Galaxea_R1_Lite_pour_powder

# Galaxea_R1_Lite_pour_powder ## Dataset Description This dataset uses an extended format based on LeRobot and is fully compatible with LeRobot. ## Task Preview <video src="videos/chunk-000/observation.images.cam_head_left_rgb/episode_000000.mp4" controls width="640"></video> [View Video Directly](videos/chunk-000/observation.images.cam_head_left_rgb/episode_000000.mp4) ### Overview - **Total Episodes:** 30 - **Total Frames:** 14053 - **FPS:** 30 - **Dataset Size:** 375.56 MB - **Robot Name:** `Galaxea_R1_Lite` - **End-Effector Type:** `two_finger_gripper` - **Teleoperation Type:** `Due to some reasons, this dataset temporarily cannot provide the teleoperation type information.` - **Sensors:** `cam_head_left_rgb`, `cam_head_right_rgb`, `cam_left_wrist_rgb`, `cam_right_wrist_rgb` - **Camera Information:** cam_head_left_rgb; cam_head_right_rgb; cam_left_wrist_rgb; cam_right_wrist_rgb - **Scene:** `ousehhold->kitchen` - **Objects:** `white_table(unknown)`, `plastic_cup(unknown)`, `green_dish(unknown)`, `pink_bowl(unknown)`, `powder(unknown)` - **Task Description:** use a gripper to pick up the cup and pour the powder into a bowl or tray. ### Primary Task Instruction > use a gripper to pick up the cup and pour the powder into a bowl or tray. ### Robot Configuration - **Robot Name:** `Galaxea_R1_Lite` - **Codebase Version:** `v2.1` - **End-Effector Type:** `two_finger_gripper` - **Teleoperation Type:** `Due to some reasons, this dataset temporarily cannot provide the teleoperation type information.` ## Scene and Objects ### Scene Type `ousehhold->kitchen` ### Objects - `white_table(unknown)` - `plastic_cup(unknown)` - `green_dish(unknown)` - `pink_bowl(unknown)` - `powder(unknown)` ## Task Descriptions - **Standardized Task Description:** `use a gripper to pick up the cup and pour the powder into a bowl or tray.` - **Operation Type:** `Due to some reasons, this dataset temporarily cannot provide the operation type information.` - **Environment Type:** `Due to some reasons, this dataset temporarily cannot provide the environment type information.` ### Sub-Tasks This dataset includes 16 distinct subtasks: 1. **Pour the powder into the green bowl with the left gripper** (Index: 0) 2. **Pour the powder into the pink bowl with the right gripper** (Index: 1) 3. **Pour the milk powder into the blue basin with left gripper** (Index: 2) 4. **Place the cup on the table with the right gripper** (Index: 3) 5. **Pick up blue cup filled with milk powder with left gripper** (Index: 4) 6. **Pour the milk powder into the pink bowl with left gripper** (Index: 5) 7. **Place blue cup with coffee powder on the table with left gripper** (Index: 6) 8. **End** (Index: 7) 9. **Grasp the glass of powder with the right gripper** (Index: 8) 10. **Grasp the glass of powder with the left gripper** (Index: 9) 11. **Place the cup on the table with the left gripper** (Index: 10) 12. **Place blue cup with milk powder on the table with left gripper** (Index: 11) 13. **Pour the powder into the pink bowl with the left gripper** (Index: 12) 14. **Pour the powder into the green bowl with the right gripper** (Index: 13) 15. **Left gripper** (Index: 14) 16. **null** (Index: 15) ### Atomic Actions - `grasp` - `pick` - `place` - `pour` ## Hardware and Sensors ### Sensors - `cam_head_left_rgb` - `cam_head_right_rgb` - `cam_left_wrist_rgb` - `cam_right_wrist_rgb` ### Camera Information - `cam_head_left_rgb`: dtype=video, shape=720x1280x3, resolution=1280x720, codec=av1, pix_fmt=yuv420p - `cam_head_right_rgb`: dtype=video, shape=720x1280x3, resolution=1280x720, codec=av1, pix_fmt=yuv420p - `cam_left_wrist_rgb`: dtype=video, shape=360x640x3, resolution=640x360, codec=av1, pix_fmt=yuv420p - `cam_right_wrist_rgb`: dtype=video, shape=360x640x3, resolution=640x360, codec=av1, pix_fmt=yuv420p ### Coordinate System - **Definition:** `right-hand-frame` ### Dimensions & Units - **Joint Rotation:** `radian` - **End-Effector Rotation:** `end_rotation_dim` - **End-Effector Translation:** `end_translation_dim` ## Dataset Statistics | Metric | Value | |--------|-------| | **Total Episodes** | 30 | | **Total Frames** | 14053 | | **Total Tasks** | 16 | | **Total Videos** | 120 | | **Total Chunks** | 1 | | **Chunk Size** | 1000 | | **FPS** | 30 | | **State Dimensions** | 14 | | **Action Dimensions** | 14 | | **Camera Views** | 4 | | **Dataset Size** | 375.56 MB | ## Data Splits The dataset is organized into the following splits: - **Training**: Episodes 0:29 ## Dataset Structure This dataset follows the LeRobot format and contains the following components: ### Data Files - **Videos**: Compressed video files containing RGB camera observations - **State Data**: Robot joint positions, velocities, and other state information - **Action Data**: Robot action commands and trajectories - **Metadata**: Episode metadata, timestamps, and annotations ### File Organization - **Data Path Pattern**: `data/chunk-{id}/episode_{id}.parquet` - **Video Path Pattern**: `videos/chunk-{id}/observation.images.cam_left_wrist_rgb/episode_{id}.mp{id}` - **Chunking**: Data is organized into 1 chunk(s) of size 1000 ### Data Structure (Tree) ``` Galaxea_R1_Lite_Galaxea_R1_Lite_pour_powder_qced_hardlink/ |-- annotations | |-- eef_acc_mag_annotation.jsonl | |-- eef_direction_annotation.jsonl | |-- eef_velocity_annotation.jsonl | |-- gripper_activity_annotation.jsonl | |-- gripper_mode_annotation.jsonl | |-- scene_annotations.jsonl | `-- subtask_annotations.jsonl |-- data | `-- chunk-000 | |-- episode_000000.parquet | |-- episode_000001.parquet | |-- episode_000002.parquet | |-- episode_000003.parquet | |-- episode_000004.parquet | |-- episode_000005.parquet | |-- episode_000006.parquet | |-- episode_000007.parquet | |-- episode_000008.parquet | |-- episode_000009.parquet | |-- episode_000010.parquet | `-- episode_000011.parquet | `-- ... (18 more entries) |-- meta | |-- episodes.jsonl | |-- episodes_stats.jsonl | |-- info.json | `-- tasks.jsonl |-- videos | `-- chunk-000 | |-- observation.images.cam_head_left_rgb | |-- observation.images.cam_head_right_rgb | |-- observation.images.cam_left_wrist_rgb | `-- observation.images.cam_right_wrist_rgb |-- info.yaml `-- README.md ``` ## Camera Views This dataset includes 4 camera views: `cam_head_left_rgb`, `cam_head_right_rgb`, `cam_left_wrist_rgb`, `cam_right_wrist_rgb`. ## Features (Full YAML) ```yaml observation.images.cam_head_left_rgb: dtype: video shape: - 720 - 1280 - 3 names: - height - width - channels info: video.height: 720 video.width: 1280 video.codec: av1 video.pix_fmt: yuv420p video.is_depth_map: false video.fps: 30 video.channels: 3 has_audio: false observation.images.cam_head_right_rgb: dtype: video shape: - 720 - 1280 - 3 names: - height - width - channels info: video.height: 720 video.width: 1280 video.codec: av1 video.pix_fmt: yuv420p video.is_depth_map: false video.fps: 30 video.channels: 3 has_audio: false observation.images.cam_left_wrist_rgb: dtype: video shape: - 360 - 640 - 3 names: - height - width - channels info: video.height: 360 video.width: 640 video.codec: av1 video.pix_fmt: yuv420p video.is_depth_map: false video.fps: 30 video.channels: 3 has_audio: false observation.images.cam_right_wrist_rgb: dtype: video shape: - 360 - 640 - 3 names: - height - width - channels info: video.height: 360 video.width: 640 video.codec: av1 video.pix_fmt: yuv420p video.is_depth_map: false video.fps: 30 video.channels: 3 has_audio: false observation.state: dtype: float32 shape: - 14 names: - left_arm_joint_1_rad - left_arm_joint_2_rad - left_arm_joint_3_rad - left_arm_joint_4_rad - left_arm_joint_5_rad - left_arm_joint_6_rad - right_arm_joint_1_rad - right_arm_joint_2_rad - right_arm_joint_3_rad - right_arm_joint_4_rad - right_arm_joint_5_rad - right_arm_joint_6_rad - left_gripper_open - right_gripper_open action: dtype: float32 shape: - 14 names: - left_arm_joint_1_rad - left_arm_joint_2_rad - left_arm_joint_3_rad - left_arm_joint_4_rad - left_arm_joint_5_rad - left_arm_joint_6_rad - right_arm_joint_1_rad - right_arm_joint_2_rad - right_arm_joint_3_rad - right_arm_joint_4_rad - right_arm_joint_5_rad - right_arm_joint_6_rad - left_gripper_open - right_gripper_open timestamp: dtype: float32 shape: - 1 names: null frame_index: dtype: int64 shape: - 1 names: null episode_index: dtype: int64 shape: - 1 names: null index: dtype: int64 shape: - 1 names: null task_index: dtype: int64 shape: - 1 names: null subtask_annotation: names: null shape: - 5 dtype: int32 scene_annotation: names: null shape: - 1 dtype: int32 eef_sim_pose_state: names: - left_eef_pos_x - left_eef_pos_y - left_eef_pos_z - left_eef_rot_x - left_eef_rot_y - left_eef_rot_z - right_eef_pos_x - right_eef_pos_y - right_eef_pos_z - right_eef_rot_x - right_eef_rot_y - right_eef_rot_z shape: - 12 dtype: float32 eef_sim_pose_action: names: - left_eef_pos_x - left_eef_pos_y - left_eef_pos_z - left_eef_rot_x - left_eef_rot_y - left_eef_rot_z - right_eef_pos_x - right_eef_pos_y - right_eef_pos_z - right_eef_rot_x - right_eef_rot_y - right_eef_rot_z shape: - 12 dtype: float32 eef_direction_state: names: - left_eef_direction - right_eef_direction shape: - 2 dtype: int32 eef_direction_action: names: - left_eef_direction - right_eef_direction shape: - 2 dtype: int32 eef_velocity_state: names: - left_eef_velocity - right_eef_velocity shape: - 2 dtype: int32 eef_velocity_action: names: - left_eef_velocity - right_eef_velocity shape: - 2 dtype: int32 eef_acc_mag_state: names: - left_eef_acc_mag - right_eef_acc_mag shape: - 2 dtype: int32 eef_acc_mag_action: names: - left_eef_acc_mag - right_eef_acc_mag shape: - 2 dtype: int32 gripper_open_scale_state: names: - left_gripper_open_scale - right_gripper_open_scale shape: - 2 dtype: float32 gripper_open_scale_action: names: - left_gripper_open_scale - right_gripper_open_scale shape: - 2 dtype: float32 gripper_mode_state: names: - left_gripper_mode - right_gripper_mode shape: - 2 dtype: int32 gripper_mode_action: names: - left_gripper_mode - right_gripper_mode shape: - 2 dtype: int32 gripper_activity_state: names: - left_gripper_activity - right_gripper_activity shape: - 2 dtype: int32 gripper_activity_action: names: - left_gripper_activity - right_gripper_activity shape: - 2 dtype: int32 ``` ## Available Annotations This dataset includes rich annotations to support diverse learning approaches: - `eef_acc_mag_annotation.jsonl` - `eef_direction_annotation.jsonl` - `eef_velocity_annotation.jsonl` - `gripper_activity_annotation.jsonl` - `gripper_mode_annotation.jsonl` - `scene_annotations.jsonl` - `subtask_annotations.jsonl` ## Dataset Tags - `RoboCOIN` - `LeRobot` ## Authors ### Contributors This dataset is contributed by:-RoboCOIN Team at Beijing Academy of Artificial Intelligence (BAAI) ### Annotators No annotator information available. ## Links - **Homepage:** [https://flagopen.github.io/RoboCOIN/](https://flagopen.github.io/RoboCOIN/) - **Paper:** [https://arxiv.org/abs/2511.17441](https://arxiv.org/abs/2511.17441) - **Repository:** [https://github.com/FlagOpen/RoboCOIN](https://github.com/FlagOpen/RoboCOIN) ## Contact and Support For questions, issues, or feedback regarding this dataset, please contact us. ### Support For technical support, please open an issue on our GitHub repository. ## License apache-2.0 ## Citation If you use this dataset in your research, please cite: ```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}, } ``` ### Additional References If you use this dataset, please also consider citing: LeRobot Framework: https://github.com/huggingface/lerobot ## Version Information Initial Release