{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:18:12Z","timestamp":1792783092056,"version":"4.5.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":85,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National Natural Science Foundation of China","award":["92248303; 62073191"],"award-info":[{"award-number":["92248303; 62073191"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Shandong Provincial Natural Science Foundation","award":["ZR2022MF296"],"award-info":[{"award-number":["ZR2022MF296"]}]},{"name":"Shandong Province Higher Educational Youth and Innovation Talent Introduction and Education Program"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Wheeled-legged robots have gained attention for their potential to combine the efficiency of wheels with the adaptability of legs. However, most prior research has focused on lightweight platforms. In this work, we present the first successful deployment of a reinforcement learning (RL) controller on a heavy wheeled-legged robot weighing over 340 kg, which, to the best of our knowledge, is one of the largest and heaviest wheeled-legged robots reported in the literature to demonstrate RL-based hybrid locomotion control. We propose a robust end-to-end control framework, incorporating a heuristic reward structure and a state estimator trained via privileged learning. Simulation experiments demonstrate accurate speed tracking performance, strong robustness to external disturbances, and graceful performance degradation under slow-response actuation. Field experiments, including plateau trials on gobi deserts, gravel, meadows, and wetlands, further demonstrate the policy\u2019s robustness, terrain adaptability, and real-world deployability, with a maximum measured speed of 3.80\u00a0m\/s achieved in outdoor tests. These simulation and field results establish a benchmark for deploying RL on heavy robotic systems under real-world constraints.<\/jats:p>","DOI":"10.1007\/s10846-026-02423-8","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T15:16:58Z","timestamp":1782919018000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning-Based Hybrid Locomotion Control for a Heavy Wheeled-Legged Robot in Challenging Terrains"],"prefix":"10.1007","volume":"112","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8070-9567","authenticated-orcid":false,"given":"Jinmian","family":"Hou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Chai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoteng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"key":"2423_CR1","doi-asserted-by":"publisher","unstructured":"Krotkov, E., Hackett, D., Jackel, L., Perschbacher, M., Pippine, J., Strauss, J., Pratt, G., Orlowski, C.: The DARPA Robotics Challenge Finals: Results and Perspectives. J. Field Robot. 34(2), 229\u2013240 (2017). https:\/\/doi.org\/10.1002\/rob.21683","DOI":"10.1002\/rob.21683"},{"key":"2423_CR2","doi-asserted-by":"crossref","unstructured":"Torres-Pardo, A., Pinto-Fern\u00e1ndez, D., Garabini, M., Angelini, F., Rodriguez-Cianca, D., Massardi, S., Tornero, J., Moreno, J.C., Torricelli, D.: Legged locomotion over irregular terrains: state of the art of human and robot performance. Bioinspir. Biomim. 17(6), 061002 (2022)","DOI":"10.1088\/1748-3190\/ac92b3"},{"key":"2423_CR3","doi-asserted-by":"crossref","unstructured":"Rubio, F., Valero, F., Llopis-Albert, C.: A review of mobile robots: concepts, methods, theoretical framework, and applications. Int. J. Adv. Robot. Syst. 16(2), 1729881419839596 (2019)","DOI":"10.1177\/1729881419839596"},{"key":"2423_CR4","doi-asserted-by":"crossref","unstructured":"Datar, A., Pan, C., Nazeri, M., Xiao, X.: Toward wheeled mobility on vertically challenging terrain: platforms, datasets, and algorithms. