{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T19:25:35Z","timestamp":1791401135071,"version":"4.3.3"},"reference-count":225,"publisher":"Informa UK Limited","issue":"18","license":[{"start":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T00:00:00Z","timestamp":1726444800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2024,9,16]]},"DOI":"10.1080\/01691864.2024.2408593","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T13:32:37Z","timestamp":1729085557000},"page":"1232-1254","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":83,"title":["Real-world robot applications of foundation models: a review"],"prefix":"10.1080","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7464-7187","authenticated-orcid":false,"given":"Kento","family":"Kawaharazuka","sequence":"first","affiliation":[{"name":"Department of Mechano-Informatics, The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1537-7770","authenticated-orcid":false,"given":"Tatsuya","family":"Matsushima","sequence":"additional","affiliation":[{"name":"School of Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Gambardella","sequence":"additional","affiliation":[{"name":"School of Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxian","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Paxton","sequence":"additional","affiliation":[{"name":"Meta AI Research, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andy","family":"Zeng","sequence":"additional","affiliation":[{"name":"Google DeepMind, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,10,16]]},"reference":[{"key":"e_1_3_2_2_1","unstructured":"Open X-Embodiment Collaboration Padalkar A Pooley A Jain A et\u00a0al. Open X-Embodiment: robotic learning datasets and RT-X models. arXiv preprint arXiv:2310.08864 2023."},{"key":"e_1_3_2_3_1","unstructured":"Brohan A Brown N Carbajal J et\u00a0al. RT-2: vision-language-action models transfer web knowledge to robotic control. In: Proceedings of The 7th Conference on Robot Learning. 2023. p. 2165\u20132183."},{"key":"e_1_3_2_4_1","unstructured":"Nair S Rajeswaran A Kumar V et\u00a0al. R3M: a universal visual representation for robot manipulation. In: 6th Annual Conference on Robot Learning. 2022. Available from: https:\/\/openreview.net\/forum?id=tGbpgz6yOrI."},{"key":"e_1_3_2_5_1","unstructured":"Ahn M Brohan A Brown N et\u00a0al. Do as i can not as i say: grounding language in robotic affordances. In: Proceedings of The 6th Conference on Robot Learning. PMLR; 2022. p. 287\u2013318."},{"key":"e_1_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Liang J Huang W Xia F et\u00a0al. Code as policies: language model programs for embodied control. In: IEEE International Conference on Robotics and Automation. 2023.","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"e_1_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Goel R Gupta P. Robotics and industry 4.0. In: A roadmap to industry 4.0: smart production sharp business and sustainable development. 2020. p. 157\u2013169.","DOI":"10.1007\/978-3-030-14544-6_9"},{"key":"e_1_3_2_8_1","doi-asserted-by":"crossref","unstructured":"H\u00e4gele M Nilsson K Pires JN et\u00a0al. Industrial robotics. In: Springer handbook of robotics. 2016. p. 1385\u20131422.","DOI":"10.1007\/978-3-319-32552-1_54"},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006585732197"},{"key":"e_1_3_2_10_1","volume-title":"Robotics for engineers","author":"Koren Y","year":"1985","unstructured":"Koren Y, Koren Y. Robotics for engineers. Vol. 168, McGraw-Hill New York; 1985."},{"key":"e_1_3_2_11_1","unstructured":"De Backer K DeStefano T Menon C et\u00a0al. Industrial robotics and the global organisation of production. In: OECD. 2018. Available from: https:\/\/www.oecd-ilibrary.org\/content\/paper\/dd98ff58-en."},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105216"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0107-58"},{"key":"e_1_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Kidd CD Breazeal C. Robots at home: understanding long-term human-robot interaction. In: 2008 IEEE\/RSJ International Conference on Intelligent Robots and Systems. 2008. p. 3230\u20133235.","DOI":"10.1109\/IROS.2008.4651113"},{"key":"e_1_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Murphy RR Tadokoro S Kleiner A. Disaster robotics. In: Springer handbook of robotics. 2016. p. 1577\u20131604.","DOI":"10.1007\/978-3-319-32552-1_60"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15327051hci1901&2_5"},{"key":"e_1_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Abdo N Stachniss C Spinello L et\u00a0al. Robot organize my shelves! tidying up objects by predicting user preferences. In: 2015 IEEE International Conference on Robotics and Automation (ICRA). 2015. p. 1557\u20131564.","DOI":"10.1109\/ICRA.2015.7139396"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2022.2114297"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"e_1_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Marchetti E Grimme S Hornecker E et\u00a0al. Pet-robot or appliance? Care home residents with dementia respond to a zoomorphic floor washing robot. In: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems. 2022. p. 1\u201321.","DOI":"10.1145\/3491102.3517463"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.07.024"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.018"},{"key":"e_1_3_2_23_1","unstructured":"Thosar M Zug S Skaria AM et\u00a0al. A review of knowledge bases for service robots in household environments. In: AIC. 2018. p. 98\u2013110."},{"key":"e_1_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Bollini M Tellex S Thompson T et\u00a0al. Interpreting and executing recipes with a cooking robot. In: Experimental Robotics: The 13th International Symposium on Experimental Robotics. 2013. p. 481\u2013495.","DOI":"10.1007\/978-3-319-00065-7_33"},{"key":"e_1_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Sugiura Y Sakamoto D Withana A et\u00a0al. Cooking with robots: designing a household system working in open environments. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2010. p. 2427\u20132430.","DOI":"10.1145\/1753326.1753693"},{"key":"e_1_3_2_26_1","unstructured":"Bommasani R Hudson DA Adeli E et\u00a0al. On the opportunities and risks of foundation models. arXiv preprint 2021."