{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T13:52:44Z","timestamp":1758981164528,"version":"3.44.0"},"reference-count":52,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128261","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"4753-4760","source":"Crossref","is-referenced-by-count":1,"title":["Sketch-MoMa: Teleoperation for Mobile Manipulator via Interpretation of Hand-Drawn Sketches"],"prefix":"10.1109","author":[{"given":"Kosei","family":"Tanada","sequence":"first","affiliation":[{"name":"Toyota Motor Corporation,Department of Advanced Robotics Research,Toyota,Aichi,Japan"}]},{"given":"Yuka","family":"Iwanaga","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation,Department of Advanced Robotics Research,Toyota,Aichi,Japan"}]},{"given":"Masayoshi","family":"Tsuchinaga","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation,Department of Advanced Robotics Research,Toyota,Aichi,Japan"}]},{"given":"Yuji","family":"Nakamura","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation,Department of Advanced Robotics Research,Toyota,Aichi,Japan"}]},{"given":"Takemitsu","family":"Mori","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation,Department of Advanced Robotics Research,Toyota,Aichi,Japan"}]},{"given":"Remi","family":"Sakai","sequence":"additional","affiliation":[{"name":"Aichi Institute of Technology,Faculty of Information Science,Toyota,Aichi,Japan"}]},{"given":"Takashi","family":"Yamamoto","sequence":"additional","affiliation":[{"name":"Aichi Institute of Technology,Faculty of Information Science,Toyota,Aichi,Japan"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ARSO.2013.6705520"},{"volume-title":"Proc. of the 8th Annual Conference on Robot Learning","author":"Cheng","article-title":"Open-television: Teleoperation with immersive active visual feedback","key":"ref2"},{"volume-title":"Proc. of the 8th Annual Conference on Robot Learning","author":"Iyer","article-title":"OPEN TEACH: A versatile teleoperation system for robotic manipulation","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.3390\/s21082667"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/RO-MAN50785.2021.9515511"},{"key":"ref6","first-page":"371","article-title":"A comparison of remote robot teleoperation interfaces for general object manipulation","volume-title":"Proc. of the ACM\/IEEE International Conference on Human-Robot Interaction","author":"Kent"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICRA46639.2022.9812372"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/JPROC.2011.2179772"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1145\/3568162.3576991"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICRA57147.2024.10611462"},{"key":"ref11","article-title":"Rt-sketch: Goal-conditioned imitation learning from hand-drawn sketches","volume-title":"Proc. of the RSS 2024 Workshop: Data Generation for Robotics","author":"Sundaresan","year":"2024"},{"volume-title":"Proc. of the The Twelfth International Conference on Learning Representations","author":"Gu","article-title":"Rt-trajectory: Robotic task generalization via hindsight trajectory sketches","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ACCESS.2023.3245833"},{"volume-title":"Proc. of the 2nd Workshop on Mobile Manipulation and Embodied Intelligence at ICRA 2024","author":"Dass","article-title":"Telemoma: A modular and versatile teleoperation system for mobile manipulation","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.15607\/RSS.2024.XX.043"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/LRA.2021.3064500"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/IROS58592.2024.10801581"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.15607\/RSS.2023.XIX.016"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.15607\/RSS.2023.XIX.015"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/2157689.2157691"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1177\/0278364919888565"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICRA.2016.7487453"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ECMR.2015.7324188"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1145\/3411764.3445110"},{"volume-title":"Airways: Optimization-based planning of quadrotor trajectories according to high-level user goals","year":"2019","author":"Gebhardt","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1145\/1518701.1518733"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1145\/288392.288599"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICRA57147.2024.10611349"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/IROS58592.2024.10801371"},{"key":"ref30","article-title":"Toward general-purpose robots via foundation models: A survey and meta-analysis","volume-title":"Tech. Rep.","author":"Hu","year":"2023"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1177\/02783649241281508"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1080\/01691864.2024.2408593"},{"volume-title":"Proc. of the 7th Annual Conference on Robot Learning","author":"Zitkovich","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","key":"ref33"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/ICRA57147.2024.10611477"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.15607\/RSS.2023.XIX.025"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.15607\/rss.2024.xx.096"},{"volume-title":"Proc. of the 7th Annual Conference on Robot Learning","author":"Rana","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning","key":"ref37"},{"volume-title":"Proc. of the 7th Annual Conference on Robot Learning","author":"Huang","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","key":"ref38"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/ICRA48891.2023.10160591"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.15607\/RSS.2024.XX.062"},{"volume-title":"Proc. of the Forty-first International Conference on Machine Learning","author":"Nasiriany","article-title":"Pivot: Iterative visual prompting elicits action-able knowledge for vlms","key":"ref41"},{"key":"ref42","article-title":"Fast segment anything","volume-title":"Tech. Rep.","author":"Zhao","year":"2023"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/ICCV51070.2023.00065"},{"volume-title":"Proc. of the 6th Annual Conference on Robot Learning","author":"Ma","article-title":"Towards scale balanced 6-dof grasp detection in cluttered scenes","key":"ref44"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1186\/s40648-019-0132-3"},{"key":"ref46","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","volume-title":"Tech. Rep.","author":"Yang","year":"2023"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1080\/01691864.2022.2109428"},{"volume-title":"Tech. Rep.","year":"2023","article-title":"Gpt-4v(ision) system card","key":"ref48"},{"volume-title":"Tech. Rep.","year":"2023","article-title":"Gemini: A family of highly capable multi-modal models","key":"ref49"},{"volume-title":"Tech. Rep.","year":"2023","article-title":"Gpt-4 technical report","key":"ref50"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1016\/S0166-4115(08)62386-9"},{"issue":"140","key":"ref52","first-page":"55","article-title":"A technique for the measurement of attitudes","volume":"22","author":"Likert","year":"1932","journal-title":"Archives of Psychology"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11128261.pdf?arnumber=11128261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:17:17Z","timestamp":1756880237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128261\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128261","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}