{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T20:21:23Z","timestamp":1783369283740,"version":"3.54.6"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2057"],"award-info":[{"award-number":["U22A2057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014103","name":"Key Technology Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["2025CXGC010210"],"award-info":[{"award-number":["2025CXGC010210"]}],"id":[{"id":"10.13039\/100014103","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"Municipal-University Collaborative Development Project of Jinan","doi-asserted-by":"publisher","award":["JNSX2025002"],"award-info":[{"award-number":["JNSX2025002"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3706100","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T19:59:21Z","timestamp":1782158361000},"page":"11868-11880","source":"Crossref","is-referenced-by-count":0,"title":["MoTL: Modality-Balanced Terrain-Aware Locomotion Learning for Quadruped Robots"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9930-5845","authenticated-orcid":false,"given":"Xing","family":"Fang","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5288-4325","authenticated-orcid":false,"given":"Zhiheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4197-142X","authenticated-orcid":false,"given":"Wenhao","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7313-9172","authenticated-orcid":false,"given":"Mingxing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1344-4415","authenticated-orcid":false,"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-3190","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Proc. CoRL","volume":"205","author":"Agarwal"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref3","article-title":"BEIT: BERT pre-training of image transformers","volume-title":"Proc. ICLR","author":"Bao"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2384"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2801794"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3449959"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2605068"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801962"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342108"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2849506"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982190"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.054"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01676"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3172469"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3186804"},{"key":"ref17","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2887342"},{"key":"ref20","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NeurIPS","volume":"34","author":"Li"},{"key":"ref21","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref22","article-title":"Multimodal alignment and fusion: A survey","author":"Li","year":"2024","journal-title":"arXiv:2411.17040"},{"key":"ref23","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. NeurIPS","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2614923"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-025-10202-x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974973.69"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202315"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref31","first-page":"3454","article-title":"TOP-nav: Legged navigation integrating terrain, obstacle and proprioception estimation","volume-title":"Proc. CoRL","volume":"270","author":"Ren"},{"key":"ref32","volume-title":"Aliengo","year":"2019"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3177289"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548208"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141662"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3310945"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref42","article-title":"ONE-PEACE: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023","journal-title":"arXiv:2305.11172"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2189550"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3230325"},{"key":"ref46","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680626"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11574695.pdf?arnumber=11574695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T19:57:41Z","timestamp":1783367861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11574695\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3706100","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}