},{"key":"e_1_3_2_27_1","unstructured":"Dong Q Li L Dai D et\u00a0al. A survey for in-context learning. arXiv preprint arXiv:2301.00234 2022."},{"key":"e_1_3_2_28_1","unstructured":"OpenAI. GPT-4 technical report. Technical report 2023."},{"key":"e_1_3_2_29_1","unstructured":"Radford A Kim JW Hallacy C et\u00a0al. Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR; 2021. p. 8748\u20138763."},{"key":"e_1_3_2_30_1","unstructured":"Wang J Wu Z Li Y et\u00a0al. Large language models for robotics: opportunities challenges and perspectives. arXiv preprint 2024."},{"key":"e_1_3_2_31_1","unstructured":"Zeng F Gan W Wang Y et\u00a0al. Large language models for robotics: a survey. arXiv preprint 2023."},{"key":"e_1_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Firoozi R Tucker J Tian S et\u00a0al. Foundation models in robotics: applications challenges and the future. arXiv preprint 2023.","DOI":"10.1177\/02783649241281508"},{"key":"e_1_3_2_33_1","unstructured":"Hu Y Xie Q Jain V et\u00a0al. Toward general-purpose robots via foundation models: a survey and meta-analysis. arXiv preprint 2023."},{"key":"e_1_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3505243"},{"key":"e_1_3_2_35_1","unstructured":"Yuan L Chen D Chen Y-L et\u00a0al. Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 2021."},{"key":"e_1_3_2_36_1","unstructured":"Brown TB Mann B Ryder N et\u00a0al. Language models are few-shot learners. In: Advances in neural information processing systems 33. 2020. p. 1877\u20131901."},{"issue":"240","key":"e_1_3_2_37_1","first-page":"1","article-title":"PaLM: scaling language modeling with pathways","volume":"24","author":"Chowdhery A","year":"2023","unstructured":"Chowdhery A, Narang S, Devlin J, et\u00a0al. PaLM: scaling language modeling with pathways. J Mach Learn Res. 2023;24(240):1\u2013113.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_2_38_1","unstructured":"Zhang S Roller S Goyal N et\u00a0al. Opt: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 2022."},{"key":"e_1_3_2_39_1","unstructured":"Zeng A Liu X Du Z et\u00a0al. Glm-130b: an open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 2022."},{"key":"e_1_3_2_40_1","unstructured":"Le Scao T Fan A Akiki C et\u00a0al. Bloom: a 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 2022."},{"key":"e_1_3_2_41_1","unstructured":"Touvron H Martin L Stone K et\u00a0al. Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 2023."},{"key":"e_1_3_2_42_1","unstructured":"Anil R Dai AM Firat O et\u00a0al. Palm 2 technical report. arXiv preprint arXiv:2305.10403 2023."},{"key":"e_1_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.abe0874"},{"key":"e_1_3_2_44_1","doi-asserted-by":"crossref","unstructured":"Krizhevsky A Sutskever I Hinton GE. ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems Vol. 60. 2012.","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_45_1","unstructured":"Vaswani A Shazeer N Parmar N et\u00a0al. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017. p. 6000\u20136010."},{"key":"e_1_3_2_46_1","unstructured":"Devlin J Chang M-W Lee K et\u00a0al. BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT. 2019. p. 4171\u20134186."},{"key":"e_1_3_2_47_1","unstructured":"Dosovitskiy A Beyer L Kolesnikov A et\u00a0al. An image is worth 16\u00d716 words: transformers for image recognition at scale. In: International Conference on Learning Representations. 2021. Available from: https:\/\/openreview.net\/forum?id=YicbFdNTTy."},{"key":"e_1_3_2_48_1","unstructured":"Gwern. GPT-3 creative fiction 2021. Available from: https:\/\/www.gwern.net\/GPT-3."},{"key":"e_1_3_2_49_1","unstructured":"Chen M Tworek J Jun H et\u00a0al. Evaluating large language models trained on code. arXiv preprint 2021."},{"key":"e_1_3_2_50_1","unstructured":"Touvron H Lavril T Izacard G et\u00a0al. Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 2023."},{"key":"e_1_3_2_51_1","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima T","year":"2022","unstructured":"Kojima T, Gu SS, Reid M, et\u00a0al. Large language models are zero-shot reasoners. Adv Neural Inf Process Syst. 2022;35:22199\u201322213.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_52_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei J","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D, et\u00a0al. Chain-of-thought prompting elicits reasoning in large language models. Adv Neural Inf Process Syst. 2022;35:24824\u201324837.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_53_1","unstructured":"Liu Y Ott M Goyal N et\u00a0al. RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint 2019. ISSN 23318422."},{"key":"e_1_3_2_54_1","unstructured":"Majumdar A Yadav K Arnaud S et\u00a0al. Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence? In: Workshop on Reincarnating Reinforcement Learning at ICLR 2023. 2023. Available from: https:\/\/openreview.net\/forum?id=NJtSbIWmt2T."},{"key":"e_1_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Kirillov A Mintun E Ravi N et\u00a0al. Segment anything. arXiv preprint 2023.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_56_1","unstructured":"Yang J Gao M Li Z et\u00a0al. Track anything: segment anything meets videos. arXiv preprint 2023."},{"key":"e_1_3_2_57_1","unstructured":"Zhang C Han D Qiao Y et\u00a0al. Faster segment anything: towards lightweight SAM for mobile applications. arXiv preprint 2023."},{"key":"e_1_3_2_58_1","doi-asserted-by":"crossref","unstructured":"Li LH Zhang P Zhang H et\u00a0al. Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022. p. 10965\u201310975.","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"e_1_3_2_59_1","unstructured":"Li J Li D Savarese S et\u00a0al. Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 2023."},{"key":"e_1_3_2_60_1","unstructured":"Alayrac J-B Donahue J Luc P et\u00a0al. Flamingo: a visual language model for few-shot learning. In: Advances in neural information processing systems. 2022. p. 23716\u201323736."},{"key":"e_1_3_2_61_1","unstructured":"Wang P Yang A Men R et\u00a0al. OFA: unifying architectures tasks and modalities through a simple sequence-to-sequence learning framework. In: International Conference on Machine Learning. 2022. p. 23318\u201323340."},{"key":"e_1_3_2_62_1","doi-asserted-by":"crossref","unstructured":"Lu J Clark C Zellers R et\u00a0al. UNIFIED-IO: a unified model for vision language and multi-modal tasks. In: The Eleventh International Conference on Learning Representations. 