datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
eval_bi_so101_round1_4camThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "bi_so_follower",
"total_episodes": 601,
"total_frames": 637163,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:601"},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Zekai-Chen/eval_bi_so101_round1_4cam.so101-chess-grasp-approach
SO-101 chess research captures
Versioned capture artifacts for the SO-101 chess project.
The current encoder-grasp schema contains six-joint actions, six-joint encoder observations, synchronized 1280x720 wrist and nearest-overhead video, timestamps, frame/episode indices, and task labels. Capture bundles include accepted and negative grasp approaches, legacy placement returns, and the newer positive/negative centered-placement collections. Centered placement journals add… See the full description on the dataset page: https://huggingface.co/datasets/Stefanobraghetto/so101-chess-grasp-approach.so101_wnThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_follower",
"total_episodes": 133,
"total_frames": 103433,
"total_tasks": 13,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:133"},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/0xNOY/so101_wn.so101_wn_geneval_so101_bimanual_total_0This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "bi_so_follower",
"total_episodes": 178,
"total_frames": 117505,
"total_tasks": 7,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:178"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Qiu-Xinchuan/eval_so101_bimanual_total_0.so101-chess-stateeval_snvla_dn_so101_wn_augThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_follower",
"total_episodes": 30,
"total_frames": 22215,
"total_tasks": 3,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:30"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/0xNOY/eval_snvla_dn_so101_wn_aug.SO101-StackBlock_Ours_60epiThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_follower",
"total_episodes": 60,
"total_frames": 51813,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 10,
"splits": {
"train": "0:60"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/HyeonseokE/SO101-StackBlock_Ours_60epi.eval_snvla_so101_wn_augThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_follower",
"total_episodes": 30,
"total_frames": 21683,
"total_tasks": 3,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:30"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/0xNOY/eval_snvla_so101_wn_aug.so101-egg-transport-act-v0
SO-101 raw egg transport: teleoperation and first ACT rollout
This dataset documents a single-arm Hiwonder SO-ARM101 task: pick up a raw egg
from a fixed pickup area and gently place it in an unheated frying pan.
Contents
Root dataset: 25 human teleoperation demonstrations in LeRobot v3 format.
evaluations/autonomous_success_001/ through
evaluations/autonomous_success_007/: seven saved autonomous-success
rollouts of an ACT policy trained from the 25… See the full description on the dataset page: https://huggingface.co/datasets/NOJIMA21/so101-egg-transport-act-v0.so101-leader-urdf
SO-101 leader URDF
Open so101_leader_new_calib.urdf with the adjacent assets/ directory intact. All mesh paths are relative; all mesh coordinates are in metres. This is a geometry/kinematics conversion of the supplied follower URDF, with a provisional trigger calibration.
Changes
Preserved the original base, shoulder, upper arm, lower arm, wrist, motor meshes, and the five arm joint origins, axes, limits and transmissions.
Replaced the fixed follower gripper body… See the full description on the dataset page: https://huggingface.co/datasets/cetiennec/so101-leader-urdf.SO101-ma_stack_RGBblock_on_bluedish_30fpsThis dataset was created using LeRobot.
Dataset Description
SO-101 robot dataset collected with the MA autonomous forward/reset pipeline. The task is to stack red, green, and blue RGB blocks on the blue dish from bottom to top. The dataset contains 100 successful episodes at 30 FPS with top and left-wrist RGB camera streams, robot state/action features, end-effector pose, gripper state, and skill/subtask annotations.
Homepage: https://huggingface.co/CoRL2026-CSI
Paper:… See the full description on the dataset page: https://huggingface.co/datasets/Cache-SCA/SO101-ma_stack_RGBblock_on_bluedish_30fps.so101_pick_cubeDexdata format SO-101 dataset
Dataset Structure
so101_pick_cube
├── videos
│ ├── so101_20260630_103330_filtered
│ │ ├── file-000.mp4_top.mp4
│ │ └── file-000.mp4_wrist.mp4
│ └── ...
└── jsonl
├── episode_00000.jsonl
├── episode_00001.jsonl
└── ...
Task Description
This dataset contains robot manipulation demonstrations for the task:
Task: Pick the cube and place it in the plate
Object variations:… See the full description on the dataset page: https://huggingface.co/datasets/Dexmal/so101_pick_cube.so101_car_pick_and_placeThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_follower",
"total_episodes": 98,
"total_frames": 67279,
"total_tasks": 2,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 500,
"fps": 30,
"splits": {
"train": "0:98"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/jonathm126/so101_car_pick_and_place.SO101-StackBlock_Ours_100epi
SO101-StackBlock_Ours_100epi
100 successful demonstrations of stacking RED → GREEN → BLUE blocks on a blue dish, collected on a single LeRobot SO-101 arm. Recorded via the AutoDataCollector pipeline (Phase 1 buffer-aware seeding + Phase 2 MI-based useful-OOD acquisition).
Task
Stack red, green, and blue blocks on the blue dish from bottom to top.
