datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
RGBench-Cloth-Sim2Real-v1
RGBench Cloth Sim-to-Real (v1)
🌐 Project page: https://rgbench.github.io/ · 📦 Code: https://github.com/hwk0809/RGBench
Nine carefully captured garments — three bimanual manipulation actions
each (fling / fold / grasp) — with real-world ground truth point
clouds for evaluating any cloth simulator's sim-to-real gap. Released
as the evaluation half of the AAAI 2026 paper Real Garment Benchmark
(RGBench).
The larger 6 000+ garment-mesh asset library and the GarmentDynamics… See the full description on the dataset page: https://huggingface.co/datasets/RGBench/RGBench-Cloth-Sim2Real-v1.Task_000100_lerobot_sim2real_Intern
Task 000100 right MimicGen success 1000, LUT, LeRobot v3
This dataset contains 1,000 successful simulated Task 000100 trajectories selected in episode order from the corrected MimicGen HDF5 source. The source file contains 1,021 successful episodes despite success3000 in its filename; this dataset uses demo_0 through demo_999.
The task is to pick up the navy cosmetic block and place it in the white basket. The LeRobot v3 dataset has 260,859 frames at 15 fps, 22 state values and… See the full description on the dataset page: https://huggingface.co/datasets/Dongkkka/Task_000100_lerobot_sim2real_Intern.Task_000100_lerobot_v2_sim2real_Intern
Task 000100 right: 450 episodes across a 5 × 6 grid
This local LeRobot v3 dataset contains 450 selected successful simulation episodes (104,491 frames at 15 Hz). It combines four source sets: MimicGen v2 (112), v3 (112), v4 (113), and the earlier 1000-episode LeRobot set (113). This package has not been uploaded.
All four sources use the same 22 joint/state names and order: 19 robot joints followed by linear_x, linear_y, and angular_z. Every action has head_joint1 =… See the full description on the dataset page: https://huggingface.co/datasets/Dongkkka/Task_000100_lerobot_v2_sim2real_Intern.ising-sim2real-results
Ising sim2real — Decoder Benchmark Results
Evaluation results for a panel of open surface-code decoders run on real Google
Willow hardware data and on synthetic circuit-level noise of rising fidelity.
The question these results answer: does the cheap synthetic benchmark predict the
real-hardware result?
This repo holds the outputs (LERs, per-shot outcomes, fitted noise models,
figures). The inputs — ingested Willow detection events, circuits, and shipped
DEMs — live in… See the full description on the dataset page: https://huggingface.co/datasets/ShayManor/ising-sim2real-results.so101_sim2real_baseline_green_block_mix_4_sourcesThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"observation.state": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [… See the full description on the dataset page: https://huggingface.co/datasets/Long27/so101_sim2real_baseline_green_block_mix_4_sources.sim2real_1224_brush_pickrollout_so101_sim2real_baseline_green_block_mix_65_35_200_spaced_72This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/Long27/rollout_so101_sim2real_baseline_green_block_mix_65_35_200_spaced_72.so101_sim2real_baselineThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"observation.state": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/so101_sim2real_baseline.so101_sim2real_baseline_green_block_mix_50_50_200This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/so101_sim2real_baseline_green_block_mix_50_50_200.so101_sim2real_baseline_green_block_mix_65_35_200This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/so101_sim2real_baseline_green_block_mix_65_35_200.rollout_so101_sim2real_baseline_green_block_mix_80_20_200_spaced_72_20260907_193818This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/rollout_so101_sim2real_baseline_green_block_mix_80_20_200_spaced_72_20260907_193818.rollout_so101_sim2real_baseline_green_block_mix_50_50_200_spaced_72_20260907_175251This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/rollout_so101_sim2real_baseline_green_block_mix_50_50_200_spaced_72_20260907_175251.so101_sim2real_delay_shift_v2_spaced_200This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"observation.state": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/so101_sim2real_delay_shift_v2_spaced_200.so101_sim2real_baseline_green_block_mix_36_64_200This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/so101_sim2real_baseline_green_block_mix_36_64_200.rollout_so101_sim2real_baseline_green_block_mix_65_35_200_spaced_72_r2_20260907_145123This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/rollout_so101_sim2real_baseline_green_block_mix_65_35_200_spaced_72_r2_20260907_145123.SoftManipulator_sim2real
SoftManipulator Sim2Real Dataset
This dataset accompanies the research paper "Bridging High-Fidelity Simulations and Physics-Based Learning Using A Surrogate Model for Soft Robot Control" published in Advanced Intelligent Systems, 2025.
