R1_Lite_tableware_cleaning
收藏R1_Lite_tableware_cleaning 数据集概述
📋 基本信息
- 数据集名称: R1_Lite_tableware_cleaning
- 机器人类型: R1_Lite
- 代码库版本: v2.1
- 末端执行器类型: two_finger_gripper
- 数据格式: 基于LeRobot的扩展格式,完全兼容LeRobot
- 许可证: apache-2.0
- 语言: 英语、中文
🎯 任务描述
主要任务
用含有洗涤剂的海绵擦拭餐具,然后将它们放回原处
子任务
包含25个不同的子任务:
- Abnormal
- End
- Grab the dish soap
- null
- Pick up a bowl and the sponge
- Place the bowl on the bowl
- Place the bowl on the plate
- Place the bowl on the table
- Place the chopsticks on the glass basin
- Place the dish soap on the table
- Place the plate on the plate
- Place the plate on the table
- Place the spoon in the glass basin
- Put down the sponge
- Rinse the bowl
- Rinse the chopsticks
- Rinse the plate
- Rinse the spoon
- Squeeze it onto the sponge
- Turn off the faucet
- Turn on the faucet
- Wash the bowl
- Wash the plate
- Wipe the bowl
- Wipe the plate
🏠 场景类型
- home
🤖 原子动作
- grasp
- pick
- place
📊 数据集统计
| 指标 | 数值 |
|---|---|
| 总情节数 | 102 |
| 总帧数 | 327254 |
| 总任务数 | 1 |
| 总视频数 | 306 |
| 总分块数 | 1 |
| 分块大小 | 1000 |
| 帧率 | 30 |
| 数据集大小 | 17.6GB |
🎥 相机视角
包含3个相机视角
🏷️ 可用标注
子任务标注
- 子任务分割: 细粒度的子任务分割和标注
场景标注
- 场景级描述: 语义场景分类和描述
末端执行器标注
- 方向: 机器人末端执行器的运动方向分类
- 速度: 操作过程中的速度大小分类
- 加速度: 运动分析的加速度大小分类
夹爪标注
- 夹爪模式: 夹爪开/关状态标注
- 夹爪活动: 活动状态分类(活动/非活动)
附加特征
- 末端执行器仿真位姿: 仿真空间中末端执行器的6D位姿信息(状态和动作均可用)
- 夹爪开合尺度: 连续的夹爪开合测量(状态和动作均可用)
📂 数据划分
- 训练集: 情节0:101
📁 数据集结构
文件组织
- 数据路径模式:
data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet - 视频路径模式:
videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4 - 分块: 数据组织为1个分块,每个分块大小1000
特征架构
视觉观察
- observation.images.cam_high_rgb: 视频(FPS: 30,编码: av1)
- observation.images.cam_left_wrist_rgb: 视频(FPS: 30,编码: av1)
- observation.images.cam_right_wrist_rgb: 视频(FPS: 30,编码: av1)
状态和动作
- observation.state: float32
- action: float32
时间信息
- timestamp: float32
- frame_index: int64
- episode_index: int64
- index: int64
- task_index: int64
标注
- subtask_annotation: int32
- scene_annotation: int32
运动特征
- eef_sim_pose_state: float32(12维)
- eef_sim_pose_action: float32(12维)
- eef_direction_state: int32(2维)
- eef_direction_action: int32(2维)
- eef_velocity_state: int32(2维)
- eef_velocity_action: int32(2维)
- eef_acc_mag_state: int32(2维)
- eef_acc_mag_action: int32(2维)
夹爪特征
- gripper_open_scale_state: float32(2维)
- gripper_open_scale_action: float32(2维)
- gripper_mode_state: int32(2维)
- gripper_mode_action: int32(2维)
- gripper_activity_state: int32(2维)
👥 作者
- 贡献者: RoboCOIN - RoboCOIN Team
🔗 相关链接
- 主页: https://flagopen.github.io/RoboCOIN/
- 论文: https://arxiv.org/abs/2511.17441
- 代码库: https://github.com/FlagOpen/RoboCOIN
- 项目页面: https://flagopen.github.io/RoboCOIN/
- 问题反馈: https://github.com/FlagOpen/RoboCOIN/issues
📚 引用
bibtex @article{robocoin, title={RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation}, author={Shihan Wu, Xuecheng Liu, Shaoxuan Xie, Pengwei Wang, Xinghang Li, Bowen Yang, Zhe Li, Kai Zhu, Hongyu Wu, Yiheng Liu, Zhaoye Long, Yue Wang, Chong Liu, Dihan Wang, Ziqiang Ni, Xiang Yang, You Liu, Ruoxuan Feng, Runtian Xu, Lei Zhang, Denghang Huang, Chenghao Jin, Anlan Yin, Xinlong Wang, Zhenguo Sun, Junkai Zhao, Mengfei Du, Mingyu Cao, Xiansheng Chen, Hongyang Cheng, Xiaojie Zhang, Yankai Fu, Ning Chen, Cheng Chi, Sixiang Chen, Huaihai Lyu, Xiaoshuai Hao, Yequan Wang, Bo Lei, Dong Liu, Xi Yang, Yance Jiao, Tengfei Pan, Yunyan Zhang, Songjing Wang, Ziqian Zhang, Xu Liu, Ji Zhang, Caowei Meng, Zhizheng Zhang, Jiyang Gao, Song Wang, Xiaokun Leng, Zhiqiang Xie, Zhenzhen Zhou, Peng Huang, Wu Yang, Yandong Guo, Yichao Zhu, Suibing Zheng, Hao Cheng, Xinmin Ding, Yang Yue, Huanqian Wang, Chi Chen, Jingrui Pang, YuXi Qian, Haoran Geng, Lianli Gao, Haiyuan Li, Bin Fang, Gao Huang, Yaodong Yang, Hao Dong, He Wang, Hang Zhao, Yadong Mu, Di Hu, Hao Zhao, Tiejun Huang, Shanghang Zhang, Yonghua Lin, Zhongyuan Wang and Guocai Yao}, journal={arXiv preprint arXiv:2511.17441}, url = {https://arxiv.org/abs/2511.17441}, year={2025} }
📌 版本信息
- v1.0.0 (2025-11): 初始发布




