{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:11Z","timestamp":1757608691825,"version":"3.44.0"},"reference-count":47,"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\/icra55743.2025.11127480","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"13722-13729","source":"Crossref","is-referenced-by-count":0,"title":["Closed Loop Interactive Embodied Reasoning for Robot Manipulation"],"prefix":"10.1109","author":[{"given":"Michal","family":"Nazarczuk","sequence":"first","affiliation":[{"name":"Huawei Noah&#x0027;s Ark London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan Kristof","family":"Behrens","sequence":"additional","affiliation":[{"name":"Czech Technical University in Prague"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karla","family":"Stepanova","sequence":"additional","affiliation":[{"name":"Czech Technical University in Prague"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matej","family":"Hoffmann","sequence":"additional","affiliation":[{"name":"Czech Technical University in Prague"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krystian","family":"Mikolajczyk","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00750"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref3","article-title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196681"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561212"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.055"},{"key":"ref8","article-title":"Robotic control via embodied chain-of-thought reasoning","author":"Michal","year":"2024","journal-title":"arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802249"},{"key":"ref10","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning","author":"Huang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref12","article-title":"Openvla: An open-source vision-language-action model","volume-title":"Conference on Robot Learning","author":"Kim","year":"2024"},{"key":"ref13","article-title":"ReAct: Synergizing reasoning and acting in language models","volume-title":"International Conference on Learning Representations","author":"Yao","year":"2023"},{"key":"ref14","article-title":"MuBlE: MuJoCo and Blender simulation Environment for task planning in Robotics Manipulation","author":"Nazarczuk","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(72)90051-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref17","article-title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","volume-title":"Conference on Neural Information Processing Systems","author":"Yi","year":"2018"},{"key":"ref18","article-title":"The NeuroSymbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","volume-title":"International Conference on Learning Representations","author":"Mao","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_44"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1129"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980391"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965875"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487165"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919848837"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594027"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.003"},{"key":"ref29","article-title":"Regression Planning Networks","volume-title":"Conference on Neural Information Processing Systems","author":"Xu","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561548"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref33","first-page":"1084","article-title":"Grounding complex natural language commands for temporal tasks in unseen environments","volume-title":"Conference on Robot Learning","author":"Liu","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341577"},{"key":"ref35","article-title":"Palm-e: An embodied multimodal language model","volume-title":"International Conference on Machine Learning","author":"Driess","year":"2023"},{"key":"ref36","article-title":"Gr-2: A generative video-languageaction model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"\\pi0: A vision-language-action flow model for general robot control","author":"Black","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197332"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_34"},{"key":"ref42","article-title":"Sequence to Sequence Learning with Neural Networks","volume-title":"Conference on Neural Information Processing Systems","author":"Sutskever","year":"2014"},{"key":"ref43","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020","journal-title":"arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"volume-title":"CLIER - Closed Loop Interactive Embodied Reasoning","year":"2025","author":"Nazarczuk","key":"ref45"},{"article-title":"Franka emika robot\u2019s instruction handbook","volume-title":"Franka Emika GmbH","year":"2021","key":"ref46"},{"volume-title":"iMatix","key":"ref47","article-title":"Zero-mq"}],"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\/11127480.pdf?arnumber=11127480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:12:12Z","timestamp":1756879932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127480","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}