2023. Available from: https:\/\/openreview.net\/forum?id=E01k9048soZ.","DOI":"10.1109\/ICME52920.2022.9859683"},{"key":"e_1_3_2_63_1","doi-asserted-by":"crossref","unstructured":"Rombach R Blattmann A Lorenz D et\u00a0al. High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_64_1","unstructured":"Ramesh A Pavlov M Goh G et\u00a0al. Zero-shot text-to-image generation. In: International Conference on Machine Learning. PMLR; 2021. p. 8821\u20138831."},{"key":"e_1_3_2_65_1","doi-asserted-by":"crossref","unstructured":"Zhou X Girdhar R Joulin A et\u00a0al. Detecting twenty-thousand classes using image-level supervision. In: ECCV. 2022.","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"e_1_3_2_66_1","doi-asserted-by":"crossref","unstructured":"Minderer M Gritsenko A Stone A et\u00a0al. Simple open-vocabulary object detection with vision transformers. In: European Conference on Computer Vision. 2022.","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"e_1_3_2_67_1","unstructured":"Liu T Wu Z Xiong W et\u00a0al. Unified multimodal pre-training and prompt-based tuning for vision-language understanding and generation. arXiv preprint arXiv:2112.05587 2021."},{"key":"e_1_3_2_68_1","unstructured":"Li B Weinberger KQ Belongie S et\u00a0al. Language-driven semantic segmentation. In: International Conference on Learning Representations. 2022. Available from: https:\/\/openreview.net\/forum?id=RriDjddCLN."},{"key":"e_1_3_2_69_1","unstructured":"Oquab M Darcet T Moutakanni T et\u00a0al. DINOv2: learning robust visual features without supervision. arXiv preprint 2023."},{"key":"e_1_3_2_70_1","doi-asserted-by":"crossref","unstructured":"Ma Y Xu G Sun X et\u00a0al. X-clip: end-to-end multi-grained contrastive learning for video-text retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia. 2022. p. 638\u2013647.","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_71_1","doi-asserted-by":"crossref","unstructured":"Chai W Guo X Wang G et\u00a0al. Stablevideo: text-driven consistency-aware diffusion video editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023. p. 23040\u201323050.","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"e_1_3_2_72_1","doi-asserted-by":"crossref","unstructured":"Elizalde B Deshmukh S Al Ismail M et\u00a0al. CLAP: learning audio concepts from natural language supervision. In: ICASSP 2023-2023 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 2023. p. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_2_73_1","doi-asserted-by":"crossref","unstructured":"Guzhov A Raue F Hees J et\u00a0al. Audioclip: extending clip to image text and audio. In: ICASSP 2022-2022 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 2022. p. 976\u2013980.","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"e_1_3_2_74_1","unstructured":"Radford A Kim JW Xu T et\u00a0al. Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning. 2023. p. 28492\u201328518."},{"key":"e_1_3_2_75_1","unstructured":"Agostinelli A Denk TI Borsos Z et\u00a0al. MusicLM: generating music from text. arXiv preprint 2023."},{"key":"e_1_3_2_76_1","unstructured":"Wang C Chen S Wu Y et\u00a0al. Neural codec language models are zero-shot text to speech synthesizers. arXiv preprint 2023."},{"key":"e_1_3_2_77_1","first-page":"72842","article-title":"Vast: a vision-audio-subtitle-text omni-modality foundation model and dataset","volume":"36","author":"Chen S","year":"2024","unstructured":"Chen S, Li H, Wang Q, et\u00a0al. Vast: a vision-audio-subtitle-text omni-modality foundation model and dataset. Adv Neural Inf Process Syst. 2024;36:72842\u201372866.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_78_1","doi-asserted-by":"crossref","unstructured":"Xue L Gao M Xing C et\u00a0al. ULIP: learning a unified representation of language images and point clouds for 3D understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023. p. 1179\u20131189.","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"e_1_3_2_79_1","doi-asserted-by":"crossref","unstructured":"Hegde D Valanarasu JMJ Patel V. Clip goes 3D: Leveraging prompt tuning for language grounded 3D recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023. p. 2028\u20132038.","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"e_1_3_2_80_1","doi-asserted-by":"crossref","unstructured":"Wu T Zhang J Fu X et\u00a0al. Omniobject3D: Large-vocabulary 3D object dataset for realistic perception reconstruction and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023. p. 803\u2013814.","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"e_1_3_2_81_1","unstructured":"Nichol A Jun H Dhariwal P et\u00a0al. Point-e: a system for generating 3D point clouds from complex prompts. arXiv preprint arXiv:2212.08751 2022."},{"key":"e_1_3_2_82_1","doi-asserted-by":"crossref","unstructured":"Cao T Kreis K Fidler S et\u00a0al. Texfusion: synthesizing 3D textures with text-guided image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023. p. 4169\u20134181.","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"e_1_3_2_83_1","unstructured":"Hong Y Zhen H Chen P et\u00a0al. 3D-LLM: injecting the 3D world into large language models. arXiv preprint 2023."},{"key":"e_1_3_2_84_1","doi-asserted-by":"crossref","unstructured":"Peng S Genova K Jiang C et\u00a0al. Openscene: 3D scene understanding with open vocabularies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023. p. 815\u2013824.","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"e_1_3_2_85_1","doi-asserted-by":"crossref","unstructured":"Chen B Xu Z Kirmani S et\u00a0al. SpatialVLM: endowing vision-language models with spatial reasoning capabilities. arXiv preprint 2024.","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"e_1_3_2_86_1","doi-asserted-by":"crossref","unstructured":"Girdhar R El-Nouby A Liu Z et\u00a0al. Imagebind: one embedding space to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023. p. 15180\u201315190.","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_2_87_1","unstructured":"Zhang Y Gong K Zhang K et\u00a0al. Meta-transformer: a unified framework for multimodal learning. arXiv preprint 2023."