learning from active human involvement through proxy value propagation. Adv. Neural Inf. Process. Syst. 36, 77969\u201377992 (2023).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"77370_CR24","doi-asserted-by":"publisher","first-page":"6595","DOI":"10.1109\/TSMC.2024.3384992","volume":"54","author":"J Wu","year":"2024","unstructured":"Wu, J. et al. Human-guided deep reinforcement learning for optimal decision making of autonomous vehicles. IEEE Trans. Syst. Man Cybern. Syst. 54, 6595\u20136609 (2024).","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"77370_CR25","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1038\/s42256-020-0225-y","volume":"2","author":"C Pek","year":"2020","unstructured":"Pek, C. et al. Using online verification to prevent autonomous vehicles from causing accidents. Nat. Mach. Intell. 2, 518\u2013528 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"77370_CR26","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1038\/s42256-022-00607-z","volume":"5","author":"M Geisslinger","year":"2023","unstructured":"Geisslinger, M., Poszler, F. & Lienkamp, M. An ethical trajectory planning algorithm for autonomous vehicles. Nat. Mach. Intell. 5, 137\u2013144 (2023).","journal-title":"Nat. Mach. Intell."},{"key":"77370_CR27","doi-asserted-by":"publisher","first-page":"1380","DOI":"10.1109\/TIV.2022.3184729","volume":"8","author":"Z Cao","year":"2023","unstructured":"Cao, Z. et al. Autonomous driving policy continual learning with one-shot disengagement case. IEEE Trans. Intell. Veh. 8, 1380\u20131391 (2023).","journal-title":"IEEE Trans. Intell. Veh."},{"key":"77370_CR28","doi-asserted-by":"publisher","first-page":"14745","DOI":"10.1109\/TPAMI.2023.3314762","volume":"45","author":"J Wu","year":"2023","unstructured":"Wu, J. et al. Human-guided reinforcement learning with sim-to-real transfer for autonomous navigation. IEEE Trans. Pattern Anal. Mach. Intell. 45, 14745\u201314759 (2023).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"77370_CR29","doi-asserted-by":"crossref","unstructured":"Kato, S. et al. Autoware on board: enabling autonomous vehicles with embedded systems. In Proceedings of the ACM\/IEEE International Conference on Cyber-Physical Systems 287\u2013296 (IEEE, 2018).","DOI":"10.1109\/ICCPS.2018.00035"},{"key":"77370_CR30","doi-asserted-by":"crossref","unstructured":"Hu, Y. et al. Planning-oriented autonomous driving. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 17853\u201317862 (IEEE, 2023).","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"77370_CR31","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1038\/s42256-022-00568-3","volume":"4","author":"GM van de Ven","year":"2022","unstructured":"van de Ven, G. M., Tuytelaars, T. & Tolias, A. S. Three types of incremental learning. Nat. Mach. Intell. 4, 1185\u20131197 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"77370_CR32","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1038\/s42256-023-00747-w","volume":"5","author":"L Wang","year":"2023","unstructured":"Wang, L. et al. Incorporating neuro-inspired adaptability for continual learning in artificial intelligence. Nat. Mach. Intell. 5, 1356\u20131368 (2023).","journal-title":"Nat. Mach. Intell."},{"key":"77370_CR33","unstructured":"Rype\u015b\u0107, G. et al. Divide and not forget: an ensemble of selectively trained experts in continual learning. In Proceedings of the International Conference on Learning Representations 1\u201318 (ICLR, 2024)."},{"key":"77370_CR34","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/s41562-025-02318-y","volume":"10","author":"E Holton","year":"2026","unstructured":"Holton, E. et al. Humans and neural networks show similar patterns of transfer and interference during continual learning. Nat. Hum. Behav. 10, 111\u2013125 (2026).","journal-title":"Nat. Hum. Behav."},{"key":"77370_CR35","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A. et al. Conservative Q-learning for offline reinforcement learning. Adv. Neural Inf. Process. Syst. 33, 1179\u20131191 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"77370_CR36","unstructured":"Dosovitskiy, A. et al. CARLA: An open urban driving simulator. In Proceedings of the Conference on Robot Learning 1\u201316 (PMLR, 2017)."},{"key":"77370_CR37","doi-asserted-by":"publisher","first-page":"106454","DOI":"10.1016\/j.aap.2021.106454","volume":"163","author":"JM Scanlon","year":"2021","unstructured":"Scanlon, J. M. et al. Waymo simulated driving behavior in reconstructed fatal crashes within an autonomous vehicle operating domain. Accid. Anal. Prev. 163, 106454 (2021).","journal-title":"Accid. Anal. Prev."},{"key":"77370_CR38","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1038\/s41586-024-07711-7","volume":"632","author":"S Dohare","year":"2024","unstructured":"Dohare, S. et al. Loss of plasticity in deep continual learning. Nature 632, 768\u2013774 (2024).","journal-title":"Nature"},{"key":"77370_CR39","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1038\/s42256-025-00983-2","volume":"7","author":"Y Meng","year":"2025","unstructured":"Meng, Y. et al. Preserving and combining knowledge in robotic lifelong reinforcement learning. Nat. Mach. Intell. 