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 16322\u201316329 (2024)","DOI":"10.1109\/ICRA57147.2024.10610079"},{"key":"2423_CR5","doi-asserted-by":"crossref","unstructured":"Wang, N., Li, X., Zhang, K., Wang, J., Xie, D.: A survey on path planning for autonomous ground vehicles in unstructured environments. Machines 12(1), 31 (2024)","DOI":"10.3390\/machines12010031"},{"key":"2423_CR6","doi-asserted-by":"crossref","unstructured":"Delmerico, J., Mintchev, S., Giusti, A., Gromov, B., Melo, K., Horvat, T., Cadena, C., Hutter, M., Ijspeert, A., Floreano, D., et al.: The current state and future outlook of rescue robotics. J. Field Robot. 36(7), 1171\u20131191 (2019)","DOI":"10.1002\/rob.21887"},{"key":"2423_CR7","doi-asserted-by":"crossref","unstructured":"Hoeller, D., Rudin, N., Sako, D., Hutter, M.: ANYmal parkour: learning agile navigation for quadrupedal robots. Sci. Robot. 9(88), eadi7566 (2024)","DOI":"10.1126\/scirobotics.adi7566"},{"key":"2423_CR8","doi-asserted-by":"crossref","unstructured":"Katz, B., Di Carlo, J., Kim, S.: Mini Cheetah: a platform for pushing the limits of dynamic quadruped control. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 6295\u20136301 (2019)","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"2423_CR9","doi-asserted-by":"publisher","unstructured":"Fankhauser, P., Bjelonic, M., Bellicoso, C.D., Miki, T., Hutter, M.: Robust rough-terrain locomotion with a quadrupedal robot. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 5761\u20135768 (2018). https:\/\/doi.org\/10.1109\/ICRA.2018.8460731","DOI":"10.1109\/ICRA.2018.8460731"},{"issue":"2","key":"2423_CR10","doi-asserted-by":"publisher","first-page":"2116","DOI":"10.1109\/LRA.2019.2899750","volume":"4","author":"M Bjelonic","year":"2019","unstructured":"Bjelonic, M., Bellicoso, C.D., Viragh, Y., Sako, D., Tresoldi, F.D., Jenelten, F., Hutter, M.: Keep rollin\u2019\u2014whole-body motion control and planning for wheeled quadrupedal robots. IEEE Robot. Autom. Lett. 4(2), 2116\u20132123 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"2","key":"2423_CR11","doi-asserted-by":"publisher","first-page":"3626","DOI":"10.1109\/LRA.2020.2979661","volume":"5","author":"M Bjelonic","year":"2020","unstructured":"Bjelonic, M., Sankar, P.K., Bellicoso, C.D., Vallery, H., Hutter, M.: Rolling in the deep-hybrid locomotion for wheeled-legged robots using online trajectory optimization. IEEE Robot. Autom. Lett. 5(2), 3626\u20133633 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2423_CR12","doi-asserted-by":"publisher","unstructured":"Arnold, M., Hildebrandt, L., Janssen, K., Ongan, E., B\u00fcrge, P., G\u00e1briel, \u00c1.G., Kennedy, J., Lolla, R., Oppliger, Q., Schaaf, M., Church, J., Fritsche, M., Klemm, V., Tuna, T., Valsecchi, G., Weibel, C., W\u00fcthrich, M., Hutter, M.: Leva: A high-mobility logistic vehicle with legged suspension (2025). arXiv:2503.10028, https:\/\/doi.org\/10.48550\/arXiv.2503.10028","DOI":"10.48550\/arXiv.2503.10028"},{"key":"2423_CR13","doi-asserted-by":"publisher","unstructured":"Wang, Y., Chen, T., Rong, X., Zhang, G., Li, Y., Xin, Y.: Design and control of skater: A wheeled-bipedal robot with high-speed turning robustness and terrain adaptability. IEEE\/ASME Trans. Mechatron. pp. 1\u201312 (2024). https:\/\/doi.org\/10.1109\/TMECH.2024.3420390","DOI":"10.1109\/TMECH.2024.3420390"},{"key":"2423_CR14","doi-asserted-by":"publisher","unstructured":"Kim, G., Lee, Y.-H., Park, H.-W.: A learning framework for diverse legged robot locomotion using barrier-based style rewards (2024). arXiv:2409.15780, https:\/\/doi.org\/10.48550\/arXiv.2409.15780","DOI":"10.48550\/arXiv.2409.15780"},{"key":"2423_CR15","doi-asserted-by":"publisher","unstructured":"Aswin\u00a0Nahrendra, I.M., Yu, B., Myung, H.: Dreamwaq: Learning robust quadrupedal locomotion with implicit terrain imagination via deep reinforcement learning. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 5078\u20135084 (2023). https:\/\/doi.org\/10.1109\/ICRA48891.2023.10161144","DOI":"10.1109\/ICRA48891.2023.10161144"},{"key":"2423_CR16","doi-asserted-by":"publisher","unstructured":"Chamorro, S., Klemm, V., Iglesia\u00a0Valls, M., Pal, C.J., Siegwart, R.: Reinforcement learning for blind stair climbing with legged and wheeled\/legged robots. In: Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 8081\u20138087 (2024). https:\/\/doi.org\/10.1109\/ICRA57147.2024.10610069. IEEE","DOI":"10.1109\/ICRA57147.2024.10610069"},{"key":"2423_CR17","doi-asserted-by":"crossref","unstructured":"Reid, W., Emanuel, B., Chamberlain-Simon, B., Karumanchi, S., Meirion-Griffith, G.: Mobility mode evaluation of a wheel-on-limb rover on glacial ice analogous to europa terrain. In: 2020 IEEE Aerospace Conference, pp. 1\u20139 (2020). IEEE","DOI":"10.1109\/AERO47225.2020.9172805"},{"key":"2423_CR18","doi-asserted-by":"crossref","unstructured":"Bjelonic, M., Grandia, R., Harley, O., Galliard, C., Zimmermann, S., Hutter, M.: Whole-body mpc and online gait sequence generation for wheeled-legged robots. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8388\u20138395 (2021). IEEE","DOI":"10.1109\/IROS51168.2021.9636371"},{"issue":"9\u201310","key":"2423_CR19","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1177\/02783649221102473","volume":"41","author":"M Bjelonic","year":"2022","unstructured":"Bjelonic, M., Grandia, R., Geilinger, M., Harley, O., Medeiros, V.S., Pajovic, V., Jelavic, E., Coros, S., Hutter, M.: Offline motion libraries and online mpc for advanced mobility skills. Int. J. Robot. Res. 41(9\u201310), 903\u2013924 (2022)","journal-title":"Int. J. Robot. Res."},{"issue":"47","key":"2423_CR20","doi-asserted-by":"publisher","first-page":"5986","DOI":"10.1126\/scirobotics.abc5986","volume":"5","author":"J Lee","year":"2020","unstructured":"Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning quadrupedal locomotion over challenging terrain. Sci. Robot. 5(47), 5986 (2020)","journal-title":"Sci. Robot."},{"issue":"62","key":"2423_CR21","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1126\/scirobotics.abk2822","volume":"7","author":"T Miki","year":"2022","unstructured":"Miki, T., Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning robust perceptive locomotion for quadrupedal robots in the wild. Sci. Robot. 7(62), 2822 (2022)","journal-title":"Sci. Robot."},{"issue":"12","key":"2423_CR22","doi-asserted-by":"publisher","first-page":"902","DOI":"10.3390\/machines12120902","volume":"12","author":"RAI Khan","year":"2024","unstructured":"Khan, R.A.I., Zhang, C., Deng, Z., Zhang, A., Pan, Y., Zhao, X., Shang, H., Li, R.: Multi-agent reinforcement learning tracking control of a bionic wheel-legged quadruped. Machines 12(12), 902 (2024)","journal-title":"Machines"},{"key":"2423_CR23","doi-asserted-by":"crossref","unstructured":"Lee, J., Bjelonic, M., Hutter, M.: Control of wheeled-legged quadrupeds using deep reinforcement learning. In: Climbing and Walking Robots Conference, pp. 119\u2013127 (2022). Springer","DOI":"10.1007\/978-3-031-15226-9_14"},{"issue":"89","key":"2423_CR24","doi-asserted-by":"publisher","first-page":"9641","DOI":"10.1126\/scirobotics.adi9641","volume":"9","author":"J Lee","year":"2024","unstructured":"Lee, J., Bjelonic, M., Reske, A., Wellhausen, L., Miki, T., Hutter, M.: Learning robust autonomous navigation and locomotion for wheeled-legged robots. Sci. Robot. 9(89), 9641 (2024)","journal-title":"Sci. Robot."},{"key":"2423_CR25","doi-asserted-by":"crossref","unstructured":"Vollenweider, E., Bjelonic, M., Klemm, V., Rudin, N., Lee, J., Hutter, M.: Advanced skills through multiple adversarial motion priors in reinforcement learning. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 5120\u20135126 (2023). IEEE","DOI":"10.1109\/ICRA48891.2023.10160751"},{"key":"2423_CR26","doi-asserted-by":"publisher","unstructured":"Lin, P.T., Chen, Z.-Y., Liaw, P.