{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T22:54:47Z","timestamp":1769554487286,"version":"3.49.0"},"reference-count":47,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801782","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"10905-10912","source":"Crossref","is-referenced-by-count":6,"title":["ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robots"],"prefix":"10.1109","author":[{"given":"Zhixuan","family":"Xu","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Computer Science"}]},{"given":"Chongkai","family":"Gao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Computer Science"}]},{"given":"Zixuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University"}]},{"given":"Gang","family":"Yang","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Computer Science"}]},{"given":"Chenrui","family":"Tie","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering and Computer Science, Peking University"}]},{"given":"Haozhuo","family":"Zheng","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Mathematics"}]},{"given":"Haoyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Mechanical Engineering"}]},{"given":"Weikun","family":"Peng","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Computer Science"}]},{"given":"Debang","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Computer Science"}]},{"given":"Tianrun","family":"Hu","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Computer Science"}]},{"given":"Tianyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering"}]},{"given":"Zhouliang","family":"Yu","sequence":"additional","affiliation":[{"name":"Hongkong University of Science and Technology,Division of Emerging Interdisciplinary Areas"}]},{"given":"Lin","family":"Shao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Computer Science"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref2","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref3","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160591"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref6","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref7","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"Padalkar","year":"2023"},{"key":"ref8","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref9","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref11","article-title":"Foundation models in robotics: Applications, challenges, and the future","author":"Firoozi","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197331"},{"key":"ref14","first-page":"1916","article-title":"Mira: Mental imagery for robotic affordances","volume-title":"Proceedings of The 6th Conference on Robot Learning","volume":"205","author":"Lin"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561802"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811889"},{"key":"ref17","first-page":"618","article-title":"Learning generalizable dexterous manipulation from human grasp affordance","volume-title":"Conference on Robot Learning","author":"Wu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00674"},{"key":"ref19","article-title":"Vat-mart: Learning visual action trajectory proposals for manipulating 3d articulated objects","author":"Wu","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref22","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3527660"},{"key":"ref25","article-title":"Softmac: Differentiable soft body simulation with forecast-based contact model and two-way coupling with articulated rigid bodies and clothes","author":"Liu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2007.910774"},{"issue":"83","key":"ref29","first-page":"1","article-title":"CVXPY: A Python-embedded modeling language for convex optimization","volume":"17","author":"Diamond","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","article-title":"Jade: A differentiable physics engine for articulated rigid bodies with intersection-free frictional contact","author":"Yang","year":"2023"},{"key":"ref31","article-title":"Barrett bh8-282 3-fingered gripper","author":"Technology","year":"2019"},{"key":"ref32","article-title":"Leap hand: Low-cost, efficient, and anthropomorphic hand for robot learning","author":"Shaw","year":"2023","journal-title":"Robotics: Science and Systems (RSS)"},{"key":"ref33","article-title":"Barrett bh8-282 3-fingered gripper","year":"2019"},{"key":"ref34","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref35","article-title":"Multireact: Multimodal tools augmented reasoning-acting traces for embodied agent planning","volume-title":"6th Robot Learning Workshop NeurIPS 2023: Pretraining, Fine-Tuning, and Generalization with Large Scale Models","author":"Yu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225337"},{"key":"ref37","article-title":"Objaverse: A universe of annotated 3d objects","author":"Deitke","year":"2022"},{"key":"ref38","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00983"},{"key":"ref40","article-title":"Thingi10k: A dataset of 10,000 3d-printing models","author":"Zhou","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00684"},{"key":"ref42","article-title":"Manifoldplus: A robust and scalable watertight manifold surface generation method for triangle soups","author":"Huang","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530103"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01868"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258849"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00011"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"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\/10801782.pdf?arnumber=10801782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:38:54Z","timestamp":1736883534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801782","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}