{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:30:33Z","timestamp":1766068233530,"version":"3.44.0"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127562","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"4853-4860","source":"Crossref","is-referenced-by-count":2,"title":["SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation"],"prefix":"10.1109","author":[{"given":"Cheng-Chun","family":"Hsu","sequence":"first","affiliation":[{"name":"NVIDIA."}]},{"given":"Bowen","family":"Wen","sequence":"additional","affiliation":[{"name":"NVIDIA."}]},{"given":"Jie","family":"Xu","sequence":"additional","affiliation":[{"name":"NVIDIA."}]},{"given":"Yashraj","family":"Narang","sequence":"additional","affiliation":[{"name":"NVIDIA."}]},{"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA."}]},{"given":"Yuke","family":"Zhu","sequence":"additional","affiliation":[{"name":"NVIDIA."}]},{"given":"Joydeep","family":"Biswas","sequence":"additional","affiliation":[{"name":"NVIDIA."}]},{"given":"Stan","family":"Birchfield","sequence":"additional","affiliation":[{"name":"NVIDIA."}]}],"member":"263","reference":[{"key":"ref1","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref4","article-title":"Video pretraining (VPT): Learning to act by watching unlabeled online videos","volume":"35","author":"Baker","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/978-3-031-73116-7_18"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/cvpr52733.2024.01599"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.15607\/RSS.2023.XIX.026"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICRA.2018.8461196"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICRA57147.2024.10610923"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.15607\/rss.2024.xx.096"},{"key":"ref11","article-title":"Learning universal policies via text-guided video generation","volume":"36","author":"Du","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Mobile ALOHA: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Fu","year":"2024","journal-title":"CoRL"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/LRA.2021.3062315"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.055","article-title":"RVT2: Learning precise manipulation from few demonstrations","author":"Goyal","year":"2024","journal-title":"RSS"},{"key":"ref15","article-title":"RVT: Robotic view transformer for 3d object manipulation","volume-title":"Conference on Robot Learning, PMLR","author":"Goyal","year":"2023"},{"key":"ref16","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"ReKep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref19","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning, PMLR","author":"Jang","year":"2022"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.15607\/RSS.2024.XX.046"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/978-3-031-73033-7_2"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICRA46639.2022.9811570"},{"key":"ref23","article-title":"3D diffuser actor: Policy diffusion with 3D scene representations","volume-title":"Conference on Robot Learning, PMLR","author":"Ke","year":"2024"},{"key":"ref24","article-title":"Learning to act from actionless videos through dense correspondences","author":"Ko","year":"2024","journal-title":"ICLR"},{"key":"ref25","article-title":"Learning plannable representations with causal InfoGAN","volume":"31","author":"Kurutach","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"FlowRetrieval: Flow-guided data retrieval for few-shot imitation learning","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR52733.2024.02636"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1007\/978-3-030-95459-8_9"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/CDC.1988.194354"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/LRA.2020.2965875"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/LRA.2022.3145961"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.15607\/RSS.2021.XVII.070"},{"key":"ref33","article-title":"R3M: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"CoRL"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.15607\/RSS.2022.XVIII.010"},{"key":"ref35","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref36","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/IROS.2013.6696520"},{"volume-title":"Equivariant descriptor fields: Se (3)-equivariant energy-based models for end-to-end visual robotic manipulation learning","author":"Ryu","key":"ref38"},{"key":"ref39","article-title":"ToolFlowNet: Robotic manipulation with tools via predicting tool flow from point clouds","volume-title":"Conference on Robot Learning, PMLR","author":"Seita","year":"2023"},{"key":"ref40","article-title":"Third-person visual imitation learning via decoupled hierarchical controller","volume":"32","author":"Sharma","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","article-title":"Perceiver-actor: A multitask transformer for robotic manipulation","volume-title":"Conference on Robot Learning, PMLR","author":"Shridhar","year":"2023"},{"key":"ref42","article-title":"Graph-structured visual imitation","volume-title":"Conference on Robot Learning, PMLR","author":"Sieb","year":"2020"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/ICRA46639.2022.9812146"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.15607\/RSS.2022.XVIII.023"},{"key":"ref45","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref46","article-title":"KITE: Keypoint-conditioned policies for semantic manipulation","volume-title":"Conference on Robot Learning, PMLR","author":"Sundaresan","year":"2023"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/ICRA48891.2023.10161569"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1109\/IROS47612.2022.9981982"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1109\/ICRA57147.2024.10611409"},{"key":"ref50","article-title":"One-shot imitation learning: A pose estimation perspective","volume-title":"Conference on Robot Learning, PMLR","author":"Vitiello","year":"2023"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1109\/ICRA.2019.8794224"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1109\/CVPR52733.2024.01956"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.15607\/RSS.2022.XVIII.044"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1109\/CVPR52733.2024.01692"},{"doi-asserted-by":"publisher","key":"ref55","DOI":"10.1109\/CVPR52729.2023.00066"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.15607\/RSS.2024.XX.092"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.1109\/ICRA48891.2023.10160217"},{"key":"ref58","article-title":"Flow as the cross-domain manipulation interface","volume-title":"Conference on Robot Learning, PMLR","author":"Xu","year":"2024"},{"key":"ref59","article-title":"DNAct: Diffusion guided multitask 3d policy learning","author":"Yan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"General flow as foundation affordance for scalable robot learning","author":"Yuan","year":"2024","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref62","article-title":"FlowBot++: Learning generalized articulated objects manipulation via articulation projection","author":"Zhang","year":"2023","journal-title":"CoRL"},{"volume-title":"Learning generalizable manipulation policies with object-centric 3D representations","year":"2023","author":"Zhu","key":"ref63"},{"key":"ref64","article-title":"VIOLA: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"Conference on Robot Learning, PMLR","author":"Zhu","year":"2023"},{"key":"ref65","article-title":"Vision-based manipulation from single human video with open-world object graphs","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127562.pdf?arnumber=11127562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:46:05Z","timestamp":1756881965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127562","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}