{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T04:18:19Z","timestamp":1787804299113,"version":"build-2784847793"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"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":["J Robotic Surg"],"DOI":"10.1007\/s11701-026-03866-9","type":"journal-article","created":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T03:25:23Z","timestamp":1787801123000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Embodied AI in the operating room: a voice-interactive robotic scrub nurse for surgical instrument handoffs"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5430-7572","authenticated-orcid":false,"given":"Mustafa","family":"Khan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2293-7967","authenticated-orcid":false,"given":"Joao","family":"Bombardelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"key":"3866_CR1","doi-asserted-by":"publisher","DOI":"10.1590\/0100-6991e-20202798","author":"ALG Morrell","year":"2023","unstructured":"Morrell ALG, Morrell-Junior AC, Morrell AG, Mendes JM, Tustumi F, De-Carli LA (2023) The history of robotic surgery and its evolution: when illusion becomes reality. Rev Col Bras Cir. https:\/\/doi.org\/10.1590\/0100-6991e-20202798","journal-title":"Rev Col Bras Cir"},{"key":"3866_CR2","doi-asserted-by":"publisher","first-page":"eaam8638","DOI":"10.1126\/scirobotics.aam8638","volume":"2","author":"GZ Yang","year":"2017","unstructured":"Yang GZ, Cambias J, Cleary K et al (2017) Medical robotics\u2014regulatory, ethical, and legal considerations for increasing levels of autonomy. Sci Robot 2:eaam8638. https:\/\/doi.org\/10.1126\/scirobotics.aam8638","journal-title":"Sci Robot"},{"key":"3866_CR3","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1146\/annurev-control-062420-090543","volume":"4","author":"A Attanasio","year":"2021","unstructured":"Attanasio A, Scaglioni B, De Momi E, Fiorini P, Valdastri P (2021) Autonomy in surgical robotics. Annu Rev Control Robot Auton Syst 4:651\u2013679. https:\/\/doi.org\/10.1146\/annurev-control-062420-090543","journal-title":"Annu Rev Control Robot Auton Syst"},{"key":"3866_CR4","doi-asserted-by":"publisher","unstructured":"Black K, Brown N, Driess D et al (2024) \u03c00: A vision-language-action flow model for general robot control. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2410.24164. arXiv:2410.24164","DOI":"10.48550\/arXiv.2410.24164"},{"key":"3866_CR5","doi-asserted-by":"crossref","unstructured":"Brohan A, Brown N, Carbajal J et al (2023) RT-1: robotics transformer for real-world control at scale. In: Robotics: Science and Systems. arXiv:2212.06817","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"3866_CR6","unstructured":"Brohan A, Brown N, Carbajal J et al (2023) RT-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning. arXiv:2307.15818"},{"key":"3866_CR7","doi-asserted-by":"publisher","DOI":"10.3389\/fsci.2026.1783803","author":"A Granados","year":"2026","unstructured":"Granados A et al (2026) Evolving surgical teams in the age of artificial intelligence and robotics. Front Sci. https:\/\/doi.org\/10.3389\/fsci.2026.1783803","journal-title":"Front Sci"},{"key":"3866_CR8","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adt3093","author":"Y Long","year":"2025","unstructured":"Long Y, Lin A, Kwok DHC et al (2025) Surgical embodied intelligence for generalized task autonomy in laparoscopic robot-assisted surgery. Sci Robot. https:\/\/doi.org\/10.1126\/scirobotics.adt3093","journal-title":"Sci Robot"},{"key":"3866_CR9","doi-asserted-by":"publisher","DOI":"10.1515\/cdbme-2024-1052","author":"C Scheppach","year":"2024","unstructured":"Scheppach C, Wagner L, Spinner C et al (2024) Innovating instrument handover techniques for robotic scrub nurses. Curr Dir Biomed