},{"key":"e_1_3_2_88_1","doi-asserted-by":"crossref","unstructured":"Wen B Yang W Kautz J et\u00a0al. FoundationPose: unified 6D pose estimation and tracking of novel objects. arXiv preprint 2023.","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"e_1_3_2_89_1","unstructured":"Tevet G Raab S Gordon B et\u00a0al. Human motion diffusion model. In: The Eleventh International Conference on Learning Representations. 2023."},{"key":"e_1_3_2_90_1","doi-asserted-by":"crossref","unstructured":"Zhang J Zhang Y Cun X et\u00a0al. T2M-GPT: generating human motion from textual descriptions with discrete representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023.","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"e_1_3_2_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"e_1_3_2_92_1","unstructured":"Shridhar M Manuelli L Fox D. CLIPort: what and where pathways for robotic manipulation. In: Proceedings of the 5th Conference on Robot Learning (CoRL). 2021."},{"key":"e_1_3_2_93_1","unstructured":"Liu Z Bahety A Song S. REFLECT: summarizing robot experiences for failure explanation and correction examples in the robofail benchmark. In: Conference on Robot Learning (CoRL). 2023. Available from: https:\/\/roboreflect.github.io\/."},{"key":"e_1_3_2_94_1","unstructured":"Zeng A Florence P Tompson J et\u00a0al. Transporter networks: rearranging the visual world for robotic manipulation. In: Conference on Robot Learning (CoRL). 2020."},{"key":"e_1_3_2_95_1","doi-asserted-by":"crossref","unstructured":"Kamath A Singh M LeCun Y et\u00a0al. Mdetr-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021. p. 1780\u20131790.","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_96_1","unstructured":"Huang W Wang C Zhang R et\u00a0al. VoxPoser: composable 3D value maps for robotic manipulation with language models. arXiv preprint 2023."},{"key":"e_1_3_2_97_1","unstructured":"Shafiullah NMM Paxton C Pinto L et\u00a0al. CLIP-fields: weakly supervised semantic fields for robotic memory. In: Robotics: science and systems. 2023."},{"key":"e_1_3_2_98_1","unstructured":"Ma YJ Liang W Wang G et\u00a0al. Eureka: human-level reward design via coding large language models. arXiv preprint arXiv:2310.12931 2023."},{"key":"e_1_3_2_99_1","doi-asserted-by":"crossref","unstructured":"Reimers N Gurevych I. Sentence-bert: sentence embeddings using siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019. p. 3982\u20133992. Available from: https:\/\/aclanthology.org\/D19-1410.","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_100_1","unstructured":"Gu X Lin T-Y Kuo W et\u00a0al. Open-vocabulary object detection via vision and language knowledge distillation. In: International Conference on Learning Representations. 2022."},{"key":"e_1_3_2_101_1","unstructured":"Tang Y Yu W Tan J et\u00a0al. SayTap: language to quadrupedal locomotion. In: 7th Annual Conference on Robot Learning. 2023. Available from: https:\/\/openreview.net\/forum?id=7TYeO2XVqI."},{"key":"e_1_3_2_102_1","unstructured":"Mirchandani S Xia F Florence P et\u00a0al. Large language models as general pattern machines. In: Proceedings of the 7th Conference on Robot Learning (CoRL). 2023."},{"key":"e_1_3_2_103_1","doi-asserted-by":"crossref","unstructured":"Chen Z Kiami S Gupta A et\u00a0al. GenAug: retargeting behaviors to unseen situations via generative augmentation. In: Robotics: science and systems. 2023.","DOI":"10.15607\/RSS.2023.XIX.010"},{"key":"e_1_3_2_104_1","doi-asserted-by":"crossref","unstructured":"Xiao T Chan H Sermanet P et\u00a0al. Robotic skill acquisition via instruction augmentation with vision-language models. In: Robotics: science and systems. 2023.","DOI":"10.15607\/RSS.2023.XIX.029"},{"key":"e_1_3_2_105_1","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S et\u00a0al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. p. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_106_1","doi-asserted-by":"crossref","unstructured":"He K Fan H Wu Y et\u00a0al. Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020. p. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_107_1","unstructured":"Shah R Kumar V. RRL: resnet as representation for reinforcement learning. In: International Conference on Machine Learning. PMLR; 2021."},{"key":"e_1_3_2_108_1","doi-asserted-by":"crossref","unstructured":"Deng J Dong W Socher R et\u00a0al. ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009. p. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_109_1","unstructured":"Grauman K Westbury A Byrne E et\u00a0al. Ego4D: around the world in 3000 hours of egocentric video. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. p. 18995\u201319012."},{"key":"e_1_3_2_110_1","unstructured":"Mandi Z Bharadhwaj H Moens V et\u00a0al. CACTI: a framework for scalable multi-task multi-scene visual imitation learning. In: CoRL 2022 Workshop on Pre-training Robot Learning. 2022. Available from: https:\/\/openreview.net\/forum?id=dRHW9-QFj9."},{"key":"e_1_3_2_111_1","unstructured":"Zeng A Attarian M Ichter B et\u00a0al. Socratic models: composing zero-shot multimodal reasoning with language. In: International Conference on Learning Representations. 2023."},{"key":"e_1_3_2_112_1","doi-asserted-by":"crossref","unstructured":"Chen B Xia F Ichter B et\u00a0al. Open-vocabulary queryable scene representations for real world planning. In: International Conference on Robotics and Automation. 2023.","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"e_1_3_2_113_1","unstructured":"Lin L-H Cui Y Hao Y et\u00a0al. Gesture-informed robot assistance via foundation models. In: 7th Annual Conference on Robot Learning. 2023. Available from: https:\/\/openreview.net\/forum?id=Ffn8Z4Q-zU."},{"key":"e_1_3_2_114_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5143773"},{"key":"e_1_3_2_115_1","doi-asserted-by":"crossref","unstructured":"Kawaharazuka K Obinata Y Kanazawa N et\u00a0al. VQA-based robotic state recognition optimized with genetic algorithm. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). 2023. p. 8306\u20138311.","DOI":"10.1109\/ICRA48891.2023.10160390"},{"key":"e_1_3_2_116_1","doi-asserted-by":"crossref","unstructured":"Kanazawa N Kawaharazuka K Obinata Y et\u00a0al. Recognition of heat-induced food state changes by time-series use of vision-language model for cooking robot. arXiv preprint arXiv:2309.01528 2023.","DOI":"10.1007\/978-3-031-44851-5_42"},{"key":"e_1_3_2_117_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272516"},{"key":"e_1_3_2_118_1","doi-asserted-by":"crossref","unstructured":"Liu W Du Y Hermans T et\u00a0al. StructDiffusion: language-guided creation of physically-valid structures using unseen objects. In: RSS 2023. 