{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:39:43Z","timestamp":1766061583722,"version":"3.48.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246479","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"9800-9807","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions"],"prefix":"10.1109","author":[{"given":"Zhuochen","family":"Miao","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Lv","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjie","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Jin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref3"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.096"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"journal-title":"One-Shot Imitation Learning","year":"2017","author":"Duan","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611615"},{"article-title":"AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons","year":"2025","author":"Fang","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128681"},{"key":"ref13","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Conference on Robot Learning","author":"Florence"},{"key":"ref14","first-page":"3949","article-title":"Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation","volume-title":"Conference on Robot Learning, CoRL 2023","volume":"229","author":"Gervet"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4484"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127562"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.120"},{"article-title":"OpenVLA: An Open-Source Vision-Language-Action Model","year":"2024","author":"Jin Kim","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128755"},{"article-title":"Data scaling laws in imitation learning for robotic manipulation","year":"2024","author":"Lin","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610356"},{"article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","year":"2024","author":"Liu","key":"ref24"},{"article-title":"What matters in learning from offline human demonstrations for robot manipulation","year":"2021","author":"Mandlekar","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.090"},{"journal-title":"DINOv2: Learning Robust Visual Features without Supervision","year":"2023","author":"Oquab","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128322"},{"key":"ref30","first-page":"305","article-title":"ALVINN: An Autonomous Land Vehicle in a Neural Network","volume-title":"Advances in Neural Information Processing Systems 1, [NIPS Conference, Denver, Colorado, USA, 1988]","author":"Pomerleau"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610131"},{"key":"ref32","first-page":"22955","article-title":"Behavior transformers: Cloning k modes with one stone","volume":"35","author":"Muhammad Shafiullah","year":"2022","journal-title":"Advances in neural information processing systems"},{"journal-title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","year":"2022","author":"Shridhar","key":"ref33"},{"article-title":"Denoising Diffusion Implicit Models","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event","author":"Song","key":"ref34"},{"article-title":"Emergent Correspondence from Image Diffusion","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Tang","key":"ref35"},{"journal-title":"Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects","year":"2018","author":"Tremblay","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981838"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"article-title":"One-shot imitation learning: A pose estimation perspective","year":"2023","author":"Vitiello","key":"ref39"},{"key":"ref40","first-page":"3194","article-title":"Few-Shot In-Context Imitation Learning via Implicit Graph Alignment","volume-title":"Conference on Robot Learning","volume":"229","author":"Vosylius"},{"article-title":"Instant Policy: InContext Imitation Learning via Graph Diffusion","year":"2024","author":"Vosylius","key":"ref41"},{"key":"ref42","first-page":"1723","article-title":"BridgeData V2: A Dataset for Robot Learning at Scale","volume-title":"Conference on Robot Learning, CoRL 2023","volume":"229","author":"Rich Walke"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801678"},{"article-title":"Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers","year":"2024","author":"Wang","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127739"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"article-title":"SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Zhang","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref51","first-page":"2165","article-title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","volume-title":"Conference on Robot Learning, CoRL 2023","volume":"229","author":"Zitkovich"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246479.pdf?arnumber=11246479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:34:45Z","timestamp":1766061285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246479","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}