{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T17:39:06Z","timestamp":1770140346916,"version":"3.49.0"},"reference-count":70,"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"}],"funder":[{"DOI":"10.13039\/501100004147","name":"Tsinghua University, BIGAI","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128658","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"3095-3102","source":"Crossref","is-referenced-by-count":1,"title":["SYNERGAI: Perception Alignment for Human-Robot Collaboration"],"prefix":"10.1109","author":[{"given":"Yixin","family":"Chen","sequence":"first","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]},{"given":"I Guoxi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]},{"given":"Yaowei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]},{"given":"Hongming","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]},{"given":"Peiyuan","family":"Zhi","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]},{"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pddl planning with pretrained large language models","author":"Silver","year":"2022","journal-title":"NeurIPS 2022 foundation models for decision making workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00280"},{"key":"ref3","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning (CoRL)","author":"Brohan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10133-5"},{"key":"ref5","article-title":"Reflect: Summarizing robot experiences for failure explanation and correction","volume-title":"Conference on Robot Learning (CoRL)","author":"Liu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00874"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211056674"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/001401300409044"},{"key":"ref12","volume-title":"The alignment problem: How can machines learn human values?","author":"Christian","year":"2021"},{"key":"ref13","article-title":"Ai alignment: A comprehensive survey","author":"Ji","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","author":"Casper","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref15","article-title":"Deep reinforcement learning from human preferences","author":"Christiano","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref16","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref17","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref18","article-title":"Aligner: Achieving efficient alignment through weak-to-strong correction","author":"Ji","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2014.x.024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1063"},{"key":"ref21","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning (CoRL)","author":"Thomason"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193254"},{"key":"ref24","article-title":"Robots that ask for help: Uncertainty alignment for large language model planners","volume-title":"Conference on Robot Learning (CoRL)","author":"Ren"},{"key":"ref25","article-title":"Webshop: Towards scalable real-world web interaction with grounded language agents","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Yao","year":"2022"},{"key":"ref26","article-title":"Mind2web: Towards a generalist agent for the web","author":"Deng","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref27","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Llm+ p: Empowering large language models with optimal planning proficiency","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Conference on Robot Learning (CoRL)","author":"Huang"},{"key":"ref30","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"NeurIPS 2023 Foundation Models for Decision Making Workshop"},{"key":"ref31","article-title":"Describe, explain, plan and select: interactive planning with llms enables open-world multi-task agents","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref32","article-title":"Closed-loop open-vocabulary mobile manipulation with gpt-4v","author":"Zhi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref34","article-title":"Semantic exploration from language abstractions and pretrained representations","author":"Tam","year":"2022","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref35","article-title":"Reward design with language models","author":"Kwon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Guiding pretraining in reinforcement learning with large language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Du"},{"key":"ref37","article-title":"Language instructed reinforcement learning for human-ai coordination","volume-title":"International Conference on Machine Learning (ICML)","author":"Hu"},{"key":"ref38","article-title":"Grounded decoding: Guiding text generation with grounded models for robot control","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Palm-e: An embodied multimodallanguage model","volume-title":"International Conference on Machine Learning (ICML)","author":"Driess"},{"key":"ref40","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref41","article-title":"Gpt-4 technical report","author":"OpenAI","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_11"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref47","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ma"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref49","article-title":"Sqa3d: Situated question answering in 3d scenes","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ma"},{"key":"ref50","article-title":"3d-11m: Injecting the 3d world into large language models","author":"Hong","year":"2023","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref51","article-title":"Chat-3d: Data-efficiently tuning large language model for universal dialogue of 3d scenes","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"An embodied generalist agent in 3d world","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW63481.2024.10645462"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37422"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref56","article-title":"Monosdf: Exploring monocular geometric cues for neural implicit surface re-construction","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref57","article-title":"Phyrecon: Physically plausible neural scene reconstruction","author":"Ni","year":"2024","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560736"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"ref62","article-title":"Taskography: Evaluating robot task planning over large 3d scene graphs","volume-title":"Conference on Robot Learning (CoRL)","author":"Agia"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812179"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref65","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139108669"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1086\/593015"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00142"},{"key":"ref69","volume-title":"Langchain","author":"Chase","year":"2022"},{"key":"ref70","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"}],"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\/11128658.pdf?arnumber=11128658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:13:31Z","timestamp":1756880011000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128658","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}