{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:25:23Z","timestamp":1756992323681,"version":"3.28.0"},"reference-count":59,"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\/icra57147.2024.10610240","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"3108-3115","source":"Crossref","is-referenced-by-count":2,"title":["Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models"],"prefix":"10.1109","author":[{"given":"Yixuan","family":"Huang","sequence":"first","affiliation":[{"name":"University of Utah,Robotics Center and Kahlert School of Computing,Salt Lake City,UT,USA,84112"}]},{"given":"Jialin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Oregon State University"}]},{"given":"Chanho","family":"Kim","sequence":"additional","affiliation":[{"name":"Oregon State University"}]},{"given":"Pupul","family":"Pradhan","sequence":"additional","affiliation":[{"name":"University of Utah,Robotics Center and Kahlert School of Computing,Salt Lake City,UT,USA,84112"}]},{"given":"Bryan","family":"Chen","sequence":"additional","affiliation":[{"name":"Oregon State University"}]},{"given":"Li","family":"Fuxin","sequence":"additional","affiliation":[{"name":"Oregon State University"}]},{"given":"Tucker","family":"Hermans","sequence":"additional","affiliation":[{"name":"University of Utah,Robotics Center and Kahlert School of Computing,Salt Lake City,UT,USA,84112"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"61","article-title":"Sensor fusion in certainty grids for mobile robots","volume-title":"AI Magazine","volume":"9","author":"Moravec","year":"1988"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/027836499201100402"},{"issue":"1","key":"ref3","first-page":"191","article-title":"The spatial semantic hierarchy","volume-title":"Artificial Intelligence","volume":"119","author":"Kuipers","year":"2000"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/105971239900700102"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907318"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2522086"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2023.XIX.031","article-title":"StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objects","volume-title":"Robotics: Science and Systems","author":"Liu","year":"2023"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA48506.2021.9561548","article-title":"Hierarchical planning for long-horizon manipulation with geometric and symbolic scene graphs","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Zhu"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2022.3143518","article-title":"Efficient and interpretable robot manipulation with graph neural networks","volume-title":"IEEE Robotics and Automation Letters","author":"Lin","year":"2022"},{"article-title":"Relational learning for skill preconditions","volume-title":"Conference on Robot Learning (CoRL)","author":"Sharma","key":"ref12"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA46639.2022.9811931","article-title":"StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Liu"},{"key":"ref14","first-page":"6232","article-title":"6-dof grasping for target-driven object manipulation in clutter","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Murali"},{"article-title":"Predicting Stable Configurations for Semantic Placement of Novel Objects","volume-title":"Conference on Robot Learning (CoRL)","author":"Paxton","key":"ref15"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2021.XVII.072","article-title":"NeRP: Neural Rearrangement Planning for Unknown Objects","volume-title":"Proceedings of Robotics: Science and Systems","author":"Qureshi"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA48891.2023.10161204","article-title":"Planning for Multi-Object Manipulation with Graph Neural Network Relational Classifiers","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Huang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2024.3360956"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342381"},{"key":"ref20","article-title":"Multi-on: Benchmarking semantic map memory using multi-object navigation","author":"Wani","year":"2020","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16180"},{"key":"ref22","first-page":"16","article-title":"Self-supervised visual planning with temporal skip connections","volume":"12","author":"Ebert","year":"2017","journal-title":"CoRL"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812087"},{"article-title":"The 2019 davis challenge on vos: Unsupervised multi-object segmentation","year":"2019","author":"Caelles","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093285"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00691"},{"article-title":"Maximal cliques on multi-frame proposal graph for unsupervised video object segmentation","year":"2023","author":"Yuan","key":"ref28"},{"key":"ref29","first-page":"440","article-title":"Pddlstream: Integrating symbolic planners and blackbox samplers via optimistic adaptive planning","volume-title":"Proceedings of the International Conference on Automated Planning and Scheduling","volume":"30","author":"Garrett"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"4051","DOI":"10.1109\/ICRA40945.2020.9197468","article-title":"Towards practical multi-object manipulation using relational reinforcement learning","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Li","year":"2020"},{"article-title":"Learning 3d dynamic scene representations for robot manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Xu","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812057"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2009.4913187"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2009.5175519"},{"key":"ref37","first-page":"11","article-title":"Knowledge representation for cognition-and learning-enabled robot manipulation","author":"Be\u00dfler","year":"2018","journal-title":"CogRob@ KR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00057"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3301234"},{"article-title":"Predicting object interactions with behavior primitives: An application in stowing tasks","volume-title":"7th Annual Conference on Robot Learning","author":"Chen","key":"ref43"},{"article-title":"Structural concept learning via graph attention for multi-level rearrangement planning","volume-title":"7th Annual Conference on Robot Learning","author":"Kulshrestha","key":"ref44"},{"key":"ref45","first-page":"148","article-title":"Sornet: Spatial objectcentric representations for sequential manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Yuan"},{"key":"ref46","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"7th Annual Conference on Robot Learning","author":"Zitkovich","key":"ref47"},{"article-title":"Shelving, stacking, hanging: Relational pose diffusion for multi-modal rearrangement","volume-title":"7th Annual Conference on Robot Learning","author":"Simeonov","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"article-title":"Learning value functions with relational state representations for guiding task-and-motion planning","volume-title":"Conference on Robot Learning (CoRL)","author":"Kim","key":"ref50"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2020.XVI.003","article-title":"Deep visual reasoning: Learning to predict action sequences for task and motion planning from an initial scene image","volume-title":"Proceedings of Robotics: Science and Systems","author":"Driess"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196681"},{"key":"ref53","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA46639.2022.9811575","article-title":"Search-Based Task Planning with Learned Skill Effect Models for Lifelong Robotic Manipulation","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Liang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.061"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref57","first-page":"9621","article-title":"PointConv: Deep Convolutional Networks on 3D Point Clouds","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wu"},{"key":"ref58","first-page":"3898","article-title":"On positional and structural node features for graph neural networks on non-attributed graphs","volume-title":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","author":"Cui"},{"key":"ref59","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","volume-title":"Advances in Neural Information Processing Systems","author":"Makoviychuk","year":"2021"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","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\/10610240.pdf?arnumber=10610240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:20:30Z","timestamp":1723267230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610240\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610240","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}