{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:43:25Z","timestamp":1775144605064,"version":"3.50.1"},"reference-count":49,"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\/icra55743.2025.11127231","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"12834-12841","source":"Crossref","is-referenced-by-count":1,"title":["Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Manipulation"],"prefix":"10.1109","author":[{"given":"Hang","family":"Li","sequence":"first","affiliation":[{"name":"Technical University of Munich"}]},{"given":"Qian","family":"Feng","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}]},{"given":"Zhi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}]},{"given":"Jianxiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}]},{"given":"Zhaopeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Agile Robots SE"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Rt2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proceedings of International Conference on Computer Vision","author":"Brohan","year":"2023"},{"key":"ref2","article-title":"Openvla: An open-source vision-language-action model","volume-title":"Proceedings of Conference on Robot Learning(CoRL)","author":"Kim","year":"2024"},{"key":"ref3","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Janner","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01712"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.028"},{"key":"ref6","article-title":"Imitating human behaviour with diffusion models","volume-title":"Proceedings of ICLR","author":"Pearce","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2020.2974707"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8794435"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1109\/ICRA46639.2022.9811666","article-title":"Ffhnet: Generating multi-fingered robotic grasps for unknown objects in real-time","volume-title":"2022 International Conference on Robotics and Automation (ICRA)","author":"Mayer","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769601"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769950"},{"key":"ref17","article-title":"Learning generalizable manipulation policies with object-centric 3d representations","volume-title":"Proceedings of Conference on Robot Learning (CoRL)","author":"Zhu","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160895"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9812379"},{"key":"ref21","article-title":"Is conditional generative modeling all you need for decisionmaking?","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Ajay","year":"2023"},{"key":"ref22","article-title":"Adaptdiffuser: Diffusion models as adaptive self-evolving planners","volume-title":"Proceedings of International Conference on Machine Learning(ICML)","author":"Liang","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3492118"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3498776"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161569"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342382"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610519"},{"key":"ref28","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","volume":"abs\/1809.10790","author":"Tremblay","year":"2018","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981838"},{"key":"ref30","article-title":"Object-centric task and motion planning in dynamic environments","volume":"abs\/1911.04679","author":"Migimatsu","year":"2019","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8794224"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8461196"},{"key":"ref33","article-title":"Segmenting unknown 3d objects from real depth images using mask R-CNN trained on synthetic point clouds","volume":"abs\/1809.05825","author":"Danielczuk","year":"2018","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref36","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","volume-title":"Proceedings of Conference on Robot Learning(CoRL)","author":"Huang","year":"2023"},{"key":"ref37","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Proceedings of Conference on Robot Learning(CoRL)","author":"Ahn","year":"2022"},{"key":"ref38","article-title":"Language to rewards for robotic skill synthesis","volume-title":"Proceedings of Conference on Robot Learning(CoRL)","author":"Yu","year":"2023"},{"key":"ref39","article-title":"Text2reward: Reward shaping with language models for reinforcement learning","volume-title":"Proceedings of International Conference on Learning Representations(ICLR)","author":"Xie","year":"2024"},{"key":"ref40","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proceedings of International Conference on Learning Representations(ICLR)","author":"Ma","year":"2024"},{"key":"ref41","article-title":"Simple open-vocabulary object detection with vision transformers","volume-title":"Proceedings of European Conference on Computer Vision (ECCV)","author":"Minderer","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01599"},{"key":"ref43","article-title":"Open-world object manipulation using pre-trained visionlanguage models","volume-title":"Proceedings of Conference on Robot Learning(CoRL)","author":"Stone","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref46","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of NeurIPS","author":"Ho","year":"2020"},{"key":"ref47","article-title":"Denoising diffusion implicit models","volume-title":"Proceedings of ICLR","author":"Song","year":"2021"},{"key":"ref48","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of Computer Vision and Pattern Recognition Conference (CVPR)","author":"Qi","year":"2017"},{"key":"ref49","volume-title":"Gpt-4 technical report","author":"Achiam","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"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\/11127231.pdf?arnumber=11127231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:16:29Z","timestamp":1756880189000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127231","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}