Eng. https:\/\/doi.org\/10.1515\/cdbme-2024-1052","journal-title":"Curr Dir Biomed Eng"},{"key":"3866_CR10","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.artmed.2014.10.006","volume":"62","author":"JP Wachs","year":"2014","unstructured":"Wachs JP, Frenkel B, Dori D (2014) Operation room tool handling and miscommunication scenarios: an object-process methodology conceptual model. Artif Intell Med 62:153\u2013163. https:\/\/doi.org\/10.1016\/j.artmed.2014.10.006","journal-title":"Artif Intell Med"},{"key":"3866_CR11","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/2447976.2447993","volume":"56","author":"MG Jacob","year":"2013","unstructured":"Jacob MG, Li YT, Akingba GA, Wachs JP (2013) Collaboration with a robotic scrub nurse. Commun ACM 56:68\u201375. https:\/\/doi.org\/10.1145\/2447976.2447993","journal-title":"Commun ACM"},{"key":"3866_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-024-00581-0","author":"L Wagner","year":"2024","unstructured":"Wagner L, Jourdan S, Mayer L et al (2024) Robotic scrub nurse to anticipate surgical instruments based on real-time laparoscopic video analysis. Commun Med. https:\/\/doi.org\/10.1038\/s43856-024-00581-0","journal-title":"Commun Med"},{"key":"3866_CR13","doi-asserted-by":"publisher","DOI":"10.3182\/20080706-5-KR-1001.02314","author":"C P\u00e9rez","year":"2008","unstructured":"P\u00e9rez C, Morales R et al (2008) Autonomous surgical robot using visual servoing in the extended image plane. IFAC Proc Vol. https:\/\/doi.org\/10.3182\/20080706-5-KR-1001.02314","journal-title":"IFAC Proc Vol"},{"key":"3866_CR14","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1016\/j.robot.2012.01.005","volume":"60","author":"C Perez-Vidal","year":"2012","unstructured":"Perez-Vidal C, Carpintero E, Garcia-Aracil N et al (2012) Steps in the development of a robotic scrub nurse. Robot Auton Syst 60:1544\u20131557. https:\/\/doi.org\/10.1016\/j.robot.2012.01.005","journal-title":"Robot Auton Syst"},{"key":"3866_CR15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.19590","author":"S Li","year":"2024","unstructured":"Li S, Wang J, Dai R et al (2024) RoboNurse-VLA: robotic scrub nurse system based on a vision-language-action model. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2409.19590. arXiv:2409.19590","journal-title":"arXiv"},{"key":"3866_CR16","doi-asserted-by":"publisher","unstructured":"Kim MJ, Pertsch K, Karamcheti S et al (2024) OpenVLA: an open-source vision-language-action model. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2406.09246. arXiv:2406.09246","DOI":"10.48550\/arXiv.2406.09246"},{"key":"3866_CR17","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1038\/s41551-017-0132-7","volume":"1","author":"L Maier-Hein","year":"2017","unstructured":"Maier-Hein L, Vedula SS, Speidel S et al (2017) Surgical data science for next-generation interventions. Nat Biomed Eng 1:691\u2013696. https:\/\/doi.org\/10.1038\/s41551-017-0132-7","journal-title":"Nat Biomed Eng"},{"key":"3866_CR18","unstructured":"Black K, Brown N, Darpinian J et al (2025) \u03c00.5: a vision-language-action model with open-world generalization. Proceedings of The 9th Conference on Robot Learning, PMLR 305:17\u201340, 2025"},{"key":"3866_CR19","doi-asserted-by":"crossref","unstructured":"Driess D, Springenberg JT, Ichter B et al (2025) Knowledge insulating vision-language-action models: train fast, run fast, generalize better. arXiv:2505.23705v1","DOI":"10.52202\/085713-3439"},{"key":"3866_CR20","doi-asserted-by":"publisher","unstructured":"Kim JW, Zhao TZ, Schmidgall S et al (2024) Surgical Robot Transformer: imitation learning for surgical tasks. In: Conference on Robot Learning. https:\/\/doi.org\/10.48550\/arXiv.2407.12998","DOI":"10.48550\/arXiv.2407.12998"},{"key":"3866_CR21","doi-asserted-by":"publisher","unstructured":"Zhao TZ, Kumar V, Levine S, Finn C (2023) Learning fine-grained bimanual manipulation with low-cost hardware. In: Robotics: Science and Systems. https:\/\/doi.org\/10.15607\/RSS.2023.XIX.016","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"3866_CR22","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. Adv Neural Inf Process Syst. 30"},{"key":"3866_CR23","unstructured":"Radford A, Kim JW, Hallacy C et al (2021) Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. 