{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T02:59:45Z","timestamp":1794538785365,"version":"4.9.1"},"reference-count":68,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611293","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T13:51:05Z","timestamp":1723125065000},"page":"4788-4795","source":"Crossref","is-referenced-by-count":94,"title":["RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking"],"prefix":"10.1109","author":[{"given":"Homanga","family":"Bharadhwaj","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,The Robotics Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jay","family":"Vakil","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,The Robotics Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohit","family":"Sharma","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,The Robotics Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,The Robotics Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubham","family":"Tulsiani","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,The Robotics Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vikash","family":"Kumar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,The Robotics Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"ref2","first-page":"885","article-title":"Robonet: Large-scale multi-robot learning","volume-title":"Conference on Robot Learning","author":"Dasari"},{"key":"ref3","first-page":"879","article-title":"Roboturk: A crowdsourcing platform for robotic skill learning through imitation","volume-title":"Conference on Robot Learning","author":"Mandlekar"},{"key":"ref4","article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","author":"Kalashnikov","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref6","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref7","article-title":"Qt- opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989249"},{"key":"ref10","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Conference on robot learning","author":"Lynch"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793952"},{"key":"ref12","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on robot learning","author":"Yu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref15","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref16","article-title":"A generalist agent","author":"Reed","year":"2022"},{"key":"ref17","article-title":"Vima: General robot manip- ulation with multimodal prompts","author":"Jiang","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref19","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architec- tures","author":"Espeholt","year":"2018"},{"key":"ref20","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"International Conference on Machine Learning","author":"Sodhani"},{"key":"ref21","article-title":"Model-based reinforcement learning for atari","author":"Kaiser","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref23","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160216"},{"key":"ref25","article-title":"Robocat: A self-improving foundation agent for robotic manipulation","author":"Bousmalis","year":"2023"},{"key":"ref26","article-title":"V-mpo: On-policy maximum a posteriori policy optimization for discrete and continuous control","author":"Song","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref28","article-title":"Cacti: A framework for scalable multi-task multi-scene visual imitation learning","author":"Mandi","year":"2022"},{"key":"ref29","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","first-page":"1678","article-title":"What matters in learning from offline human demonstrations for robot manipula- tion","volume-title":"Conference on Robot Learning","author":"Mandlekar"},{"key":"ref31","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref32","article-title":"Rb2: Robotic manipulation benchmarking with a twist","author":"Dasari","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref35","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref36","article-title":"The unsurprising effectiveness of pre-trained vision models for control","author":"Parisi","year":"2022"},{"key":"ref37","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","author":"Majumdar","year":"2023"},{"key":"ref38","article-title":"Rrl: Resnet as representation for reinforcement learning","author":"Shah","year":"2021"},{"key":"ref39","article-title":"Lossless adaptation of pretrained vision models for robotic manipulation","author":"Sharma","year":"2023"},{"key":"ref40","article-title":"On pre-training for visuo-motor control: Revisiting a learning-from-scratch baseline","author":"Hansen","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7979"},{"key":"ref42","article-title":"Language conditioned imitation learning over unstructured data","author":"Lynch","year":"2020"},{"key":"ref43","first-page":"13 139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume":"33","author":"Stepputtis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning","author":"Brohan"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460857"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161288"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.002"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"ref49","first-page":"654","article-title":"Videodex: Learning dexterity from internet videos","volume-title":"Conference on Robot Learning","author":"Shaw"},{"key":"ref50","article-title":"Zero-shot robot manipulation from passive human videos","author":"Bharadhwaj","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01117"},{"key":"ref54","article-title":"Dall-e-bot: Introducing web-scale diffusion models to robotics","author":"Kapelyukh","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.010"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"ref57","article-title":"Simple open-vocabulary object detection with vision transformers","author":"Minderer","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160846"},{"key":"ref59","first-page":"16","article-title":"Self-supervised visual planning with temporal skip connections","volume":"12","author":"Ebert","year":"2017","journal-title":"CoRL"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref61","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref64","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref65","article-title":"Clip on wheels: Zero-shot object navigation as object localization and exploration","author":"Gadre","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2021.3138382"},{"key":"ref67","article-title":"Behavior transformers: Cloning k modes with one stone","author":"Shafiullah","year":"2022"},{"key":"ref68","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611293.pdf?arnumber=10611293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T00:08:03Z","timestamp":1723334883000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611293","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}