📋 Dataset Overview
This dataset contains experimental and simulation data for a 3-actuator pneumatic soft manipulator, designed to enable sim-to-real transfer learning and surrogate model development. The data includes motion capture… See the full description on the dataset page: https://huggingface.co/datasets/Ndolphin/SoftManipulator_sim2real.so101_sim2real_baseline_green_block_mix_80_20_200This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/so101_sim2real_baseline_green_block_mix_80_20_200.sim2real_test04This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_mujoco",
"total_episodes": 100,
"total_frames": 65234,
"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/Minato-Shoji/sim2real_test04.sim2real_test01This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_mujoco",
"total_episodes": 50,
"total_frames": 32617,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:50"
},
"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/Minato-Shoji/sim2real_test01.rollout_so101_sim2real_baseline_green_block_mix_65_35_200_spaced_72This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/vasco281204/rollout_so101_sim2real_baseline_green_block_mix_65_35_200_spaced_72.rf-loc-sim2real
Associated Paper
This dataset release accompanies the paper Bridging the sim-to-real gap in RF localization with large-scale synthetic pretraining, published in Information Fusion. The Rome and Oslo real-world data, together with the synthetic RF localization datasets packaged here, are used in the study to train, pretrain, fine-tune, and evaluate models for sim-to-real RF fingerprinting localization.
RF-Loc-Sim2Real Dataset Export
This dataset contains… See the full description on the dataset page: https://huggingface.co/datasets/asaribekyan/rf-loc-sim2real.rollout_act_sim2real_mujoco_36sim_v2_72rollout_act_sim2real_finetune_dataset2_72so100_sim2real_blockThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "so100_follower",
"total_episodes": 2,
"total_frames": 1595,
"total_tasks": 1,
"total_videos": 4,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:2"
},
"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/pranavsaroha/so100_sim2real_block.sim2real_test02This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_mujoco",
"total_episodes": 100,
"total_frames": 65234,
"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/Minato-Shoji/sim2real_test02.SoftManipulator_sim2real
SoftManipulator Sim2Real Dataset
This dataset accompanies the research paper "Bridging High-Fidelity Simulations and Physics-Based Learning Using A Surrogate Model for Soft Robot Control" published in Advanced Intelligent Systems, 2025.
📋 Dataset Overview
This dataset contains experimental and simulation data for a 3-actuator pneumatic soft manipulator, designed to enable sim-to-real transfer learning and surrogate model development. The data includes motion… See the full description on the dataset page: https://huggingface.co/datasets/SELVA183/SoftManipulator_sim2real.sim2real_gta5_to_cityscapessim2real_test06This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_mujoco",
"total_episodes": 100,
"total_frames": 65870,
"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/Minato-Shoji/sim2real_test06.sim2real_brush_oder_pick_2This dataset was created using Physical AI Tools and LeRobot.
Dataset Structure
meta/info.json:
{
"total_episodes": 1000,
"total_frames": 140703,
"total_videos": 1000,
"codebase_version": "v2.1",
"robot_type": "FFW_SG2",
"total_tasks": 1,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 10,
"splits": {
"train": "0:1000"
},
"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/Dongkkka/sim2real_brush_oder_pick_2.Sim2Real-Generalization