{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:55:24Z","timestamp":1772906124278,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"HPC Resources provided by the Erlangen National HPC Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/lra.2026.3665444","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:08:52Z","timestamp":1771276132000},"page":"4785-4792","source":"Crossref","is-referenced-by-count":1,"title":["Augmented Reality for RObots (ARRO): Pointing Visuomotor Policies Towards Visual Robustness"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9248-581X","authenticated-orcid":false,"given":"Reihaneh","family":"Mirjalili","sequence":"first","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7098-7802","authenticated-orcid":false,"given":"Tobias","family":"J\u00fclg","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8279-7476","authenticated-orcid":false,"given":"Florian","family":"Walter","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5680-6500","authenticated-orcid":false,"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref5","first-page":"1199","article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"Proc. Conf. Robot Learn.","author":"Zhu","year":"2023"},{"key":"ref6","first-page":"2565","article-title":"Imitating task and motion planning with visuomotor transformers","volume-title":"Proc. Conf. Robot Learn.","author":"Dalal","year":"2023"},{"key":"ref7","first-page":"1723","article-title":"BridgeData V2: A dataset for robot learning at scale","volume-title":"Proc. Conf. Robot Learn.","author":"Walke","year":"2023"},{"key":"ref8","first-page":"4066","article-title":"Mobile ALOHA: Learning bimanual mobile manipulation using low-cost whole-body teleoperation","volume-title":"Proc. Conf. Robot Learn.","author":"Fu","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611293"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611615"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.152"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref15","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref17","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn.","author":"Kim","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611331"},{"key":"ref20","first-page":"3705","article-title":"Evaluating real-world robot manipulation policies in simulation","volume-title":"Proc. Conf. Robot Learn.","author":"Li","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"ref25","first-page":"4545","article-title":"Phantom: Training robots without robots using only human videos","volume-title":"Proc. Conf. Robot Learn.","author":"Lepert","year":"2025"},{"key":"ref26","first-page":"2955","article-title":"Polybot: Training one policy across robots while embracing variability","volume-title":"Proc. Conf. Robot Learn.","author":"Yang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461196"},{"key":"ref29","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Zeng","year":"2021"},{"key":"ref30","first-page":"894","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2022"},{"key":"ref31","first-page":"979","article-title":"Graph-structured visual imitation","volume-title":"Proc. Conf. Robot Learn.","author":"Sieb","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95459-8_9"},{"key":"ref33","first-page":"4573","article-title":"ReKep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2024"},{"key":"ref34","first-page":"37321","article-title":"PIVOT: Iterative visual prompting elicits actionable knowledge for VLMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nasiriany","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.062"},{"key":"ref36","first-page":"892","article-title":"R3M: A universal visual representation for robot manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Nair","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01709"},{"key":"ref39","article-title":"CACTI: A framework for scalable multi-task multi-scene visual imitation learning","volume-title":"Proc. CoRL 2022 Workshop Pre-training Robot Learn.","author":"Mandi","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.010"},{"key":"ref42","first-page":"2429","article-title":"Generative image as action models","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2025"},{"key":"ref43","first-page":"4314","article-title":"Enhancing visual domain robustness in behaviour cloning via saliency-guided augmentation","volume-title":"Proc. Conf. Robot Learn.","author":"Zhuang","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2894216"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.069"},{"key":"ref46","first-page":"3536","article-title":"SHADOW: Leveraging segmentation masks for cross-embodiment policy transfer","volume-title":"Proc. Conf. Robot Learn.","author":"Lepert","year":"2025"},{"key":"ref47","first-page":"209","article-title":"RoVi-Aug: Robot and viewpoint augmentation for cross-embodiment robot learning","volume-title":"Proc. Conf. Robot Learn.","author":"Chen","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref49","first-page":"41175","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi","year":"2025"},{"key":"ref50","article-title":"GPT-4 technical report","author":"Achiam","year":"2024"},{"key":"ref51","article-title":"Robot control stack: A lean ecosystem for robot learning at scale","author":"Jlg","year":"2025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref53","article-title":"ManiSkill2: A unified benchmark for generalizable manipulation skills","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2023"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11400564\/11397430.pdf?arnumber=11397430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:32:56Z","timestamp":1772692376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":53,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3665444","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}