# Episode 0 of ICRA-WBCD/IO-AI-SenseXperience-UMI

- format: LeRobot v3.0
- robot: sensexperience_umi
- robot family, as the index files it: Other robots
- kind, as the index files it: recording; other (inferred from the name)
- frames per second: 30
- frames in this episode: 130
- task: navigate to the silver shelf
- episodes in the dataset: 1,051
- licence: apache-2.0
- dataset page: https://huggingface.co/datasets/ICRA-WBCD/IO-AI-SenseXperience-UMI

LeRobot v3 keeps many episodes in one file. Download the data file and keep the rows whose episode_index is 0. Each video file holds several episodes back to back: cut it to episode_seconds. Or load it with LeRobot: LeRobotDataset('ICRA-WBCD/IO-AI-SenseXperience-UMI', episodes=[0]). The data file is 23 MB and holds many episodes; data_via_index gives only this one's rows.

Columns of the data file:

- `observation.pose.head`: float32, shape 7 (x, y, z, qx, qy, qz, qw)
- `observation.pose.left_gripper`: float32, shape 7 (x, y, z, qx, qy, qz, qw)
- `observation.pose.right_gripper`: float32, shape 7 (x, y, z, qx, qy, qz, qw)
- `observation.state`: float64, shape 4 (left_Left_Gripper_IntegratedPose_rad, left_Left_Gripper_IntegratedPose_dist, right_Right_Gripper_IntegratedPose_rad, right_Right_Gripper_IntegratedPose_dist)
- `timestamp`: float32, shape 1

| file | camera | size | this episode | link |
|---|---|---|---|---|
| data |  | 23.4 MB | rows where episode_index == 0 (global frames 0 to 129, 130 frames) | https://huggingface.co/datasets/ICRA-WBCD/IO-AI-SenseXperience-UMI/resolve/main/data/chunk-000/file-000.parquet |
| video | observation.images.camera_depth_head | 209.5 MB | seconds 0.0 to 4.333 | https://huggingface.co/datasets/ICRA-WBCD/IO-AI-SenseXperience-UMI/resolve/main/videos/observation.images.camera_depth_head/chunk-000/file-000.mp4 |
| video | observation.images.camera_gripper | 209.6 MB | seconds 0.0 to 4.333 | https://huggingface.co/datasets/ICRA-WBCD/IO-AI-SenseXperience-UMI/resolve/main/videos/observation.images.camera_gripper/chunk-000/file-000.mp4 |
| video | observation.images.camera_head_right | 208.0 MB | seconds 0.0 to 4.333 | https://huggingface.co/datasets/ICRA-WBCD/IO-AI-SenseXperience-UMI/resolve/main/videos/observation.images.camera_head_right/chunk-000/file-000.mp4 |
| video | observation.images.camera_head_left | 204.1 MB | seconds 0.0 to 4.333 | https://huggingface.co/datasets/ICRA-WBCD/IO-AI-SenseXperience-UMI/resolve/main/videos/observation.images.camera_head_left/chunk-000/file-000.mp4 |
| video | observation.images.camera_left_wrist | 207.2 MB | seconds 0.0 to 4.333 | https://huggingface.co/datasets/ICRA-WBCD/IO-AI-SenseXperience-UMI/resolve/main/videos/observation.images.camera_left_wrist/chunk-000/file-000.mp4 |
| video | observation.images.camera_right_wrist | 207.0 MB | seconds 0.0 to 4.333 | https://huggingface.co/datasets/ICRA-WBCD/IO-AI-SenseXperience-UMI/resolve/main/videos/observation.images.camera_right_wrist/chunk-000/file-000.mp4 |

If your network cannot reach Hugging Face, this site fetches the episode's rows for you, and only that episode's: https://datasets.gurasees.com/episode-data/ICRA-WBCD/IO-AI-SenseXperience-UMI?episode=0 (parquet) or https://datasets.gurasees.com/episode-data/ICRA-WBCD/IO-AI-SenseXperience-UMI?episode=0&format=json (JSON). Videos are not relayed.

- next episode: https://datasets.gurasees.com/episodes/ICRA-WBCD/IO-AI-SenseXperience-UMI.md?episode=1
- last episode: https://datasets.gurasees.com/episodes/ICRA-WBCD/IO-AI-SenseXperience-UMI.md?episode=1050