{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:13:04Z","timestamp":1771330384415,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"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":[[2024,12,10]]},"DOI":"10.1109\/robio64047.2024.10907585","type":"proceedings-article","created":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T13:33:40Z","timestamp":1741354420000},"page":"913-918","source":"Crossref","is-referenced-by-count":1,"title":["Instruction-Following Long-Horizon Manipulation by LLM-Empowered Symbolic Planner"],"prefix":"10.1109","author":[{"given":"Zhihao","family":"Li","sequence":"first","affiliation":[{"name":"T-Stone Robotics Institute, The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjia","family":"Liu","sequence":"additional","affiliation":[{"name":"T-Stone Robotics Institute, The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Li","sequence":"additional","affiliation":[{"name":"T-Stone Robotics Institute, The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghao","family":"Yu","sequence":"additional","affiliation":[{"name":"T-Stone Robotics Institute, The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Teng","sequence":"additional","affiliation":[{"name":"T-Stone Robotics Institute, The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunbo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computing Technologies Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miao","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Technological Sciences, Wuhan University,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tin Lun","family":"Lam","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Chen","sequence":"additional","affiliation":[{"name":"T-Stone Robotics Institute, The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811911"},{"key":"ref2","first-page":"651","volume-title":"Scalable deep reinforcement learning for vision-based robotic manipulation [c] conference on robot learning","author":"Kalashnikov","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551399"},{"key":"ref6","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"20","article-title":"Chatgpt for robotics: Design principles and model abilities[j]. microsoft auton","volume":"2","author":"Vemprala","year":"2023","journal-title":"Syst. Robot. Res"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342169"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1129"},{"key":"ref10","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Conference on Robot Learning","author":"Huang","year":"2023"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"118132","DOI":"10.1016\/j.eswa.2022.118132","article-title":"A robust context attention network for human hand detection","volume":"208","author":"Xie","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803267"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506611"},{"key":"ref14","first-page":"22160","article-title":"D13dv-10k: A large-scale scene dataset for deep learning-based 3d vision","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ling","year":"2024"},{"key":"ref15","article-title":"The learnability of in-context learning","volume":"36","author":"Wies","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Doremi: Grounding language model by detecting and recovering from plan-execution misalignment","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.30006"},{"key":"ref19","article-title":"Glm-130b: An open bilingual pre-trained model","author":"Zeng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","author":"Liu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"9118","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"}],"event":{"name":"2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Bangkok, Thailand","start":{"date-parts":[[2024,12,10]]},"end":{"date-parts":[[2024,12,14]]}},"container-title":["2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10906779\/10907273\/10907585.pdf?arnumber=10907585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:36:33Z","timestamp":1755545793000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10907585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/robio64047.2024.10907585","relation":{},"subject":[],"published":{"date-parts":[[2024,12,10]]}}}