Unitree G1 Static Apple Pick & Place#

The simulated Static Apple Pick & Place workflow path uses a Unitree G1 to move an apple to a plate in NVIDIA Isaac Lab. It carries those demonstrations through GR00T N1.7 training and closed-loop evaluation.

AVAILABLE

Understand the Workflow#

Conceptual Overview

Understand the role of each stage and the difference between simulation and physical data collection.

Conceptual Overview
Architecture and Data Requirements

Review the pipeline, robot-control software, and data requirements before running the stages.

Architecture and Data Requirements

Before You Start#

Complete Installation to prepare the workstation and simulation environment. Recording demonstrations requires an XR headset; check the XR headset, handheld controller, and network requirements before starting the recording stage.

Use the Environment Variable Reference when restoring runtime and run settings in a new terminal.

Follow the Workflow Path#

Follow the five stages in order, or use the published stage inputs to start at conversion, training, or evaluation. After recording, optional Isaac AutoData generation can expand your demonstrations before conversion. The recording guide uses Isaac Lab-Arena with Pink IK for upper-body control and AGILE for lower-body control (g1_wbc_agile_pink). Native Isaac Lab with AGILE is a supported alternative; both provide the command fields required by the supplied training configuration.

Simulation Practice

1

Launch the scene and practice driving the Unitree G1 with AGILE.

G1 Simulation
Demonstration Recording

2

Record HDF5 demonstrations in Isaac Lab-Arena with Pink IK and AGILE using a supported XR device. The task scores each episode automatically.

G1 Demonstration Recording
Dataset Conversion

3

Convert the HDF5 data to LeRobot and validate the fields required by the policy training modality for Unitree G1.

G1 Dataset Conversion
Policy Training

4

Train GR00T N1.7 on the validated dataset of Unitree G1 demonstrations.

G1 Policy Training
Policy Evaluation

5

Run the trained policy in the workflow’s scene and collect episode metrics.

G1 Policy Evaluation

Workflow Artifacts#

Commands use outputs/g1/ under the repository root for one run. Choose new recording and output paths when starting another run.

Stage

Output

Next Input

Recording in Isaac Lab-Arena with Pink IK and AGILE

recording-arena.hdf5

Direct conversion or Arena AutoData generation

Optional Arena generation

generated-arena.hdf5

Arena conversion

Conversion

lerobot/ or lerobot-generated/

GR00T training dataset

Training

training/checkpoint-20000/

Checkpoint preflight and policy server

Evaluation

evaluation/<timestamp>/

Episode metrics and HTML report

Keep the original manifested recordings. Merged HDF5 files cannot be used for replay or AutoData with the current merger.

For the native AGILE alternative, the guides use recording-native.hdf5 and generated-native.hdf5. Native fixed-base data requires a custom training and evaluation configuration because it lacks navigation and base-height commands.

Tip

Start conversion with a generated HDF5 download. LeRobot dataset and model downloads are included in the G1 policy training and G1 policy evaluation steps.

Hugging Face Dataset and Checkpoint#

The checkpoint below is separate from the released checkpoint pinned in runtime.toml.

Dataset

DATASET ON HUGGING FACE

nvidia/GR00T-E2E-Reference-Workflow-SIM-G1-N1.7-AppletoPlate-Dataset

Recorded HDF5, generated HDF5, and LeRobot demonstrations for the Unitree G1 static-apple simulation workflow.

https://huggingface.co/datasets/nvidia/GR00T-E2E-Reference-Workflow-SIM-G1-N1.7-AppletoPlate-Dataset
Checkpoint

MODEL ON HUGGING FACE

nvidia/GR00T-E2E-Reference-Workflow-SIM-G1-N1.7-AppletoPlate-Model

Fine-tuned GR00T N1.7 checkpoint for the same Unitree G1 simulation task.

https://huggingface.co/nvidia/GR00T-E2E-Reference-Workflow-SIM-G1-N1.7-AppletoPlate-Model

Supporting Guidance#

Data Generation (Optional)

Optional: turn a few AGILE recordings into many with Isaac AutoData. The launcher selects the recorded action layout and manipulating hand automatically.

G1 Data Generation With Isaac AutoData

Testing and Limitations#

This workflow covers one Unitree G1 task on Linux x86_64. By default, recording and checkpoint evaluation use the same success criteria. Manually ending a recording does not change its success label. Pass --no-auto_success to let the operator decide which episodes to accept. The released checkpoint can test whether the components work together; its results do not establish expected performance in this workflow’s scene.

See Reference for supported configurations and limitations.