datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Unitree_G1edu_u3_place_bread
Unitree_G1edu-u3_place_bread
Dataset Description
This dataset uses an extended format based on LeRobot and is fully compatible with LeRobot.
Task Preview
View Video Directly
Overview
Total Episodes: 1464
Total Frames: 500679
FPS: 30
Dataset Size: 6.51 GB
Robot Name: Unitree_G1edu-u3
End-Effector Type: three_finger_end_effector
Teleoperation Type: data_glove
Sensors: cam_high_rgb,
cam_left_wrist_rgb,
cam_right_wrist_rgb… See the full description on the dataset page: https://huggingface.co/datasets/RoboCOIN/Unitree_G1edu_u3_place_bread.G1_Dex1_ToolboxStorageG1_Dex1_OrganizeToolsunitree-wbt-stepitG1_Dex1_StorePaddleUnitree_G1edu_u3_pour_drink
Unitree_G1edu-u3_pour_drink
Dataset Description
This dataset uses an extended format based on LeRobot and is fully compatible with LeRobot.
Task Preview
View Video Directly
Overview
Total Episodes: 1298
Total Frames: 967967
FPS: 30
Dataset Size: 5.20 GB
Robot Name: Unitree_G1edu-u3
End-Effector Type: five_finger_end_effector
Teleoperation Type: human_motion_capture
Sensors: cam_high_rgb
Camera Information: cam_high_rgb… See the full description on the dataset page: https://huggingface.co/datasets/RoboCOIN/Unitree_G1edu_u3_pour_drink.G1_Dex1_Stack_BlockThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Stack_Block.Unitree_G1edu_u3_place_bread_1
Unitree_G1edu-u3_place_bread_1
Dataset Description
This dataset uses an extended format based on LeRobot and is fully compatible with LeRobot.
Task Preview
View Video Directly
Overview
Total Episodes: 1042
Total Frames: 334156
FPS: 30
Dataset Size: 4.78 GB
Robot Name: Unitree_G1edu-u3
End-Effector Type: three_finger_end_effector
Teleoperation Type: data_glove
Sensors: cam_high_rgb,
cam_left_wrist_rgb,
cam_right_wrist_rgb… See the full description on the dataset page: https://huggingface.co/datasets/RoboCOIN/Unitree_G1edu_u3_place_bread_1.G1_Dex1_Fold_TowelThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Fold_Towel.G1_Dex3_ToastedBread_DatasetThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex3_ToastedBread_Dataset.G1_Dex1_Organize_ToolsThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Organize_Tools.G1_Dex1_Wipe_TableThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Wipe_Table.G1_Dex1_DualRobot_Clean_TableThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_DualRobot_Clean_Table.G1_Dex1_Erase_BoardThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Erase_Board.unitree_model
unitree_model
This is a repository providing Unitree's robot 3D models for different environments.
For more information about robots model, please visit unitree_ros.
Generate from urdf
Please follow import_urdf tutorial to convert URDF.
Due to some bugs in the python script in version 4.5, please use Direct Import.
Specify the settings as follows:
Select Movebale Base in Links
Select Stiffness in Joint Configuration
Select Force in Drive Type
Allow… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/unitree_model.G1_Dex1_HangCupG1_Dex1_Prepare_FruitThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Prepare_Fruit.G1_Dex1_MountCameraRedGripper_DatasetThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "Unitree_G1_Gripper",
"total_episodes": 201,
"total_frames": 172649,
"total_tasks": 1,
"total_videos": 804,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:201"},
"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/unitreerobotics/G1_Dex1_MountCameraRedGripper_Dataset.G1_WBT_Inspire_Put_Clothes_into_Washing_Machine
Data Structure
Observations
observation.state.ee_state (12)
End-effector states of the robot.
Computed via forward kinematics (FK) from the root link to the left and right end-effectors.
Includes the contribution of the waist.
Represented as concatenated poses of both end-effectors.
observation.state.hand_state (12 or 2)
Finger states for both hands. The dimensionality depends on the hand type.
Inspire Hand (range: 0.0 – 1.0, open → close)… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_WBT_Inspire_Put_Clothes_into_Washing_Machine.G1_WBT_Brainco_Collect_Plates_Into_Dishwasher
Data Structure
Observations
observation.state.ee_state (12)
End-effector states of the robot.
Computed via forward kinematics (FK) from the root link to the left and right end-effectors.
Includes the contribution of the waist.
Represented as concatenated poses of both end-effectors.
observation.state.hand_state (12 or 2)
Finger states for both hands. The dimensionality depends on the hand type.
Inspire Hand (range: 0.0 – 1.0, open → close)… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_WBT_Brainco_Collect_Plates_Into_Dishwasher.G1_Dex1_Pack_PencilBoxThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Pack_PencilBox.Unitree_G1edu_u3_place_towel
Unitree_G1edu-u3_place_towel
Dataset Description
This dataset uses an extended format based on LeRobot and is fully compatible with LeRobot.
Task Preview
View Video Directly
Overview
Total Episodes: 402
Total Frames: 106275
FPS: 30
Dataset Size: 1.26 GB
Robot Name: Unitree_G1edu-u3
End-Effector Type: three_finger_end_effector
Teleoperation Type: human_motion_capture
Sensors: cam_high_rgb,
cam_left_wrist_rgb… See the full description on the dataset page: https://huggingface.co/datasets/RoboCOIN/Unitree_G1edu_u3_place_towel.G1_Dex1_Bag_InsertThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Bag_Insert.G1_Dex1_Pour_MedicineThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Pour_Medicine.G1_Dex1_Pack_PingPongThis dataset was created using LeRobot.
Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in Part 5 of AVP Teleoperation Documentation.
Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
Dataset Structure
meta/info.json:
{
"codebase_version":… See the full description on the dataset page: https://huggingface.co/datasets/unitreerobotics/G1_Dex1_Pack_PingPong.G1_Dex1_StoreEarphonesG1_WBT_Inspire_Clean_The_Living_RoomRoboCupFootball_DatasetThis dataset consists of data from the TORSO_21_dataset open-source dataset as well as newly collected data from new scenarios, and it has been processed into a format suitable for training YOLO series models. The trainset directory contains images and labels for training, while the testset directory contains images and labels for testing.
G1_Dex1_PlugInEthernetG1_WBT_Inspire_Put_Vegetables_Into_Basket