{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:51:40Z","timestamp":1780581100772,"version":"3.54.1"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801678","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"2870-2877","source":"Crossref","is-referenced-by-count":24,"title":["RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effective"],"prefix":"10.1109","author":[{"given":"Chenxi","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Noematrix Intelligence Technology Ltd"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongjie","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao-Shu","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref2","first-page":"1761","article-title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","volume-title":"Conference on Robot Learning","author":"Chen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref7","first-page":"16931","article-title":"Reinforcement Learning with Neural Radiance Fields","volume":"35","author":"Driess","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611615"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610799"},{"key":"ref11","first-page":"3949","article-title":"Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation","volume-title":"Conference on Robot Learning","author":"Gervet"},{"key":"ref12","first-page":"694","article-title":"RVT: Robotic View Transformer for 3D Object Manipulation","volume-title":"Conference on Robot Learning","author":"Goyal"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref14","first-page":"175","article-title":"Instruction-Driven History-Aware Policies for Robotic Manipulations","volume-title":"Conference on Robot Learning","author":"Guhur"},{"key":"ref15","first-page":"3766","article-title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","volume-title":"Conference on Robot Learning","author":"Ha"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref21","first-page":"991","article-title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref22","first-page":"9902","article-title":"Planning with Diffusion for Flexible Behavior Synthesis","volume-title":"International Conference on Machine Learning","author":"Janner"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2016.xii.042"},{"key":"ref24","first-page":"23301","article-title":"LIV: Language-Image Representations and Rewards for Robotic Control","volume-title":"International Conference on Machine Learning","author":"Ma"},{"key":"ref25","article-title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","volume-title":"International Conference on Learning Representations","author":"Ma"},{"key":"ref26","article-title":"Where are We in the Search for an Artificial Visual Cortex for Embodied Intelligence?","volume-title":"ICRA 2023 Workshop on Pretraining for Robotics","author":"Majumdar"},{"key":"ref27","first-page":"1678","article-title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","volume-title":"Conference on Robot Learning","author":"Mandlekar"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref30","first-page":"892","article-title":"R3M: A Universal Visual Representation for Robot Manipulation","volume-title":"Conference on Robot Learning","author":"Nair"},{"key":"ref31","article-title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","volume-title":"IEEE International Conference on Robotics and Automation","author":"Padalkar"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.010"},{"key":"ref34","article-title":"ALVINN: An Autonomous Land Vehicle in a Neural Network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","first-page":"652","article-title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi"},{"key":"ref36","first-page":"23192","article-title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","volume":"35","author":"Qian","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","first-page":"416","article-title":"Real-World Robot Learning with Masked Visual Pre-Training","volume-title":"Conference on Robot Learning","author":"Radosavovic"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461076"},{"key":"ref39","article-title":"A Generalist Agent","author":"Reed","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.701"},{"key":"ref41","first-page":"405","article-title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","volume-title":"Conference on Robot Learning","author":"Shen"},{"key":"ref42","first-page":"785","article-title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref43","article-title":"Learning Structured Output Representation using Deep Conditional Generative Models","volume":"28","author":"Sohn","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","article-title":"Denoising Diffusion Implicit Models","volume-title":"The International Conference on Learning Representations","author":"Song"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref46","year":"2023","journal-title":"Octo: An Open-Source Generalist Robot Policy"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073608"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref51","first-page":"2323","article-title":"ChainedDiffuser: Unifying Trajectory Diffusion and Keypose Prediction for Robotic Manipulation","volume-title":"Conference on Robot Learning","author":"Xian","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00823"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref54","first-page":"284","article-title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","volume-title":"Conference on Robot Learning","author":"Ze"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref56","first-page":"3342","article-title":"A Universal Semantic-Geometric Representation for Robotic Manipulation","volume-title":"Proceedings of Machine Learning Research","volume":"229","author":"Zhang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.016"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref61","article-title":"Learning generalizable manipulation policies with object-centric 3d representations","volume-title":"7th Annual Conference on Robot Learning","author":"Zhu"},{"key":"ref62","first-page":"2165","article-title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","volume-title":"Conference on Robot Learning","author":"Zitkovich"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801678.pdf?arnumber=10801678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:07:58Z","timestamp":1735196878000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801678","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}