7, 256\u2013269 (2025).","journal-title":"Nat. Mach. Intell."},{"key":"77370_CR40","doi-asserted-by":"publisher","first-page":"3790","DOI":"10.1109\/TITS.2020.3025670","volume":"22","author":"A Bucchiarone","year":"2021","unstructured":"Bucchiarone, A. et al. Autonomous shuttle-as-a-service: Challenges, opportunities, and social implications. IEEE Trans. Intell. Transp. Syst. 22, 3790\u20133799 (2021).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"77370_CR41","doi-asserted-by":"publisher","first-page":"102834","DOI":"10.1016\/j.tre.2022.102834","volume":"165","author":"S Srinivas","year":"2022","unstructured":"Srinivas, S., Ramachandiran, S. & Rajendran, S. Autonomous robot-driven deliveries: a review of recent developments and future directions. Transp. Res. Pt. E-Logist. Transp. Rev. 165, 102834 (2022).","journal-title":"Transp. Res. Pt. E-Logist. Transp. Rev."},{"key":"77370_CR42","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1038\/s43586-024-00363-x","volume":"4","author":"J Healy","year":"2024","unstructured":"Healy, J. & McInnes, L. Uniform manifold approximation and projection. Nat. Rev. Methods Prim. 4, 82 (2024).","journal-title":"Nat. Rev. Methods Prim."},{"key":"77370_CR43","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J. et al. Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. USA 114, 3521\u20133526 (2017).","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"77370_CR44","first-page":"3742","volume":"31","author":"H Ritter","year":"2018","unstructured":"Ritter, H., Botev, A. & Barber, D. Online structured Laplace approximations for overcoming catastrophic forgetting. Adv. Neural Inf. Process. Syst. 31, 3742\u20133752 (2018).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"77370_CR45","doi-asserted-by":"crossref","unstructured":"Lee, J. et al. Continual learning with extended Kronecker-factored approximate curvature. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 9001\u20139010 (IEEE, 2020).","DOI":"10.1109\/CVPR42600.2020.00902"},{"key":"77370_CR46","unstructured":"Schwarz, J. et al. Progress & compress: a scalable framework for continual learning. In Proceedings of the International Conference on Machine Learning 4528\u20134537 (PMLR, 2018)."},{"key":"77370_CR47","first-page":"22379","volume":"34","author":"L Wang","year":"2021","unstructured":"Wang, L. et al. AFEC: active forgetting of negative transfer in continual learning. Adv. Neural Inf. Process. Syst. 34, 22379\u201322391 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"77370_CR48","doi-asserted-by":"publisher","first-page":"5435","DOI":"10.1109\/TITS.2024.3524609","volume":"26","author":"H Yang","year":"2025","unstructured":"Yang, H. et al. Human-guided continual learning for personalized decision-making of autonomous driving. IEEE Trans. Intell. Transp. Syst. 26, 5435\u20135447 (2025).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"77370_CR49","doi-asserted-by":"publisher","first-page":"e2401626122","DOI":"10.1073\/pnas.2401626122","volume":"122","author":"H Lu","year":"2025","unstructured":"Lu, H. et al. Empowering safer, socially sensitive autonomous vehicles using human-plausible cognitive encoding. Proc. Natl. Acad. Sci. USA 122, e2401626122 (2025).","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"77370_CR50","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10994-009-5152-4","volume":"79","author":"BD Shai","year":"2010","unstructured":"Shai, B. D. et al. A theory of learning from different domains. Mach. Learn. 79, 151\u2013175 (2010).","journal-title":"Mach. Learn."},{"key":"77370_CR51","doi-asserted-by":"crossref","unstructured":"McAllester, D. A. PAC-Bayesian model averaging. In Proceedings of the Annual Conference Computational Learning Theory 164\u2013170 (ACM, 1999).","DOI":"10.1145\/307400.307435"},{"key":"77370_CR52","first-page":"22405","volume":"34","author":"J Cha","year":"2021","unstructured":"Cha, J. et al. SWAD: domain generalization by seeking flat minima. Adv. Neural Inf. Process. Syst. 34, 22405\u201322418 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"77370_CR53","doi-asserted-by":"publisher","unstructured":"Yang, H. Human-guided continual learning for multifaceted improvement of self-driving vehicles. HugCL https:\/\/doi.org\/10.5281\/zenodo.20834824 (2026).","DOI":"10.5281\/zenodo.20834824"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77370-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77370-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77370-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T09:38:21Z","timestamp":1791970701000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77370-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,5]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["77370"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-77370-x","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,5]]},"assertion":[{"value":"30 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"10779"}}