{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T18:38:01Z","timestamp":1772476681615,"version":"3.50.1"},"reference-count":38,"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\/icra55743.2025.11127842","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"11972-11978","source":"Crossref","is-referenced-by-count":1,"title":["LEMMo-Plan: LLM-Enhanced Learning from Multi-Modal Demonstration for Planning Sequential Contact-Rich Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"Kejia","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}]},{"given":"Zheng","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}]},{"given":"Lingyun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}]},{"given":"Fan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}]},{"given":"Zhenshan","family":"Bing","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}]},{"given":"Sami","family":"Haddadin","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Germany"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2024","journal-title":"Gpt-4 technical report"},{"key":"ref2","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":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-00983-2"},{"key":"ref5","article-title":"Understanding the planning of llm agents: A survey","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Palm-e: an embodied multimodal language model","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Driess","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref9","article-title":"Translating natural language to planning goals with large-language models","author":"Xie","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610065"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3477090"},{"key":"ref12","first-page":"201","article-title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","volume-title":"Proceedings of The 7th Conference on Robot Learning","author":"Wang"},{"key":"ref13","article-title":"Evaluating uncertainty-based failure detection for closed-loop llm planners","volume-title":"IEEE 2024 International Conference on Robotics and Automation (ICRA)","author":"Zheng","year":"2024"},{"key":"ref14","article-title":"Generalizable long-horizon manipulations with large language models","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.30006"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610183"},{"key":"ref17","article-title":"Behavior tree generation using large language models for sequential manipulation planning with human instructions and feedback","author":"Ao","year":"2024","journal-title":"ICRA 2024 Workshop Exploring Role Allocation in Human-Robot Co-Manipulation"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611369"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911428653"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5772\/5611"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943187"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911426178"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146589"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref26","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"Gupta","year":"2019","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3466076"},{"key":"ref29","article-title":"Human demonstrations are generalizable knowledge for robots","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801525"},{"key":"ref31","article-title":"A touch, vision, and language dataset for multimodal alignment","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"6912","article-title":"Hearing touch: Audio-visual pretraining for contact-rich manipulation","volume-title":"f2024 IEEE International Conference on Robotics and Automation (ICRA)","author":"Mejia"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793542"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094433"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/s17122762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341726"},{"key":"ref38","first-page":"arXiv","article-title":"Bridging language and action: A survey of language-conditioned robot manipulation","author":"Zhou","year":"2023","journal-title":"arXiv e-prints"}],"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\/11127842.pdf?arnumber=11127842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:06:07Z","timestamp":1756879567000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127842","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}