{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T13:17:19Z","timestamp":1785331039166,"version":"3.55.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031918124","type":"print"},{"value":"9783031918131","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-91813-1_17","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:41:51Z","timestamp":1748090511000},"page":"264-273","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["RoboTwin: Dual-Arm Robot Benchmark with\u00a0Generative Digital Twins (Early Version)"],"prefix":"10.1007","author":[{"given":"Yao","family":"Mu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijia","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zanxin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yude","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lunkai","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"17_CR1","unstructured":"GPT-4V(ision) system card (2023). https:\/\/api.semanticscholar.org\/CorpusID:263218031"},{"key":"17_CR2","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint: arXiv:2303.08774 (2023)"},{"key":"17_CR3","unstructured":"Ahn, M., et\u00a0al.: Do as i can, not as i say: grounding language in robotic affordances. arXiv preprint: arXiv:2204.01691 (2022)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Bahl, S., Mendonca, R., Chen, L., Jain, U., Pathak, D.: Affordances from human videos as a versatile representation for robotics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13778\u201313790 (2023)","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"17_CR5","unstructured":"Brohan, A., et\u00a0al.: RT-1: robotics transformer for real-world control at scale. In: arXiv preprint: arXiv:2212.06817 (2022)"},{"key":"17_CR6","unstructured":"Chebotar, Y., et\u00a0al.: Q-transformer: scalable offline reinforcement learning via autoregressive Q-functions. In: Conference on Robot Learning, pp. 3909\u20133928. PMLR (2023)"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Chi, C., et al.: Diffusion policy: visuomotor policy learning via action diffusion. arXiv preprint: arXiv:2303.04137 (2023)","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"17_CR8","unstructured":"Dalal, M., Mandlekar, A., Garrett, C., Handa, A., Salakhutdinov, R., Fox, D.: Imitating task and motion planning with visuomotor transformers. arXiv preprint: arXiv:2305.16309 (2023)"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Ebert, F., et al.: Bridge data: boosting generalization of robotic skills with cross-domain datasets. arXiv preprint: arXiv:2109.13396 (2021)","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"17_CR10","unstructured":"Gu, J., et\u00a0al.: ManiSkill2: a unified benchmark for generalizable manipulation skills. arXiv preprint: arXiv:2302.04659 (2023)"},{"key":"17_CR11","unstructured":"G\u00fcrtler, N., et al.: Benchmarking offline reinforcement learning on real-robot hardware. arXiv preprint: arXiv:2307.15690 (2023)"},{"issue":"2","key":"17_CR12","doi-asserted-by":"publisher","first-page":"3019","DOI":"10.1109\/LRA.2020.2974707","volume":"5","author":"S James","year":"2020","unstructured":"James, S., Ma, Z., Arrojo, D.R., Davison, A.J.: RLBench: the robot learning benchmark & learning environment. IEEE Robot. Autom. Lett. 5(2), 3019\u20133026 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"17_CR13","unstructured":"Jang, E., et al.: BC-Z: zero-shot task generalization with robotic imitation learning. In: Conference on Robot Learning, pp. 991\u20131002. PMLR (2022)"},{"key":"17_CR14","unstructured":"Jiang, Y., et al.: VIMA: general robot manipulation with multimodal prompts. In: International Conference on Machine Learning (2023)"},{"key":"17_CR15","unstructured":"Kalashnikov, D., et al.: MT-Opt: continuous multi-task robotic reinforcement learning at scale. arXiv preprint: arXiv:2104.08212 (2021)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Kumar, A., et al.: Pre-training for robots: offline RL enables learning new tasks from a handful of trials. arXiv preprint: arXiv:2210.05178 (2022)","DOI":"10.15607\/RSS.2023.XIX.019"},{"key":"17_CR17","unstructured":"Kumar, A., Singh, A., Tian, S., Finn, C., Levine, S.: A workflow for offline model-free robotic reinforcement learning. arXiv preprint: arXiv:2109.10813 (2021)"},{"key":"17_CR18","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: tutorial, review, and perspectives on open problems. arXiv preprint: arXiv:2005.01643 (2020)"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Lynch, C., et al.: Interactive language: talking to robots in real time. IEEE Robot. Autom. Lett. (2023)","DOI":"10.1109\/LRA.2023.3295255"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Mandlekar, A., et al.: Scaling robot supervision to hundreds of hours with RoboTurk: robotic manipulation dataset through human reasoning and dexterity. arXiv preprint: arXiv:1911.04052 (2019)","DOI":"10.1109\/IROS40897.2019.8968114"},{"key":"17_CR21","unstructured":"Mandlekar, A., et al.: MimicGen: a data generation system for scalable robot learning using human demonstrations. arXiv preprint: arXiv:2310.17596 (2023)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Mandlekar, A., Xu, D., Mart\u00edn-Mart\u00edn, R., Savarese, S., Fei-Fei, L.: Learning to generalize across long-horizon tasks from human demonstrations. In: Robotics: Science and Systems (RSS) (2020)","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"17_CR23","doi-asserted-by":"publisher","unstructured":"Mandlekar, A., Xu, D., Mart\u00edn-Mart\u00edn, R., Zhu, Y., Fei-Fei, L., Savarese, S.: Human-in-the-loop imitation learning using remote teleoperation (2020). https:\/\/doi.org\/10.48550\/ARXIV.2012.06733, https:\/\/arxiv.org\/abs\/2012.06733","DOI":"10.48550\/ARXIV.2012.06733"},{"key":"17_CR24","unstructured":"Mandlekar, A., et al.: RoboTurk: a crowdsourcing platform for robotic skill learning through imitation. In: Conference on Robot Learning (2018)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Nasiriany, S., et al.: RoboCasa: large-scale simulation of everyday tasks for generalist robots. arXiv preprint: arXiv:2406.02523 (2024)","DOI":"10.15607\/RSS.2024.XX.050"},{"key":"17_CR26","unstructured":"Pomerleau, D.A.: ALVINN: an autonomous land vehicle in a neural network. In: Advances in Neural Information Processing Systems, pp. 305\u2013313 (1989)"},{"key":"17_CR27","unstructured":"Sharma, P., Mohan, L., Pinto, L., Gupta, A.: Multiple interactions made easy (MIME): Large scale demonstrations data for imitation. In: Conference on Robot Learning, pp. 906\u2013915. PMLR (2018)"},{"key":"17_CR28","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"17_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"17_CR30","unstructured":"Ze, Y., Zhang, G., Zhang, K., Hu, C., Wang, M., Xu, H.: 3D diffusion policy. arXiv preprint: arXiv:2403.03954 (2024)"},{"key":"17_CR31","unstructured":"Zeng, A., et al.: Transporter networks: rearranging the visual world for robotic manipulation. In: Conference on Robot Learning (2020)"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: Deep imitation learning for complex manipulation tasks from virtual reality teleoperation. In: IEEE International Conference on Robotics and Automation (ICRA) (2018)","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, T.Z., Kumar, V., Levine, S., Finn, C.: Learning fine-grained bimanual manipulation with low-cost hardware. arXiv preprint: arXiv:2304.13705 (2023)","DOI":"10.15607\/RSS.2023.XIX.016"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91813-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:41:58Z","timestamp":1748090518000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91813-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031918124","9783031918131"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91813-1_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}