{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:50:32Z","timestamp":1780444232805,"version":"3.54.1"},"reference-count":36,"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\/iros58592.2024.10802733","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"7359-7366","source":"Crossref","is-referenced-by-count":7,"title":["Open6DOR: Benchmarking Open-instruction 6-DoF Object Rearrangement and A VLM-based Approach"],"prefix":"10.1109","author":[{"given":"Yufei","family":"Ding","sequence":"first","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Geng","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyi","family":"Xu","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaomeng","family":"Fang","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiazhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songlin","family":"Wei","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyu","family":"Dai","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhizheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Rearrangement: A challenge for embodied ai","author":"Batra","year":"2020"},{"key":"ref2","author":"Brohan","year":"2023","journal-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917700714"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2448951"},{"key":"ref6","article-title":"A survey on evaluation of large language models","author":"Chang","year":"2023","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01263"},{"key":"ref8","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00447"},{"key":"ref10","volume-title":"Blender","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref13","article-title":"Sage: Bridging semantic and actionable parts for generalizable articulated-object manipulation under language instructions","author":"Geng","year":"2023"},{"key":"ref14","article-title":"Multi-skill mobile manipulation for object rearrangement","author":"Gu","year":"2022"},{"key":"ref15","article-title":"Rt-trajectory: Robotic task generalization via hindsight trajectory sketches","author":"Gu","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827450"},{"key":"ref17","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023"},{"key":"ref18","article-title":"Grounded decoding: Guiding text generation with grounded models for robot control","author":"Huang","year":"2023"},{"key":"ref19","article-title":"Vima: General robot manipulation with multimodal prompts","author":"Jiang","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611220"},{"key":"ref21","article-title":"Manipllm: Embodied multimodal large language model for object-centric robotic manipulation","author":"Li","year":"2023"},{"key":"ref22","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3129136"},{"key":"ref24","volume-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00519"},{"key":"ref26","year":"2023","journal-title":"OpenAI: Gpt-4 technical report"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref28","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref29","first-page":"308","article-title":"Fully autonomous real-world reinforcement learning with applications to mobile manipulation","volume-title":"Conference on Robot Learning","author":"Sun"},{"key":"ref30","article-title":"curobo: Parallelized collision-free minimum-jerk robot motion generation","author":"Sundaralingam","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01566"},{"key":"ref32","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","author":"Wu","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965078"},{"key":"ref34","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024"},{"key":"ref35","article-title":"Gamma: Graspability-aware mobile manipulation policy learning based on online grasping pose fusion","author":"Zhang","year":"2023"},{"key":"ref36","article-title":"Vlmbench: A compositional benchmark for vision-and-language manipulation","author":"Zheng","year":"2022"}],"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\/10802733.pdf?arnumber=10802733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:02:13Z","timestamp":1735196533000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802733","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}