so-arm100
soarm100_dataThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "so100",
"total_episodes": 25,
"total_frames": 11178,
"total_tasks": 1,
"total_videos": 50,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:25"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Dangvi/soarm100_data.soarm100_data2This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "so100",
"total_episodes": 25,
"total_frames": 11150,
"total_tasks": 1,
"total_videos": 50,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:25"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Dangvi/soarm100_data2.so_arm_100_image_rnd_4This dataset was created using LeRobot.
Dataset Description
The SO ARM 100 test dataset series is an example dataset for testing purposes. It is a synthetic dataset from a
high-fidelity pick and place task recorded from an expert policy trained in IsaacLab. The dataset consists of image
observations, joint angle observations, and joint angle actions. There are five datasets in the series with varying
degrees of domain randomization, as shown below. In addition to the state… See the full description on the dataset page: https://huggingface.co/datasets/Nfiniteai/so_arm_100_image_rnd_4.SOARM100-169ep-joysoarm100_dataset
soarm100_dataset
This dataset was generated using a phospho starter pack.
This dataset contains a series of episodes recorded with a robot and multiple cameras. It can be directly used to train a policy using imitation learning. It's compatible with LeRobot and RLDS.
SOARM100-ep67joy