139:8748\u20138763"},{"key":"3866_CR24","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac JB, Donahue J, Luc P et al (2022) Flamingo: a visual language model for few-shot learning. Adv Neural Inf Process Syst 35:23716\u201323736","journal-title":"Adv Neural Inf Process Syst"},{"key":"3866_CR25","unstructured":"Beyer L, Steiner A, Pinto AS et al (2024) PaliGemma: a versatile 3B vision-language model for transfer. arXiv. arXiv:2407.07726."},{"key":"3866_CR26","unstructured":"Radford A, Kim JW, Xu T, Brockman G, McLeavey C, Sutskever I (2023) Robust speech recognition via large-scale weak supervision. Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28492\u201328518, 2023"},{"key":"3866_CR27","unstructured":"Cartesia (2026) Sonic text-to-speech models: technical documentation"},{"key":"3866_CR28","doi-asserted-by":"crossref","unstructured":"Black K, Galliker MY, Levine S (2025) Real-time execution of action chunking flow policies. In: Advances in Neural Information Processing Systems. arXiv:2506.07339","DOI":"10.52202\/085713-1122"},{"key":"3866_CR29","unstructured":"Amin A, Aniceto R, Balakrishna A et al (2025) \u03c0*0.6: a VLA that learns from experience. arXiv. arXiv:2511.14759."},{"key":"3866_CR30","unstructured":"Xu C, Springenberg JT, Equi M, Amin A, Esmail A, Levine S, Ke L (2026) RL Token: bootstrapping online reinforcement learning with vision-language-action models. arXiv preprint"},{"key":"3866_CR31","unstructured":"Torne M, Pertsch K, Walke H et al (2026) MEM: multi-scale embodied memory for vision-language-action models. arXiv preprint"},{"key":"3866_CR32","doi-asserted-by":"crossref","unstructured":"Chi C, Feng S, Du Y et al (2023) Diffusion policy: visuomotor policy learning via action diffusion. In: Robotics: Science and Systems. arXiv:2303.04137","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"3866_CR33","doi-asserted-by":"publisher","unstructured":"Mazza L et al (2026) Supervised mixture-of-experts for surgical grasping and retraction. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2601.21971. arXiv:2601.21971","DOI":"10.48550\/arXiv.2601.21971"},{"key":"3866_CR34","doi-asserted-by":"crossref","unstructured":"Belkhale S, Ding T, Xiao T et al (2024) RT-H: action hierarchies using language. arXiv. arXiv:2403.01823.","DOI":"10.15607\/RSS.2024.XX.049"},{"key":"3866_CR35","unstructured":"Shi LX, Ichter B, Equi M et al (2025) Hi Robot: open-ended instruction following with hierarchical vision-language-action models. In: International Conference on Machine Learning. PMLR. 267"},{"key":"3866_CR36","doi-asserted-by":"publisher","unstructured":"Open X-E, Collaboration, Padalkar A, Pooley A et al (2024) Open X-Embodiment: Robotic learning datasets and RT-X models. In: IEEE International Conference on Robotics and Automation. https:\/\/doi.org\/10.48550\/arXiv.2310.08864","DOI":"10.48550\/arXiv.2310.08864"},{"key":"3866_CR37","doi-asserted-by":"publisher","unstructured":"Strabala K, Lee MK, Dragan A et al (2013) Toward seamless human-robot handovers. J Hum Robot Interact 2. https:\/\/doi.org\/10.5898\/JHRI.2.1.Strabala","DOI":"10.5898\/JHRI.2.1.Strabala"},{"key":"3866_CR38","doi-asserted-by":"publisher","first-page":"1855","DOI":"10.1109\/TRO.2021.3075365","volume":"37","author":"V Ortenzi","year":"2021","unstructured":"Ortenzi