{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:44:51Z","timestamp":1768520691327,"version":"3.49.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246336","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"14907-14914","source":"Crossref","is-referenced-by-count":1,"title":["Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Masaru","family":"Yajima","sequence":"first","affiliation":[{"name":"Institute of Science Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Ota","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric,Kanagawa,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asako","family":"Kanezaki","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rei","family":"Kawakami","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2018.07.020"},{"key":"ref2","article-title":"Compare contact model-based control and contact model-free learning: A survey of robotic peg-in-hole assembly strategies","author":"Xu","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102366"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.977187"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2021.100259"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161116"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341714"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(01)00161-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363806"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2015.1130172"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812312"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161491"},{"key":"ref14","first-page":"373","article-title":"Dense object nets: Learning dense visual object descriptors by and for robotic manipulation","volume-title":"CoRL","volume":"87","author":"Florence"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01878"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01794"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.29"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.077"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196733"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062315"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794226"},{"key":"ref24","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"CoRL","volume":"164","author":"Jang"},{"key":"ref25","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"CoRL","volume":"205","author":"Shridhar"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref27","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref30","article-title":"Rl-vlm-f: Reinforcement learning from vision language foundation model feedback","volume-title":"Proc. of ICML","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802423"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968072"},{"key":"ref33","first-page":"1696","article-title":"Fast robust peg-in-hole insertion with continuous visual servoing","volume-title":"CoRL","volume":"155","author":"Haugaard"},{"key":"ref34","article-title":"LLaVA-onevision: Easy visual task transfer","author":"Li","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref35","article-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1980.272026"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00146"},{"issue":"86","key":"ref38","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246336.pdf?arnumber=11246336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:11:01Z","timestamp":1765519861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246336","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}