{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:50:22Z","timestamp":1777657822982,"version":"3.51.4"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing Innovation Center of Humanoid Robotics, China"},{"name":"Shichao Fan’s internship"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302031"],"award-info":[{"award-number":["62302031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LQ23F020024"],"award-info":[{"award-number":["LQ23F020024"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/lra.2025.3619794","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:55:27Z","timestamp":1760032527000},"page":"12788-12795","source":"Crossref","is-referenced-by-count":2,"title":["Diffusion Trajectory-Guided Policy for Long-Horizon Robot Manipulation"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6835-2466","authenticated-orcid":false,"given":"Shichao","family":"Fan","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering and Automation, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5655-0990","authenticated-orcid":false,"given":"Quantao","family":"Yang","sequence":"additional","affiliation":[{"name":"Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"given":"Yajie","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2095-2140","authenticated-orcid":false,"given":"Kun","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Innovation Center of Humanoid Robotics, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6818-1125","authenticated-orcid":false,"given":"Zhengping","family":"Che","sequence":"additional","affiliation":[{"name":"Beijing Innovation Center of Humanoid Robotics, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5181-6451","authenticated-orcid":false,"given":"Qingjie","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"given":"Min","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1199","article-title":"VIOLA: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"Proc. Conf. Robot Learn.","author":"Zhu","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3443610"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref6","article-title":"A survey on vision-language-action models for embodied AI","author":"Ma","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","article-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models","volume-title":"Proc. NeurIPS 2023 Found. Models Decis. Mak. Workshop","author":"Black"},{"key":"ref9","first-page":"1","article-title":"Video language planning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Du"},{"key":"ref10","first-page":"9156","article-title":"Learning universal policies via text-guided video generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Du","year":"2024"},{"key":"ref11","article-title":"RT-trajectory: Robotic task generalization via hindsight trajectory sketches","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.049"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref14","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref15","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref16","article-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2024","journal-title":"Proc. 12th Int. Conf. Learn. Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref18","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proc. Robot.: Sci. Syst.","author":"Team","year":"2024"},{"key":"ref19","first-page":"68760","article-title":"Video prediction models as rewards for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Escontrela","year":"2024"},{"key":"ref20","article-title":"MimicPlay: Long-horizon imitation learning by watching human play","volume-title":"Proc. Conf. Robot Learn.","author":"Wang","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127630"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.092"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128834"},{"key":"ref24","article-title":"Flow as the cross-domain manipulation interface","volume-title":"Proc. Conf. Robot Learn.","author":"Xu","year":"2024"},{"key":"ref25","article-title":"FreqPolicy: Efficient flow-based visuomotor policy via frequency consistency","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Su","year":"2025"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref28","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle","year":"2021"},{"key":"ref29","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023"},{"key":"ref30","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2020","author":"Ho"},{"key":"ref31","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611293"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref34","article-title":"Vision-language foundation models as effective robot imitators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2024"},{"key":"ref35","article-title":"3D diffuser actor: Policy diffusion with 3D scene representations","volume-title":"Proc. Conf. Robot Learn.","author":"Ke"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801581"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4484"},{"key":"ref40","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","author":"Padalkar","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127989"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11215960\/11197656.pdf?arnumber=11197656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:02:00Z","timestamp":1764010920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11197656\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":41,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3619794","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}