Per episode:
Pick red block → place on blue dish
Re-detect → pick green block → stack on red
Re-detect → pick blue block →… See the full description on the dataset page: https://huggingface.co/datasets/CoRL2026-CSI/SO101-StackBlock_Ours_100epi.bi_so101_fold_10inch_4camThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "bi_so_follower",
"total_episodes": 603,
"total_frames": 541612,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:603"},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/deepreach/bi_so101_fold_10inch_4cam.bi_so101_fold_towel_4camThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "bi_so_follower",
"total_episodes": 603,
"total_frames": 541612,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:603"},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Zekai-Chen/bi_so101_fold_towel_4cam.SO101-StackBlock_Ours_80epiThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_follower",
"total_episodes": 80,
"total_frames": 69000,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 10,
"splits": {
"train": "0:80"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/HyeonseokE/SO101-StackBlock_Ours_80epi.eval_so101_pick_place_bottle_v0This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so_follower",
"total_episodes": 67,
"total_frames": 31113,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:67"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Elvinky/eval_so101_pick_place_bottle_v0.so101-test-leader-v1This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_physical_wrapped",
"total_episodes": 0,
"total_frames": 0,
"total_tasks": 0,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/bendca61/so101-test-leader-v1.SO101-FoldTowel_Ours_20epiThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_follower",
"total_episodes": 20,
"total_frames": 15107,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 10,
"splits": {
"train": "0:20"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/HyeonseokE/SO101-FoldTowel_Ours_20epi.SO101-cap_stack_RGBblock_on_bluedish_10fps
SO101 CAP Stack RGB Blocks on Blue Dish
This dataset contains 100 LeRobot v3.0 demonstration episodes for an SO101 follower robot. The task is: Stack red, green, and blue blocks on the blue dish from bottom to top. The dataset was collected at 10 Hz and includes paired top-view and wrist-view RGB videos, robot state/action trajectories, and CAP skill annotations.
Dataset Details
Field
Value
Repository… See the full description on the dataset page: https://huggingface.co/datasets/CoRL2026-CSI/SO101-cap_stack_RGBblock_on_bluedish_10fps.SO101-FoldTowel_Ours_80epiThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_follower",
"total_episodes": 80,
"total_frames": 59857,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 10,
"splits": {
"train": "0:80"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/HyeonseokE/SO101-FoldTowel_Ours_80epi.MimicAnno-so101-26B-runs
SO101 annotations — Gemma-4 26B (QLoRA) MimicAnno run
20 episodes from the SO101 dataset, automatically segmented and
phase-labeled by the MimicAnno
pipeline using the 26B Gemma-4 QLoRA adapter
(https://huggingface.co/Gayagaya/gem4_26B_adapter).
Contents (per episode dir)
file
description
video.mp4
source episode video
signals.json
per-frame hand/object signals (schema v3)
boundaries.json
segment boundaries
annotation.jsonVLM phase labels + tools… See the full description on the dataset page: https://huggingface.co/datasets/Gayagaya/MimicAnno-so101-26B-runs.so101_towel_3cam_rl_0This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "bi_so_follower",
"total_episodes": 150,
"total_frames": 211560,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:150"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Qiu-Xinchuan/so101_towel_3cam_rl_0.molmoact2-so101-zero-shot-eval
MolmoAct2 SO-101 Zero-Shot Evaluation Traces
This repository contains evaluation traces from running allenai/MolmoAct2-SO100_101 zero-shot on an SO-101 robot arm using the official LeRobot MolmoAct2 integration plus a remote async inference setup.
This is an evaluation artifact, not a training dataset or model checkpoint. The model under test is AllenAI's released MolmoAct2 SO-100/SO-101 checkpoint.
Summary
MolmoAct2 remote inference was successfully brought up on… See the full description on the dataset page: https://huggingface.co/datasets/abdul004/molmoact2-so101-zero-shot-eval.SO101-OpenDrawer_Ours_100epiThis dataset was created using LeRobot.
Dataset Description
A robot manipulation dataset for imitation learning, compatible with LeRobot v3.0 format.
Robot Type: so101_follower
Total Episodes: 100
Total Frames: 28003
FPS: 10
Codebase Version: v3.0
Features
Feature
Shape
Type
observation.state
[6]
float32
action
[6]
float32
observation.images.top
[480, 640, 3]
video
observation.images.left_wrist
[480, 640, 3]
video
Dataset Structure… See the full description on the dataset page: https://huggingface.co/datasets/CoRL2026-CSI/SO101-OpenDrawer_Ours_100epi.so101_towel_3cam_rl_1This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "bi_so_follower",
"total_episodes": 100,
"total_frames": 150123,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:100"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Qiu-Xinchuan/so101_towel_3cam_rl_1.SO101-ma_sort_RGBblock_to_matchingplate_30fpsThis dataset was created using LeRobot.
Dataset Description
SO-101 robot dataset collected with the MA autonomous forward/reset pipeline. The task is to sort red, green, and blue RGB blocks onto plates of the matching color. The dataset contains 100 successful episodes at 30 FPS with top and left-wrist RGB camera streams, robot state/action features, end-effector pose, gripper state, and skill/subtask annotations.
Homepage: https://huggingface.co/CoRL2026-CSI
Paper: [More… See the full description on the dataset page: https://huggingface.co/datasets/Cache-SCA/SO101-ma_sort_RGBblock_to_matchingplate_30fps.so101_cube_pick_place_0622
so101_cube_pick_place_0622 (TsFile)
Apache TsFile version of Chaenn/so101_cube_pick_place_0622.
Overview
A LeRobot robot manipulation dataset. Each frame holds the commanded action and observed observation.state joint positions; camera views are stored as videos in the original dataset.
Episodes: 102
Frames: 112484
Sampling rate: 30 fps
Tasks: 1
Split: a single train split
Robot: so_follower
Cameras (not uploaded): top, wrist, side
Schema (TsFile… See the full description on the dataset page: https://huggingface.co/datasets/THULab/so101_cube_pick_place_0622.