{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:30:58Z","timestamp":1759365058029,"version":"build-2065373602"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Japan Science and Technology Agency (JST) Moonshot Research and Development Grant through the Development of Semi-Autonomous CA","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3611812","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T17:47:17Z","timestamp":1758217637000},"page":"167034-167044","source":"Crossref","is-referenced-by-count":0,"title":["Action-Inclusive Multi-Future Prediction Using a Generative Model in Human-Related Scenes for Mobile Robots"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9778-7853","authenticated-orcid":false,"given":"Chenfei","family":"Xu","sequence":"first","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8865-955X","authenticated-orcid":false,"given":"Huthaifa","family":"Ahmad","sequence":"additional","affiliation":[{"name":"RIKEN Information Research and Development and Strategy Headquarters, RIKEN, Kyoto, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2961-8417","authenticated-orcid":false,"given":"Yuya","family":"Okadome","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Technology, Tokyo University of Science, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0805-7648","authenticated-orcid":false,"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6307-5104","authenticated-orcid":false,"given":"Yutaka","family":"Nakamura","sequence":"additional","affiliation":[{"name":"RIKEN Information Research and Development and Strategy Headquarters, RIKEN, Kyoto, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MMAR49549.2021.9528442"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-023-00817-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.10.472"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.20965\/jrm.2022.p0654"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6694084"},{"key":"ref6","first-page":"2455","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Ha"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-08744-2"},{"key":"ref8","first-page":"52310","article-title":"Generative world explorer","volume-title":"Proc. 13th Int. Conf. Learn. Represent. (ICLR)","volume":"2025","author":"Lu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01472"},{"key":"ref10","first-page":"45210","article-title":"Learning interactive real-world simulators","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","volume":"2024","author":"Yang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref12","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref14","first-page":"19259","article-title":"VDT: General-purpose video diffusion transformers via mask modeling","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","volume":"2024","author":"Lu"},{"key":"ref15","first-page":"4383","article-title":"Understanding and improving layer normalization","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107631"},{"key":"ref19","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","author":"Vuong","year":"2023","journal-title":"arXiv:2310.08864"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/s21248229"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636613"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611090"},{"key":"ref23","first-page":"119411","article-title":"Human-aware vision-and-language navigation: Bridging simulation to reality with dynamic human interactions","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"37","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2925731"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3329626"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342447"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01842"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/app14010089"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref30","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref31","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref32","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAE59995.2024.10569186"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/c2012-0-06836-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2012.6385773"},{"key":"ref37","first-page":"3308","article-title":"VEEGAN: Reducing mode collapse in GANs using implicit variational learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Srivastava"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11170425.pdf?arnumber=11170425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:13:51Z","timestamp":1759295631000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11170425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3611812","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}