-R., Nguyen, V.L.: Design of a high-payload mecanum-wheel ground vehicle (MWGV). Robot. Syst. Appl. 1(1), 24\u201334 (2021). https:\/\/doi.org\/10.21595\/rsa.2021.22133","DOI":"10.21595\/rsa.2021.22133"},{"issue":"5","key":"2423_CR27","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1108\/IR.2012.04939eaa.005","volume":"39","author":"R Bloss","year":"2012","unstructured":"Bloss, R.: Robot walks on all four legs and carries a heavy load. Industrial Robot: An International Journal 39(5), 480\u2013481 (2012). https:\/\/doi.org\/10.1108\/IR.2012.04939eaa.005","journal-title":"Industrial Robot: An International Journal"},{"key":"2423_CR28","doi-asserted-by":"crossref","unstructured":"Michael, K.: Meet boston dynamics\u2019 ls3 - the latest robotic war machine. University of Wollongong (2012). Journal contribution","DOI":"10.64628\/AA.94t6spm79"},{"key":"2423_CR29","doi-asserted-by":"publisher","unstructured":"Ding, L., Gong, X., Hu, L., Wang, G., Shao, Z., Yang, H., Gao, H., Deng, Z.: Motion planning and contact force distribution for heavy-duty hexapod robots walking on unknown rugged terrains. J. Field Robot. 41(6), 1680\u20131701 (2024). https:\/\/doi.org\/10.1002\/rob.22338, https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/rob.22338","DOI":"10.1002\/rob.22338"},{"key":"2423_CR30","doi-asserted-by":"publisher","unstructured":"Hou, J., Wang, K., Chai, H., Xu, W., Li, Y., Zhang, G.: Safe reinforcement learning framework for high-obstacle climbing in heavy wheeled-legged robots. Control Engineering Practice 173, 106970 (2026). https:\/\/doi.org\/10.1016\/j.conengprac.2026.106970","DOI":"10.1016\/j.conengprac.2026.106970"},{"key":"2423_CR31","doi-asserted-by":"crossref","unstructured":"Pinto, L., Andrychowicz, M., Welinder, P., Zaremba, W., Abbeel, P.: Asymmetric actor critic for image-based robot learning (2017). arXiv:1710.06542","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"2423_CR32","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017). arXiv:1707.06347"},{"issue":"4","key":"2423_CR33","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1109\/MEX.1986.4307016","volume":"1","author":"MH Raibert","year":"1986","unstructured":"Raibert, M.H., Tello, E.R.: Legged robots that balance. IEEE Expert 1(4), 89\u201389 (1986). https:\/\/doi.org\/10.1109\/MEX.1986.4307016","journal-title":"IEEE Expert"},{"key":"2423_CR34","unstructured":"Makoviychuk, V., Wawrzyniak, L., Guo, Y., Lu, M., Storey, K., Macklin, M., Hoeller, D., Rudin, N., Allshire, A., Handa, A., et al.: Isaac gym: High performance gpu-based physics simulation for robot learning (2021). arXiv:2108.10470"},{"key":"2423_CR35","unstructured":"Rudin, N., Hoeller, D., Reist, P., Hutter, M.: Learning to walk in minutes using massively parallel deep reinforcement learning. In: Conference on Robot Learning, pp. 91\u2013100 (2022). PMLR"},{"issue":"2","key":"2423_CR36","doi-asserted-by":"publisher","first-page":"4630","DOI":"10.1109\/LRA.2022.3151396","volume":"7","author":"G Ji","year":"2022","unstructured":"Ji, G., Mun, J., Kim, H., Hwangbo, J.: Concurrent training of a control policy and a state estimator for dynamic and robust legged locomotion. IEEE Robot. Autom. Lett. 7(2), 4630\u20134637 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"4","key":"2423_CR37","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1177\/02783649231224053","volume":"43","author":"GB Margolis","year":"2024","unstructured":"Margolis, G.B., Yang, G., Paigwar, K., Chen, T., Agrawal, P.: Rapid locomotion via reinforcement learning. Int. J. Robot. Res. 43(4), 572\u2013587 (2024)","journal-title":"Int. J. Robot. Res."}],"container-title":["Journal of Intelligent &amp; Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-026-02423-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-026-02423-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-026-02423-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T01:18:58Z","timestamp":1790212738000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-026-02423-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":37,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2423"],"URL":"https:\/\/doi.org\/10.1007\/s10846-026-02423-8","relation":{},"ISSN":["1573-0409"],"issn-type":[{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,1]]},"assertion":[{"value":"24 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 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":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":4,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"92"}}