{"RequestId":"7452e4d2-2b6e-4ee5-a1dc-4b6aeba726a9","Code":200,"Message":"success","Data":{"isTop":null,"relatedPaperId":[227368],"nexa":"{}","Id":169304,"Namespace":"X-Humanoid","Name":"RoboMIND2.0","CreatedBy":"JayYoung0911","ChineseName":null,"License":"Apache License 2.0","Description":null,"Visibility":5,"Type":4,"Owner":"X-Humanoid","UserDefineTags":"Sim-to-Real,Embodied AI,Heterogeneous Robots,Long-horizon Tasks,Robotics-Dataset,Large-Scale-Robotics,Real-World-Data","Likes":27,"Downloads":375231,"Size":null,"ReadmeContent":"\n\n

\n \n \n \n

\n\n\n![RoboMIND2.0](assets/teaser.jpg)\n\n# \uD83C\uDF89\uD83C\uDF89 RoboMIND2.0 \uD83C\uDF89\uD83C\uDF89\n\n[中文](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0/file/view/master/README.zh.md?id=169304&status=1) | [English](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0/file/view/master/README.md?id=169304&status=1)\n\nRoboMIND2.0 has arrived. This release brings a major upgrade over RoboMIND.\n\nWe focus on complex data from **dual-arm manipulation** and **mobile manipulation** scenarios, which are highly demanded by the community. RoboMIND2.0 introduces many practical features to further advance robot learning and embodied intelligence research.\n\nWanna review RoboMIND1.0? Please check modelscope repo [RoboMIND MS](https://modelscope.cn/datasets/X-Humanoid/RoboMIND) or Huggingface repo [RoboMIND HF](https://huggingface.co/datasets/x-humanoid-robomind/RoboMIND).\n\n## Key Upgrades\n- RoboMIND2.0 scales up to **310K trajectories**, totaling over **1,000 hours** of data.\n- RoboMIND2.0 includes **12K tactile-enriched sequences**.\n- RoboMIND2.0 collects **20K mobile manipulation trajectories**.\n- RoboMIND2.0 covers **6 popular robotic embodiments**.\n\n## Embodiments Involved \uD83E\uDD16\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
\"Tienkung\"\"Tianyi\"\"AgileX\"
TienkungTianyiAgileX
\"Franka\"\"UR\"\"Ark\"
FrankaURArk
\n\n### Sub-repository Links\n\n- **Tienkung**\n - [X-Humanoid/RoboMIND2.0-Tienkung](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Tienkung)\n\n- **Tianyi**\n - [X-Humanoid/RoboMIND2.0-Tianyi](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Tianyi)\n\n- **Tianyi (Mobile)**\n - [X-Humanoid/RoboMIND2.0-Tianyi-mobile](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Tianyi-mobile)\n\n- **AgileX**\n - [X-Humanoid/RoboMIND2.0-Agilex](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Agilex)\n\n- **AgileX (Mobile)**\n - [X-Humanoid/RoboMIND2.0-Agilex-mobile](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Agilex-mobile)\n\n- **Franka**\n - [X-Humanoid/RoboMIND2.0-Franka-Part-1](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Franka-Part-1)\n - [X-Humanoid/RoboMIND2.0-Franka-Part-2](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Franka-Part-2)\n - [X-Humanoid/RoboMIND2.0-Franka-Part-3](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Franka-Part-3)\n - [X-Humanoid/RoboMIND2.0-Franka-Part-4](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Franka-Part-4)\n - [X-Humanoid/RoboMIND2.0-Franka-Part-5](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Franka-Part-5)\n\n- **UR**\n - [X-Humanoid/RoboMIND2.0-UR5](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-UR5)\n\n- **UR + DexHand**\n - [X-Humanoid/RoboMIND2.0-UR5-Dex](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-UR5-Dex)\n\n- **Ark**\n - [X-Humanoid/RoboMIND2.0-Ark](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Ark)\n\n- **Ark (Mobile)**\n - [X-Humanoid/RoboMIND2.0-Ark-mobile](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Ark-mobile)\n\n- **Simulation**\n - [X-Humanoid/RoboMIND2.0-Tienkung-sim](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Tienkung-sim)\n - [X-Humanoid/RoboMIND2.0-Franka-sim](https://modelscope.cn/datasets/X-Humanoid/RoboMIND2.0-Franka-sim)\n\n## Overall HDF5 Data Structure\n\nBelow is the unified HDF5 format used in RoboMIND2.0. Each dataset variant contains a subset of the following structure.