V, Cosgun A, Pardi T, Chan WP, Croft E, Kuli\u0107 D (2021) Object handovers: a review for robotics. IEEE Trans Robot 37:1855\u20131873. https:\/\/doi.org\/10.1109\/TRO.2021.3075365","journal-title":"IEEE Trans Robot"},{"key":"3866_CR39","doi-asserted-by":"publisher","DOI":"10.1007\/s00464-024-10958-w","author":"R Younis","year":"2024","unstructured":"Younis R, Yamlahi A, Bodenstedt S et al (2024) A surgical activity model of laparoscopic cholecystectomy for cooperation with collaborative robots. Surg Endosc. https:\/\/doi.org\/10.1007\/s00464-024-10958-w","journal-title":"Surg Endosc"},{"key":"3866_CR40","doi-asserted-by":"publisher","DOI":"10.3171\/2021.6.JNS21923","author":"DZ Khan","year":"2022","unstructured":"Khan DZ, Luengo I et al (2022) Automated operative workflow analysis of endoscopic pituitary surgery using machine learning. J Neurosurg. https:\/\/doi.org\/10.3171\/2021.6.JNS21923","journal-title":"J Neurosurg"},{"key":"3866_CR41","doi-asserted-by":"publisher","unstructured":"Zhang FX, Al Moubayed N, Shum HPH (2022) Towards graph representation learning based surgical workflow anticipation. In: IEEE-EMBS International Conference on Biomedical and Health Informatics. https:\/\/doi.org\/10.1109\/BHI56158.2022.9926801","DOI":"10.1109\/BHI56158.2022.9926801"},{"key":"3866_CR42","doi-asserted-by":"publisher","first-page":"eabj2908","DOI":"10.1126\/scirobotics.abj2908","volume":"7","author":"H Saeidi","year":"2022","unstructured":"Saeidi H, Opfermann JD, Kam M et al (2022) Autonomous robotic laparoscopic surgery for intestinal anastomosis. Sci Robot 7:eabj2908. https:\/\/doi.org\/10.1126\/scirobotics.abj2908","journal-title":"Sci Robot"},{"key":"3866_CR43","doi-asserted-by":"publisher","unstructured":"Chen WF, Yamamoto T, Dayicioglu D, Shaked A (2025) Robot-assisted lymph node-to-vein anastomosis using a next-generation microsurgical robot. Curr Oncol 32. https:\/\/doi.org\/10.3390\/curroncol32070377","DOI":"10.3390\/curroncol32070377"},{"key":"3866_CR44","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adt5254","author":"JW Kim","year":"2025","unstructured":"Kim JW, Chen JT, Hansen P et al (2025) SRT-H: a hierarchical framework for autonomous surgery via language-conditioned imitation learning. Sci Robot. https:\/\/doi.org\/10.1126\/scirobotics.adt5254","journal-title":"Sci Robot"},{"key":"3866_CR45","doi-asserted-by":"publisher","DOI":"10.20517\/ais.2024.32","author":"G Furnari","year":"2025","unstructured":"Furnari G, Secchi C, Ferraguti F (2025) Sequence-based imitation learning for surgical robot operations. Artif Intell Surg. https:\/\/doi.org\/10.20517\/ais.2024.32","journal-title":"Artif Intell Surg"}],"container-title":["Journal of Robotic Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11701-026-03866-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11701-026-03866-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11701-026-03866-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T03:25:46Z","timestamp":1787801146000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11701-026-03866-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,27]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3866"],"URL":"https:\/\/doi.org\/10.1007\/s11701-026-03866-9","relation":{},"ISSN":["1863-2491"],"issn-type":[{"value":"1863-2491","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,27]]},"assertion":[{"value":"21 July 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was conducted in a simulated operating-room environment and did not involve patients, human research participants, identifiable human data, animals, or biological specimens. Institutional review board approval and informed consent were therefore not required.","order":2,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"894"}}