2023.","DOI":"10.15607\/RSS.2023.XIX.031"},{"key":"e_1_3_2_119_1","unstructured":"Black K Nakamoto M Atreya P et\u00a0al. Zero-shot robotic manipulation with pretrained image-editing diffusion models. arXiv preprint arXiv:2310.10639 2023."},{"key":"e_1_3_2_120_1","doi-asserted-by":"crossref","unstructured":"Brooks T Holynski A Efros AA. Instructpix2pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023. p. 18392\u201318402.","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_121_1","unstructured":"Du Y Yang M Dai B et\u00a0al. Learning universal policies via text-guided video generation. arXiv preprint 2023."},{"key":"e_1_3_2_122_1","unstructured":"Kwon M Xie SM Bullard K et\u00a0al. Reward design with language models. In: International Conference on Learning Representations. 2023."},{"key":"e_1_3_2_123_1","unstructured":"Yu W Gileadi N Fu C et\u00a0al. Language to rewards for robotic skill synthesis. In: 7th Annual Conference on Robot Learning. 2023. Available from: https:\/\/openreview.net\/forum?id=SgTPdyehXMA."},{"key":"e_1_3_2_124_1","unstructured":"Lin J Du Y Watkins O et\u00a0al. Learning to model the world with language. arXiv preprint 2023."},{"key":"e_1_3_2_125_1","unstructured":"Hafner D Pasukonis J Ba J et\u00a0al. Mastering diverse domains through world models. arXiv preprint 2023."},{"key":"e_1_3_2_126_1","unstructured":"Cui Y Niekum S Gupta A et\u00a0al. Can foundation models perform zero-shot task specification for robot manipulation? In: Learning for Dynamics and Control Conference. 2022. p. 893\u2013905."},{"key":"e_1_3_2_127_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"e_1_3_2_128_1","doi-asserted-by":"crossref","unstructured":"Bahl S Mendonca R Chen L et\u00a0al. Affordances from human videos as a versatile representation for robotics. In: CVPR. 2023.","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"e_1_3_2_129_1","unstructured":"Ma YJ Sodhani S Jayaraman D et\u00a0al. VIP: towards universal visual reward and representation via value-implicit pre-training. In: International Conference on Learning Representations. 2023."},{"key":"e_1_3_2_130_1","unstructured":"Ma YJ Liang W Som V et\u00a0al. LIV: language-image representations and rewards for robotic control. In: International Conference on Machine Learning. 2023."},{"key":"e_1_3_2_131_1","unstructured":"Shah D Osinski B Ichter B et\u00a0al. LM-Nav: robotic navigation with large pre-trained models of language vision and action. In: 6th Annual Conference on Robot Learning. 2022."},{"key":"e_1_3_2_132_1","unstructured":"Gadre SY Wortsman M Ilharco G et\u00a0al. Clip on wheels: zero-shot object navigation as object localization and exploration. arXiv preprint arXiv:2203.10421 3(4):7 2022."},{"key":"e_1_3_2_133_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_134_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_135_1","doi-asserted-by":"crossref","unstructured":"Huang C Mees O Zeng A et\u00a0al. Audio visual language maps for robot navigation. In: International Symposium on Experimental Robotics (ISER). 2023.","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"e_1_3_2_136_1","doi-asserted-by":"crossref","unstructured":"Huang C Mees O Zeng A et\u00a0al. Visual language maps for robot navigation. In: IEEE International Conference on Robotics and Automation (ICRA). 2023.","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"e_1_3_2_137_1","doi-asserted-by":"crossref","unstructured":"Jatavallabhula KM Kuwajerwala A Gu Q et\u00a0al. ConceptFusion: open-set multimodal 3D mapping. In: Robotics: science and systems (RSS) 2023. 2023.","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"e_1_3_2_138_1","doi-asserted-by":"crossref","unstructured":"Yamazaki K Hanyu T Vo K et\u00a0al. Open-fusion: real-time open-vocabulary 3D mapping and queryable scene representation. In: IEEE International Conference on Robotics and Automation (ICRA). 2024.","DOI":"10.1109\/ICRA57147.2024.10610193"},{"key":"e_1_3_2_139_1","unstructured":"Gu Q Kuwajerwala A Jatavallabhula KM et\u00a0al. ConceptGraphs: open-vocabulary 3D scene graphs for perception and planning. In: 2nd Workshop on Language and Robot Learning: Language as Grounding. 2023. Available from: https:\/\/openreview.net\/forum?id=QVbHQ33R0x."},{"key":"e_1_3_2_140_1","unstructured":"Huang W Abbeel P Pathak D et\u00a0al. Language models as zero-shot planners: extracting actionable knowledge for embodied agents. In: International Conference on Machine Learning. 2022. p. 9118\u20139147."},{"key":"e_1_3_2_141_1","unstructured":"Huang W Xia F Xiao T et\u00a0al. Inner monologue: embodied reasoning through planning with language models. In: Conference on Robot Learning. 2022."},{"key":"e_1_3_2_142_1","doi-asserted-by":"crossref","unstructured":"Mees O Borja-Diaz J Burgard W. Grounding language with visual affordances over unstructured data. In: IEEE International Conference on Robotics and Automation (ICRA). 2023.","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"e_1_3_2_143_1","doi-asserted-by":"crossref","unstructured":"Yang Z Garrett CR Lozano-P\u00e9rez T et\u00a0al. Sequence-based plan feasibility prediction for efficient task and motion planning. In: Robotics: science and systems. 2023.","DOI":"10.15607\/RSS.2023.XIX.061"},{"key":"e_1_3_2_144_1","unstructured":"Huang W Xia F Shah D et\u00a0al. Grounded decoding: guiding text generation with grounded models for robot control. In: Thirty-Seventh Conference on Neural Information Processing Systems. 2023. Available from: https:\/\/openreview.net\/forum?id=JCCi58IUsh."},{"key":"e_1_3_2_145_1","doi-asserted-by":"crossref","unstructured":"Ding Y Zhang X Paxton C et\u00a0al. Task and motion planning with large language models for object rearrangement. arXiv preprint 2023.","DOI":"10.1109\/IROS55552.2023.10342169"},{"key":"e_1_3_2_146_1","doi-asserted-by":"crossref","unstructured":"Lin K Agia C Migimatsu T et\u00a0al. Text2Motion: from natural language instructions to feasible plans. In: ICRA 2023 Workshop Pretraining4Robotics. 2023.","DOI":"10.1007\/s10514-023-10131-7"},{"key":"e_1_3_2_147_1","unstructured":"Wu Y Min SY Bisk Y et\u00a0al. Plan eliminate and track \u2013 language models are good teachers for embodied agents. arXiv preprint 2023."