{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:30:07Z","timestamp":1777656607340,"version":"3.51.4"},"reference-count":74,"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\/icra57147.2024.10610710","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"17529-17536","source":"Crossref","is-referenced-by-count":6,"title":["Point Cloud Models Improve Visual Robustness in Robotic Learners"],"prefix":"10.1109","author":[{"given":"Skand","family":"Peri","sequence":"first","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iain","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Utah"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanho","family":"Kim","sequence":"additional","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Fuxin","sequence":"additional","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tucker","family":"Hermans","sequence":"additional","affiliation":[{"name":"University of Utah"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Lee","sequence":"additional","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2894592"},{"key":"ref2","article-title":"End-to-end training of deep visuomotor policies","author":"Levine","year":"2016","journal-title":"JMLR"},{"key":"ref3","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"Conference on Robot Learning","author":"Nair"},{"key":"ref4","article-title":"On pre-training for visuo-motor control: Revisiting a learning-from-scratch baseline","volume-title":"International Conference on Machine Learning (ICML)","author":"Hansen"},{"key":"ref5","article-title":"Decomposing the generalization gap in imitation learning for visual robotic manipulation","author":"Xie","year":"2023","journal-title":"ArXiv"},{"key":"ref6","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"International Conference on Learning Representations","author":"Yarats"},{"key":"ref7","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","author":"Yarats","year":"2021","journal-title":"ArXiv"},{"key":"ref8","article-title":"Stabilizing deep q-learning with convnets and vision transformers under data augmentation","author":"Hansen","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref9","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic"},{"key":"ref10","article-title":"The unsurprising effectiveness of pre-trained vision models for control","volume-title":"International Conference on Machine Learning","author":"Parisi"},{"key":"ref11","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023","journal-title":"arXiv preprint arXiv:2301.04104"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00134"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning","volume-title":"AAAI Conference on Artificial Intelligence","author":"Hasselt"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref16","article-title":"Towards human-level bimanual dexterous manipulation with reinforcement learning","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Chen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160216"},{"key":"ref18","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019","journal-title":"arXiv preprint arXiv:1912.01603"},{"key":"ref19","article-title":"Model-based reinforcement learning for atari","volume-title":"International Conference on Learning Representations","author":"Kaiser"},{"key":"ref20","article-title":"Self-supervised 3d representation learning for robotics","volume-title":"ICRA2023 Workshop on Pretraining for Robotics (PT4R)","author":"Singh"},{"key":"ref21","article-title":"Language grounding with 3d objects","volume-title":"Conference on Robot Learning","author":"Thomason"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3259681"},{"key":"ref23","article-title":"Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds","volume-title":"Conference on Robot Learning (CoRL)","author":"Liu"},{"key":"ref24","article-title":"Dexpoint: Generalizable point cloud reinforcement learning for sim-to-real dexterous manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Qin"},{"key":"ref25","article-title":"On the efficacy of 3d point cloud reinforcement learning","author":"Ling","year":"2023","journal-title":"arXiv preprint arXiv:2306.06799"},{"key":"ref26","article-title":"Learning generalizable manipulation policies with object-centric 3d representations","volume-title":"Conference on Robot Learning","author":"Zhu"},{"key":"ref27","article-title":"Quantifying generalization in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Cobbe"},{"key":"ref28","article-title":"Observational overfitting in reinforcement learning","author":"Song","year":"2019","journal-title":"ArXiv"},{"key":"ref29","article-title":"Learning dynamics and generalization in reinforcement learning","author":"Lyle","year":"2022","journal-title":"ArXiv"},{"key":"ref30","article-title":"What is essential for unseen goal generalization of offline goal-conditioned rl?","author":"Yang","year":"2023","journal-title":"ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01002"},{"key":"ref33","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020","journal-title":"ArXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref35","article-title":"Masked visual pretraining for motor control","author":"Xiao","year":"2022","journal-title":"ArXiv"},{"key":"ref36","article-title":"Robonet: Large-scale multi-robot learning","volume-title":"Proceedings of the Conference on Robot Learning","author":"Dasari"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968114"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7689"},{"key":"ref41","article-title":"Point-based value iteration: An anytime algorithm for pomdps","author":"Pineau","year":"2003","journal-title":"Ijcai"},{"key":"ref42","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Chua"},{"key":"ref43","article-title":"Deepaveragers: offline reinforcement learning by solving derived non-parametric mdps","author":"Shrestha","year":"2021","journal-title":"ICLR"},{"key":"ref44","article-title":"Mastering atari with discrete world models","volume-title":"Internation Conference on Learning Representations","author":"Hafner"},{"key":"ref45","article-title":"Mastering the unsupervised reinforcement learning benchmark from pixels","volume-title":"40th International Conference on Machine Learning","author":"Rajeswar"},{"key":"ref46","article-title":"Temporal difference learning for model predictive control","volume-title":"International Conference on Machine Learning","author":"Hansen"},{"key":"ref47","article-title":"Modem: Accelerating visual model-based reinforcement learning with demonstrations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hansen"},{"key":"ref48","article-title":"Learning latent dynamics for planning from pixels","volume-title":"International Conference on machine learning","author":"Hafner"},{"key":"ref49","article-title":"Entity abstraction in visual model-based reinforcement learning","volume-title":"Conference on Robot Learning","author":"Veerapaneni"},{"key":"ref50","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv preprint arXiv:1803.10122"},{"key":"ref51","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018","journal-title":"arXiv"},{"key":"ref52","article-title":"Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids","author":"Li","year":"2019","journal-title":"ICLR"},{"key":"ref53","article-title":"Learning to simulate complex physics with graph networks","author":"Sanchez-Gonzalez","year":"2020","journal-title":"ICML"},{"key":"ref54","article-title":"Robocook: Long-horizon elasto-plastic object manipulation with diverse tools","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv:2306.14447"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.008"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161204"},{"key":"ref57","article-title":"Acting optimally in partially observable stochastic domains","volume-title":"AAAI Conference on Artificial Intelligence","author":"Cassandra"},{"key":"ref58","article-title":"Value prediction network","author":"Oh","year":"2017","journal-title":"NeurIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"ref60","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Mnih"},{"key":"ref61","article-title":"Improving regression performance with distributional losses","volume-title":"International Conference on Machine Learning","author":"Imani"},{"key":"ref62","article-title":"Highdimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"CoRR"},{"key":"ref63","article-title":"Maniskill2: A unified benchmark for generalizable manipulation skills","volume-title":"International Conference on Learning Representations","author":"Gu"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02030"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00028"},{"key":"ref67","article-title":"Maniskill: Generalizable manipulation skill benchmark with large-scale demonstrations","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Mu"},{"key":"ref68","article-title":"Dreamerv3-torch","volume-title":"Github","year":"2023"},{"key":"ref69","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref71","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"ArXiv"},{"key":"ref72","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref74","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Qi"}],"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\/10610710.pdf?arnumber=10610710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:21:40Z","timestamp":1723267300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610710","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}