\n\n```\n/\n├── metadata\n│ ├── language_instruction\n│ ├── data_type\n│ ├── data_format_version\n│ ├── collection_time\n│ ├── collector\n│ ├── sim_assets\n│ └── trajectory_length\n│\n├── camera_model\n│ ├── camera_top\n│ ├── camera_front\n│ ├── camera_left\n│ ├── camera_right\n│ ├── camera_head\n│ ├── camera_wrist_left\n│ └── camera_wrist_right\n│\n├── camera_color_resolution\n│ ├── camera_top\n│ ├── camera_front\n│ ├── camera_left\n│ ├── camera_right\n│ ├── camera_head\n│ ├── camera_wrist_left\n│ └── camera_wrist_right\n│\n├── camera_color_channel\n│ ├── camera_top\n│ ├── camera_front\n│ ├── camera_left\n│ ├── camera_right\n│ ├── camera_head\n│ ├── camera_wrist_left\n│ └── camera_wrist_right\n│\n├── camera_depth_resolution\n│ ├── camera_top\n│ ├── camera_front\n│ ├── camera_left\n│ ├── camera_right\n│ ├── camera_head\n│ ├── camera_wrist_left\n│ └── camera_wrist_right\n│\n├── camera_intrinsics\n│ ├── camera_top\n│ │ ├── matrix\n│ │ └── dist_coeffs\n│ ├── camera_front\n│ │ ├── matrix\n│ │ └── dist_coeffs\n│ ├── camera_left\n│ │ ├── matrix\n│ │ └── dist_coeffs\n│ ├── camera_right\n│ │ ├── matrix\n│ │ └── dist_coeffs\n│ ├── camera_head\n│ │ ├── matrix\n│ │ └── dist_coeffs\n│ ├── camera_wrist_left\n│ │ ├── matrix\n│ │ └── dist_coeffs\n│ └── camera_wrist_right\n│ ├── matrix\n│ └── dist_coeffs\n│\n├── camera_extrinsics\n│ ├── camera_top\n│ ├── camera_front\n│ ├── camera_left\n│ ├── camera_right\n│ ├── camera_head\n│ ├── camera_wrist_left\n│ └── camera_wrist_right\n│\n├── base_to_robot_transformation\n│ ├── base_to_robot_left\n│ ├── base_to_robot_right\n│ └── base_to_robot_single\n│\n├── force_model\n│ ├── force_left_end_effector\n│ ├── force_right_end_effector\n│ ├── force_left_arm_joints\n│ └── force_right_arm_joints\n│\n├── tactile_model\n│ ├── tactile_left\n│ └── tactile_right\n│\n├── master\n│ ├── arm_left_position_raw\n│ │ ├── timestamp\n│ │ ├── is_intervene\n│ │ └── data\n│ ├── arm_left_position_align\n│ ├── arm_right_position_raw\n│ ├── arm_right_position_align\n│ ├── arm_single_position_raw\n│ ├── arm_single_position_align\n│ ├── end_effector_left_position_raw\n│ ├── end_effector_left_position_align\n│ ├── end_effector_right_position_raw\n│ ├── end_effector_right_position_align\n│ ├── end_effector_single_position_raw\n│ ├── end_effector_single_position_align\n│ ├── end_effector_left_pose_raw\n│ ├── end_effector_left_pose_align\n│ ├── end_effector_right_pose_raw\n│ ├── end_effector_right_pose_align\n│ ├── end_effector_single_pose_raw\n│ ├── end_effector_single_pose_align\n│ ├── head_position_raw\n│ ├── head_position_align\n│ ├── waist_position_raw\n│ ├── waist_position_align\n│ ├── leg_left_position_raw\n│ ├── leg_left_position_align\n│ ├── leg_right_position_raw\n│ ├── leg_right_position_align\n│ ├── chassis_pose_raw\n│ ├── chassis_pose_align\n│ ├── chassis_twist_raw\n│ └── chassis_twist_align\n│\n├── puppet\n│ └── (same structure as master)\n│\n├── camera_observations\n│ ├── timestamp\n│ ├── is_intervene\n│ ├── color_images\n│ │ ├── camera_top\n│ │ ├── camera_front\n│ │ ├── camera_left\n│ │ ├── camera_right\n│ │ ├── camera_head\n│ │ ├── camera_wrist_left\n│ │ └── camera_wrist_right\n│ └── depth_images\n│ ├── camera_top\n│ ├── camera_front\n│ ├── camera_left\n│ ├── camera_right\n│ ├── camera_head\n│ ├── camera_wrist_left\n│ └── camera_wrist_right\n│\n├── force_observations\n│ ├── force_left_end_effector_raw\n│ ├── force_left_end_effector_align\n│ ├── force_right_end_effector_raw\n│ ├── force_right_end_effector_align\n│ ├── force_left_arm_joints_raw\n│ ├── force_left_arm_joints_align\n│ ├── force_right_arm_joints_raw\n│ └── force_right_arm_joints_align\n│\n└── tactile_observations\n ├── tactile_left_raw\n ├── tactile_left_align\n ├── tactile_right_raw\n └── tactile_right_align\n\n```\n\n## RoboMIND-Sim\nAdditionally, we have open-sourced a simulation environment built on Isaac Sim, which includes training datasets and standardized evaluation scripts. Researchers can leverage these resources out-of-the-box to rapidly conduct model performance evaluation and algorithm validation within the simulation.\n[RoboMIND-Sim](https://github.com/Open-X-Humanoid/RoboMIND-Sim) \n\n## Discussion:\n\"Tienkung\"\n\n## Citation\nIf you find this project helpful, please cite:\n```\n@misc{hou2025robomind20multimodalbimanual,\n title={RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied Intelligence}, \n author={Chengkai Hou and Kun Wu and Jiaming Liu and Zhengping Che and Di Wu and Fei Liao and Guangrun Li and Jingyang He and Qiuxuan Feng and Zhao Jin and Chenyang Gu and Zhuoyang Liu and Nuowei Han and Xiangju Mi and Yaoxu Lv and Yankai Fu and Gaole Dai and Langzhe Gu and Tao Li and Yuheng Zhang and Yixue Zhang and Xinhua Wang and Shichao Fan and Meng Li and Zhen Zhao and Ning Liu and Zhiyuan Xu and Pei Ren and Junjie Ji and Haonan Liu and Kuan Cheng and Shanghang Zhang and Jian Tang},\n year={2025},\n eprint={2512.24653},\n archivePrefix={arXiv},\n url={https://arxiv.org/abs/2512.24653}, \n}\n```","AlreadyStar":false,"GmtCreate":1767505653,"GmtModified":1791218405,"Tags":null,"Status":1,"FullName":"X-Humanoid","Organization":{"Id":2922,"GmtCreated":1762302783,"GmtModified":1762303353,"Name":"X-Humanoid","FullName":"X-Humanoid","Type":1,"Avatar":"https://resources.modelscope.cn/avatar/ffa840ba-c4f2-448e-8bdb-12aba7aa11cb.png","CreatedBy":"jydong01","GithubAddress":"https://github.com/Open-X-Humanoid","Description":"[\"root\",{},[\"p\",{},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"data-type\":\"leaf\"},\"欢迎来到北京人形机器人旗下开源组织-开工造物开源社区，让我们一起探索具身智能的无限可能。\"]]],[\"p\",{},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"data-type\":\"leaf\"},\"\"]]],[\"p\",{\"ind\":{\"left\":0},\"list\":{\"listId\":\"lz4h3m7ietb\",\"level\":0,\"isTaskList\":false,\"isOrdered\":false,\"listStyleType\":\"SCIR_ECIR_SREC\",\"symbolStyle\":{},\"listStyle\":{\"format\":\"bullet\",\"text\":\"●\",\"align\":\"left\"}}},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"data-type\":\"leaf\"},\"北京人形官网：https://x-humanoid.com/\"]]],[\"p\",{\"ind\":{\"left\":0},\"list\":{\"listId\":\"lz4h3m7ietb\",\"level\":0,\"isTaskList\":false,\"isOrdered\":false,\"listStyleType\":\"SCIR_ECIR_SREC\",\"symbolStyle\":{},\"listStyle\":{\"format\":\"bullet\",\"text\":\"●\",\"align\":\"left\"}}},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"data-type\":\"leaf\"},\"天工造物开源社区官网：https://opensource.x-humanoid-cloud.com/\"]]],[\"p\",{\"ind\":{\"left\":0},\"list\":{\"listId\":\"lz4h3m7ietb\",\"level\":0,\"isTaskList\":false,\"isOrdered\":false,\"listStyleType\":\"SCIR_ECIR_SREC\",\"symbolStyle\":{},\"listStyle\":{\"format\":\"bullet\",\"text\":\"●\",\"align\":\"left\"},\"extraData\":{},\"isChecked\":false,\"hideSymbol\":false}},[\"span\",{\"data-type\":\"text\"},[\"span\",{\"data-type\":\"leaf\"},\"联系我们：opensource@x-humanoid.com\"]]]]","DatasetCount":null},"UsedFor":null,"CertificationMark":0,"LastUpdatedTime":1784097913,"FromSite":"maas","SourcePlatform":null,"topIndex":null,"IsFlex":0,"StorageSize":51037175577,"RelateArxivId":["2512.24653"],"Avatar":null,"ProtectedMode":2,"ApprovalMode":1,"ApplyMeta":null,"NEXA":{"Source":null,"DatasetCover":null,"ScientificField":null,"SubScientificField":null,"Catalogues":[]}},"PageNumber":null,"PageSize":null,"TotalCount":null}