},{"key":"e_1_3_2_148_1","unstructured":"Sundaresan P Belkhale S Sadigh D et\u00a0al. KITE: keypoint-conditioned policies for semantic manipulation. In: 7th Annual Conference on Robot Learning. 2023. Available from: https:\/\/openreview.net\/forum?id=veGdf4L4Xz."},{"key":"e_1_3_2_149_1","unstructured":"Ren AZ Dixit A Bodrova A et\u00a0al. Robots that ask for help: uncertainty alignment for large language model planners. In: Conference on Robot Learning (CoRL). 2023."},{"key":"e_1_3_2_150_1","unstructured":"Rana K Haviland J Garg S et\u00a0al. SayPlan: grounding large language models using 3D scene graphs for scalable task planning. In: 7th Annual Conference on Robot Learning. 2023. Available from: https:\/\/openreview.net\/forum?id=wMpOMO0Ss7a."},{"key":"e_1_3_2_151_1","doi-asserted-by":"crossref","unstructured":"Ichikura A Kawaharazuka K Obinata Y et\u00a0al. A method for selecting scenes and emotion-based descriptions for a robot's diary. In: IEEE RO-MAN. 2023.","DOI":"10.1109\/RO-MAN57019.2023.10309432"},{"key":"e_1_3_2_152_1","doi-asserted-by":"crossref","unstructured":"Liu P Orru Y Paxton C et\u00a0al. OK-Robot: what really matters in integrating open-knowledge models for robotics. arXiv preprint arXiv:2401.12202 2024.","DOI":"10.15607\/RSS.2024.XX.091"},{"key":"e_1_3_2_153_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"e_1_3_2_154_1","doi-asserted-by":"crossref","unstructured":"Singh I Blukis V Mousavian A et\u00a0al. ProgPrompt: generating situated robot task plans using large language models. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). 2023.","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"e_1_3_2_155_1","doi-asserted-by":"crossref","unstructured":"Wake N Kanehira A Sasabuchi K et\u00a0al. Chatgpt empowered long-step robot control in various environments: a case application. arXiv preprint 2023.","DOI":"10.1109\/ACCESS.2023.3310935"},{"key":"e_1_3_2_156_1","doi-asserted-by":"crossref","unstructured":"Shirasaka M Matsushima T Tsunashima S et\u00a0al. Self-recovery prompting: promptable general purpose service robot system with foundation models and self-recovery. In: 2024 IEEE International Conference on Robotics and Automation (ICRA). IEEE; 2024. p.\u00a017395\u201317402.","DOI":"10.1109\/ICRA57147.2024.10611640"},{"key":"e_1_3_2_157_1","unstructured":"Liu B Jiang Y Zhang X et\u00a0al. LLM+P: empowering large language models with optimal planning proficiency. arXiv preprint 2023."},{"key":"e_1_3_2_158_1","unstructured":"Aeronautiques C Howe A Knoblock C et\u00a0al. PDDL -- the planning domain definition language. Technical Report Tech. Rep. 1998."},{"key":"e_1_3_2_159_1","unstructured":"Wang G Xie Y Jiang Y et\u00a0al. Voyager: an open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 2023."},{"key":"e_1_3_2_160_1","doi-asserted-by":"crossref","unstructured":"Vemprala S Bonatti R Bucker A et\u00a0al. ChatGPT for robotics: design principles and model abilities. arXiv preprint 2023.","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"e_1_3_2_161_1","unstructured":"Puig X Undersander E Szot A et\u00a0al. Habitat 3.0: a co-habitat for humans avatars and robots. arXiv preprint arXiv:2310.13724 2023."},{"key":"e_1_3_2_162_1","doi-asserted-by":"crossref","unstructured":"Yoneda T Fang J Li P et\u00a0al. Statler: state-maintaining language models for embodied reasoning. arXiv preprint 2023.","DOI":"10.1109\/ICRA57147.2024.10610634"},{"key":"e_1_3_2_163_1","unstructured":"Obinata Y Kanazawa N Kawaharazuka K et\u00a0al. Foundation model based open vocabulary task planning and executive system for general purpose service robots. arXiv preprint 2023."},{"key":"e_1_3_2_164_1","doi-asserted-by":"crossref","unstructured":"Shirai K Beltran-Hernandez CC Hamaya M et\u00a0al. Vision-language interpreter for robot task planning. arXiv preprint arXiv:2311.00967 2023.","DOI":"10.1109\/ICRA57147.2024.10611112"},{"key":"e_1_3_2_165_1","unstructured":"Wang Y-J Zhang B Chen J et\u00a0al. Prompt a robot to walk with large language models. arXiv preprint 2023."},{"key":"e_1_3_2_166_1","doi-asserted-by":"crossref","unstructured":"Yu T Xiao T Stone A et\u00a0al. Scaling robot learning with semantically imagined experience. arXiv preprint arXiv:2302.11550 2023.","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"e_1_3_2_167_1","doi-asserted-by":"crossref","unstructured":"Brohan A Brown N Carbajal J et\u00a0al. Rt-1: robotics transformer for real-world control at scale. In: Proceedings of Robotics: Science and Systems. 2023.","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"e_1_3_2_168_1","doi-asserted-by":"crossref","unstructured":"Wang S Saharia C Montgomery C et\u00a0al. Imagen editor and editbench: advancing and evaluating text-guided image inpainting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023. p. 18359\u201318369.","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"e_1_3_2_169_1","unstructured":"Stone A Xiao T Lu Y et\u00a0al. Open-world object manipulation using pre-trained vision-language models. arXiv preprint 2023."},{"key":"e_1_3_2_170_1","doi-asserted-by":"crossref","unstructured":"Sermanet P Lynch C Chebotar Y et\u00a0al. Time-contrastive networks: self-supervised learning from video. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE; 2018. p. 1134\u20131141.","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"e_1_3_2_171_1","unstructured":"Xiao T Radosavovic I Darrell T et\u00a0al. Masked visual pre-training for motor control. arXiv preprint arXiv:2203.06173 2022."},{"key":"e_1_3_2_172_1","unstructured":"Radosavovic I Xiao T James S et\u00a0al. Real-world robot learning with masked visual pre-training. In: 6th Annual Conference on Robot Learning. 2022. Available from: https:\/\/openreview.net\/forum?id=KWCZfuqshd."},{"key":"e_1_3_2_173_1","doi-asserted-by":"crossref","unstructured":"He K Chen X Xie S et\u00a0al. Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022. p. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_174_1","unstructured":"Driess D Xia F M Sajjadi MS et\u00a0al. Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 2023."},{"key":"e_1_3_2_175_1","unstructured":"Sermanet P Ding T Zhao J et\u00a0al. RoboVQA: multimodal long-horizon reasoning for robotics. In: 2nd Workshop on Language and Robot Learning: Language as Grounding. 