YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

IsaacLab-Arena Environments

Hugging Face

Isaac Lab-Arena is a robotics simulation framework that enhances NVIDIA IsaacLab by providing a composable, scalable system for creating diverse simulation environments and evaluating robot learning policies. GPU-accelerated simulation environments for robotics learning, compatible with LeRobot and the EnvHub ecosystem.

Available Environments

The following are example environments built with NVIDIA IsaacLab Arena. The community can create custom environments using the IsaacLab Arena framework:

Preview Environment Description
GR1 Microwave gr1_microwave Reach out to the microwave and open it.
Galileo Pick and Place galileo_pnp Pick objects and place in target location
G1 Loco-manipulation g1_locomanip_pnp Pick up the brown box from the shelf, and place it into the blue bin on the table located at the right of the shelf.
Kitchen Pick and Place kitchen_pnp Kitchen object manipulation tasks
Press Button press_button Locate and press button

Quick Start

Evaluate a trained policy e.g. SmolVLA:

lerobot-eval \
    --policy.path=nvidia/smolvla-arena-gr1-microwave \
    --env.type=isaaclab_arena \
    --env.hub_path=nvidia/isaaclab-arena-envs \
    --rename_map='{"observation.images.robot_pov_cam_rgb": "observation.images.robot_pov_cam"}' \
    --policy.device=cuda \
    --env.environment=gr1_microwave \
    --env.embodiment=gr1_pink \
    --env.object=mustard_bottle \
    --env.headless=false \
    --env.enable_cameras=true \
    --env.video=true \
    --env.video_length=10 \
    --env.video_interval=15 \
    --env.state_keys=robot_joint_pos \
    --env.camera_keys=robot_pov_cam_rgb \
    --trust_remote_code=True \
    --eval.batch_size=1

Related Links

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support