{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T08:51:42Z","timestamp":1773391902528,"version":"3.50.1"},"reference-count":86,"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\/iros60139.2025.11246368","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"8826-8833","source":"Crossref","is-referenced-by-count":2,"title":["Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Qi","family":"Wu","sequence":"first","affiliation":[{"name":"Stanford University"}]},{"given":"Zipeng","family":"Fu","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Xuxin","family":"Cheng","sequence":"additional","affiliation":[{"name":"UC San Diego"}]},{"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[{"name":"UC San Diego"}]},{"given":"Chelsea","family":"Finn","sequence":"additional","affiliation":[{"name":"Stanford University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794273"},{"key":"ref4","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Conference on Robot Learning (CoRL)","author":"Agarwal"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref6","article-title":"Development of wabot 1","author":"Kato","year":"1973","journal-title":"Biomechanism"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1998.677288"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS47582.2021.9555782"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.7210\/jrsj.30.372"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246947"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21560"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570360"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363867"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803402"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989550"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2006.886254"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635892"},{"key":"ref18","author":"Fu","year":"2024","journal-title":"Humanplus: Humanoid shadowing and imitation from humans"},{"key":"ref19","author":"Cheng","year":"2024","journal-title":"Open-television: Teleoperation with immersive active visual feedback"},{"key":"ref20","author":"He","year":"2024","journal-title":"Omnih2o: Universal and dexterous human-to-humanoid whole-body teleoperation and learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610977"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.047"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794449"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9993259"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2505910"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.094"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151396"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref31","article-title":"Continuous versatile jumping using learned action residuals","author":"Yang","year":"2023","journal-title":"L4DC"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610200"},{"key":"ref33","article-title":"Robot parkour learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Zhuang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981198"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160486"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3307008"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10146-0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143567"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561835"},{"key":"ref40","author":"Liu","year":"2024","journal-title":"Visual whole-body control for legged loco-manipulation"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611066"},{"key":"ref42","article-title":"UMI on legs: Making manipulation policies mobile with manipulation-centric whole-body controllers","author":"Ha","year":"2024"},{"key":"ref43","article-title":"Deep whole-body control: learning a unified policy for manipulation and locomotion","volume-title":"Conference on Robot Learning","author":"Fu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3336109\/mm5"},{"key":"ref45","article-title":"Roboduet: A framework affording mobile-manipulation and cross-embodiment","author":"Pan","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3335777"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801980"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161470"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802742"},{"key":"ref50","article-title":"Creative robot tool use with large language models","author":"Xu","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611307"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3610978.3641080"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref54","author":"Huang","year":"2023","journal-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models"},{"key":"ref55","author":"Driess","year":"2023","journal-title":"Palm-e: An embodied multimodal language model"},{"key":"ref56","volume-title":"Language to rewards for robotic skill synthesis","author":"Yu","year":"2023"},{"key":"ref57","author":"Yuan","year":"2024","journal-title":"Robopoint: A vision-language model for spatial affordance prediction for robotics"},{"key":"ref58","author":"Nasiriany","year":"2024","journal-title":"Pivot: Iterative visual prompting elic-its actionable knowledge for vlms"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127234"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"ref61","author":"Liu","year":"2024","journal-title":"Moka: Open-vocabulary robotic manipulation through mark-based visual prompting"},{"key":"ref62","author":"Du","year":"2023","journal-title":"Video language planning"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"ref65","author":"Duan","year":"2024","journal-title":"Manipulate-anything: Automating real-world robots using vision-language models"},{"key":"ref66","author":"Brohan","year":"2023","journal-title":"Rt-2: Vision- language-action models transfer web knowledge to robotic control"},{"key":"ref67","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Proceedings of the 5th Conference on Robot Learning (CoRL)","author":"Shridhar"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref69","author":"Kim","year":"2024","journal-title":"Openvla: An open-source vision-language-action model"},{"key":"ref70","author":"Zhen","year":"2024","journal-title":"3d-vla: A 3d vision-language-action generative world model"},{"key":"ref71","author":"Black","year":"2023","journal-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models"},{"key":"ref72","author":"Stone","year":"2023","journal-title":"Open-world object manipulation using pre-trained vision-language models"},{"key":"ref73","author":"Gu","year":"2023","journal-title":"Rt-trajectory: Robotic task generalization via hindsight trajectory sketches"},{"key":"ref74","author":"Sundaresan","year":"2024","journal-title":"Rt-sketch: Goal-conditioned imitation learning from hand-drawn sketches"},{"key":"ref75","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.049","article-title":"Rt-h: Action hierarchies using language","author":"Belkhale","year":"2024"},{"key":"ref76","article-title":"LM-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"6th Annual Conference on Robot Learning","author":"Shah"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref78","author":"Tang","year":"2023","journal-title":"Saytap: Language to quadrupedal locomotion"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3455788"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref82","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref84","author":"Zhang","year":"2023","journal-title":"Faster segment anything: Towards lightweight sam for mobile applications"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00304"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11245880"}],"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\/11246368.pdf?arnumber=11246368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:19:52Z","timestamp":1766132392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246368","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}