2023. Available from: https:\/\/openreview.net\/forum?id=z3zBluGh1L."},{"key":"e_1_3_2_176_1","unstructured":"Kalashnikov D Varley J Chebotar Y et\u00a0al. Scaling up multi-task robotic reinforcement learning. In: 5th Annual Conference on Robot Learning. 2021. Available from: https:\/\/openreview.net\/forum?id=p9Pe-l9MMEq."},{"key":"e_1_3_2_177_1","unstructured":"Jang E Irpan A Khansari M et\u00a0al. BC-Z: zero-shot task generalization with robotic imitation learning. In: 5th Annual Conference on Robot Learning. 2021. Available from: https:\/\/openreview.net\/forum?id=8kbp23tSGYv."},{"key":"e_1_3_2_178_1","unstructured":"Reed S Zolna K Parisotto E et\u00a0al. A generalist agent. In: Transactions on machine learning research. 2022. Available from: https:\/\/openreview.net\/forum?id=1ikK0kHjvj."},{"key":"e_1_3_2_179_1","unstructured":"Chebotar Y Vuong Q Hausman K et\u00a0al. Q-transformer: scalable offline reinforcement learning via autoregressive Q-functions. In: 7th Annual Conference on Robot Learning. 2023."},{"key":"e_1_3_2_180_1","unstructured":"Bousmalis K Vezzani G Rao D et\u00a0al. RoboCat: a self-improving foundation agent for robotic manipulation. arXiv preprint arXiv:2306.11706 2023."},{"key":"e_1_3_2_181_1","unstructured":"Schubert I Zhang J Bruce J et\u00a0al. A generalist dynamics model for control. arXiv preprint arXiv:2305.10912 2023."},{"key":"e_1_3_2_182_1","doi-asserted-by":"crossref","unstructured":"Kelly M Sidrane C Driggs-Campbell K et\u00a0al. Hg-dagger: interactive imitation learning with human experts. In: 2019 International Conference on Robotics and Automation (ICRA). 2019. p. 8077\u20138083.","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"e_1_3_2_183_1","unstructured":"Jiang Y Gupta A Zhang Z et\u00a0al. VIMA: robot manipulation with multimodal prompts. In: Fortieth International Conference on Machine Learning. 2023."},{"key":"e_1_3_2_184_1","unstructured":"Chen X Djolonga J Padlewski P et\u00a0al. PaLI-X: on scaling up a multilingual vision and language model. arXiv preprint arXiv:2305.18565 2023."},{"key":"e_1_3_2_185_1","unstructured":"Gu J Kirmani S Wohlhart P et\u00a0al. RT-trajectory: robotic task generalization via hindsight trajectory sketches. arXiv preprint arXiv:2311.01977 2023."},{"key":"e_1_3_2_186_1","unstructured":"Anonymous. RT-sketch: goal-conditioned imitation learning from hand-drawn sketches. 2024. Available from: https:\/\/openreview.net\/forum?id=YxvmODVWny."},{"key":"e_1_3_2_187_1","unstructured":"Ahn M Dwibedi D Finn C et\u00a0al. Autort: embodied foundation models for large scale orchestration of robotic agents. arXiv preprint arXiv:2401.12963 2024."},{"key":"e_1_3_2_188_1","doi-asserted-by":"crossref","unstructured":"Leal I Choromanski K Jain D et\u00a0al. Sara-rt: scaling up robotics transformers with self-adaptive robust attention. arXiv preprint arXiv:2312.01990 2023.","DOI":"10.1109\/ICRA57147.2024.10611597"},{"key":"e_1_3_2_189_1","unstructured":"Octo Model Team Ghosh D Walke H Pertsch K et\u00a0al. Octo: an open-source generalist robot policy. 2023. Available from: https:\/\/octo-models.github.io."},{"key":"e_1_3_2_190_1","doi-asserted-by":"crossref","unstructured":"Chi C Feng S Du Y et\u00a0al. Diffusion policy: visuomotor policy learning via action diffusion. arXiv preprint arXiv:2303.04137 2023.","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"e_1_3_2_191_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_192_1","unstructured":"Tassa Y Doron Y Muldal A et\u00a0al. Deepmind control suite. arXiv preprint arXiv:1801.00690 2018."},{"key":"e_1_3_2_193_1","doi-asserted-by":"crossref","unstructured":"Geng Z Cao C Tulyakov S. 3D guided fine-grained face manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019. p. 9821\u20139830.","DOI":"10.1109\/CVPR.2019.01005"},{"key":"e_1_3_2_194_1","doi-asserted-by":"crossref","unstructured":"Gu S Holly E Lillicrap T et\u00a0al. Deep reinforcement learning for robotic manipulation. In: 2017 IEEE International Conference on Robotics and Automation (ICRA). 2017. p. 3389\u20133396.","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"e_1_3_2_195_1","unstructured":"Yang M Du Y Ghasemipour K et\u00a0al. Learning interactive real-world simulators. arXiv preprint arXiv:2310.06114 2023."},{"key":"e_1_3_2_196_1","unstructured":"Jaegle A Borgeaud S Alayrac J-B et\u00a0al. Perceiver io: a general architecture for structured inputs & outputs. In: International Conference on Learning Representations. 2022. Available from: https:\/\/openreview.net\/forum?id=fILj7WpI-g."},{"key":"e_1_3_2_197_1","unstructured":"Shridhar M Manuelli L Fox D. Perceiver-actor: a multi-task transformer for robotic manipulation. In: 6th Annual Conference on Robot Learning. 2022. Available from: https:\/\/openreview.net\/forum?id=PS_eCS_WCvD."},{"key":"e_1_3_2_198_1","doi-asserted-by":"crossref","unstructured":"Perez E Strub F De Vries H et\u00a0al. Film: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence Vol. 32. 2018.","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_2_199_1","doi-asserted-by":"crossref","unstructured":"Bharadhwaj H Vakil J Sharma M et\u00a0al. Roboagent: generalization and efficiency in robot manipulation via semantic augmentations and action chunking. arXiv preprint arXiv:2309.01918 2023.","DOI":"10.1109\/ICRA57147.2024.10611293"},{"key":"e_1_3_2_200_1","unstructured":"Tan M Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning. PMLR; 2019. p. 6105\u20136114."},{"key":"e_1_3_2_201_1","first-page":"12786","article-title":"Tokenlearner: adaptive space-time tokenization for videos","volume":"34","author":"Ryoo M","year":"2021","unstructured":"Ryoo M, Piergiovanni AJ, Arnab A, et\u00a0al. Tokenlearner: adaptive space-time tokenization for videos. Adv Neural Inf Process Syst. 2021;34:12786\u201312797.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_202_1","unstructured":"Dasari S Ebert F Tian S et\u00a0al. Robonet: large-scale multi-robot learning. In: Conference on Robot Learning (CoRL). 2019."},{"key":"e_1_3_2_203_1","unstructured":"Fu J Kumar A Nachum O et\u00a0al. D4rl: datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219 2020."},{"key":"e_1_3_2_204_1","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar A","year":"2020","unstructured":"Kumar A, Zhou A, Tucker G, et\u00a0al. Conservative q-learning for offline reinforcement learning. Adv Neural Inf Process Syst. 2020;33:1179\u20131191.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_205_1","first-page":"14129","article-title":"Mopo: model-based offline policy optimization","volume":"33","author":"Yu T","year":"2020","unstructured":"Yu T, Thomas G, Yu L, et\u00a0al. Mopo: model-based offline policy optimization. Adv Neural Inf Process Syst. 2020;33:14129\u201314142.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_206_1","unstructured":"Matsushima T Furuta H Matsuo Y et\u00a0al. Deployment-efficient reinforcement learning via model-based offline optimization. In: International Conference on Learning Representations. 2021. Available from: https:\/\/openreview.net\/forum?id=3hGNqpI4WS."},{"key":"e_1_3_2_207_1","doi-asserted-by":"crossref","unstructured":"Ebert F Yang Y Schmeckpeper K et\u00a0al. Bridge data: boosting generalization of robotic skills with cross-domain datasets. In: Robotics: science and systems. 2022.","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"e_1_3_2_208_1","unstructured":"Walke H Black K Lee A et\u00a0al. Bridgedata v2: a dataset for robot learning at scale. In: Conference on Robot Learning (CoRL). 2023."},{"key":"e_1_3_2_209_1","doi-asserted-by":"crossref","unstructured":"Zhao TZ Kumar V Levine S et\u00a0al. Learning fine-grained bimanual manipulation with low-cost hardware. arXiv preprint arXiv:2304.13705 2023.","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"e_1_3_2_210_1","doi-asserted-by":"crossref","unstructured":"Fu Z Zhao TZ Finn C. Mobile ALOHA: learning bimanual mobile manipulation with low-cost whole-body teleoperation. arXiv preprint arXiv:2401.02117 2024.","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"e_1_3_2_211_1","unstructured":"Wu P Shentu Y Yi Z et\u00a0al. GELLO: a general low-cost and intuitive teleoperation framework for robot manipulators. arXiv preprint arXiv:2309.13037 2023."},{"key":"e_1_3_2_212_1","volume-title":"Reinforcement learning: an introduction","author":"Sutton RS","year":"2018","unstructured":"Sutton RS, Barto AG. Reinforcement learning: an introduction. The MIT Press; 2018."},{"key":"e_1_3_2_213_1","first-page":"35365","article-title":"Uni [mask]: unified inference in sequential decision problems","volume":"35","author":"Carroll M","year":"2022","unstructured":"Carroll M, Paradise O, Lin J, et\u00a0al. Uni [mask]: unified inference in sequential decision problems. Adv Neural Inf Process Syst. 2022;35:35365\u201335378.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_214_1","unstructured":"Wu P Majumdar A Stone K et\u00a0al. Masked trajectory models for prediction representation and control. In: Proceedings of the 40th International Conference on Machine Learning volume 202 of Proceedings of Machine Learning Research. PMLR; 2023 Jan. p.\u00a037607\u201337623."},{"key":"e_1_3_2_215_1","doi-asserted-by":"crossref","unstructured":"Hatori J Kikuchi Y Kobayashi S et\u00a0al. Interactively picking real-world objects with unconstrained spoken language instructions. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE; 2018. p. 3774\u20133781.","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"e_1_3_2_216_1","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2016.1164622"},{"key":"e_1_3_2_217_1","doi-asserted-by":"crossref","unstructured":"Shah D Sridhar A Bhorkar A et\u00a0al. GNM: a general navigation model to drive any robot. In: International Conference on Robotics and Automation (ICRA). 2023.","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"e_1_3_2_218_1","unstructured":"Shah D Sridhar A Dashora N et\u00a0al. ViNT: a foundation model for visual navigation. In: 7th Annual Conference on Robot Learning. 2023."},{"key":"e_1_3_2_219_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10136-2"},{"key":"e_1_3_2_220_1","doi-asserted-by":"crossref","unstructured":"Kawaharazuka K Obinata Y Kanazawa N et\u00a0al. Robotic applications of pre-trained vision-language models to various recognition behaviors. arXiv preprint arXiv:2303.05674 2023.","DOI":"10.1109\/Humanoids57100.2023.10375211"},{"key":"e_1_3_2_221_1","unstructured":"Yenamandra S Ramachandran A Yadav K et\u00a0al. HomeRobot: open-vocabulary mobile manipulation. In: 7th Annual Conference on Robot Learning. 2023. Available from: https:\/\/openreview.net\/forum?id=b-cto-fetlz."},{"key":"e_1_3_2_222_1","doi-asserted-by":"crossref","unstructured":"Ichikura A Kawaharazuka K Obinata Y et\u00a0al. Automatic diary generation system including information on joint experiences between humans and robots. arXiv preprint arXiv:2309.01948 2023.","DOI":"10.1007\/978-3-031-44981-9_33"},{"issue":"1","key":"e_1_3_2_223_1","first-page":"1","article-title":"The story of beau: exploring the potential of generative diaries in shaping social perceptions of robots","volume":"17","author":"Cho H","year":"2023","unstructured":"Cho H, Nam T-J. The story of beau: exploring the potential of generative diaries in shaping social perceptions of robots. Int J Des. 2023;17(1):1\u201315.","journal-title":"Int J Des"},{"key":"e_1_3_2_224_1","doi-asserted-by":"crossref","unstructured":"Chang M Gervet T Khanna M et\u00a0al. Goat: go to any thing. arXiv preprint arXiv:2311.06430 2023.","DOI":"10.15607\/RSS.2024.XX.073"},{"key":"e_1_3_2_225_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"e_1_3_2_226_1","doi-asserted-by":"crossref","unstructured":"Gong R Huang J Zhao Y et\u00a0al. ARNOLD: a benchmark for language-grounded task learning with continuous states in realistic 3D scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) 2023.","DOI":"10.1109\/ICCV51070.2023.01873"}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2024.2408593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T14:38:22Z","timestamp":1732891102000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2024.2408593"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,16]]},"references-count":225,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2024,9,16]]}},"alternative-id":["10.1080\/01691864.2024.2408593"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2024.2408593","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,16]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2024-02-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-24","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}