← LeRobot for companies

Robot Setup Advisor

From your first experiment to an existing industrial cell. Compare robots across manufacturers, check your work area in 3D, and plan training, deployment and cost with LeRobot.

What do you want the robot to do?

Start with your situation, then refine the setup. You can explore every step without an account.

Or define your project

Choose the goal and task below. The remaining steps update as you go.

Describe your project with AI optional · HF sign-in
An AI model reads your description and fills every step; you can correct any answer. Usage is billed to your Hugging Face account (a fraction of a cent).
Your goal
The task
How many tasks?
Your data

Two learning paths · choose for your task

How will the robot learn?

IL: a good starting point when people can demonstrate the behavior. Record examples, train ACT or fine-tune a VLA, evaluate and collect corrections.

RL: consider it when you can score success and repeat trials with resets. This advisor models HIL-SERL with supervised robot practice, a reward classifier and human interventions.

For example: demonstrate varied pick-and-place tasks with IL; consider RL for a repeatable insertion task with a reliable reward. Precision alone does not decide the method. Demonstrations can also bootstrap RL.

Which robot fits the job?

Choose a robot from any manufacturer in the catalog, then check payload and workspace. Blue shows an estimated reach envelope; orange is your work area. Models without kinematics use a simplified estimate.

Start with your payload and work area, or .
Objects the robot handles

Preview: GLB, self-contained glTF, STL, OBJ or USDZ. Have USD, USDA or USDC? See the asset guide below.

Payload

Heaviest object with the gripper.

Work area (in front of the robot base)
Width
Depth
Height
Gap to base
Robot budget
Rank robots by
Your work areaReachable spaceOut of reach

EXPLORE THE CATALOG

All manufacturers welcome

Search within the task selected in Project. Select a row to preview a robot, then choose it for your setup. Integration status is separate from payload and reach.

From USD assets to a robot workspace
1. Start with an asset

Use your CAD export or NVIDIA SimReady USD assets from the Hub. Keep the original USD files and their dependencies for simulation.

2. Preview the geometry here

Pick a SimReady object, or export a supported GLB or USDZ. This advisor uses lightweight geometry previews; it does not import an entire USD stage or run its physics. Confirm scale and mass after import.

3. Build and evaluate the simulation

In your simulator, configure collisions, joints, materials, cameras, actions and the task. An asset alone is not an evaluation environment. EnvHub connects supported environments to LeRobot.

Which policy, and where to train it?

The policy follows from your task. Pick the GPU you have, or train on Hugging Face Jobs and pay by the second.

Compute you have for training

Where does the policy run?

Where inference happens decides the hardware, the network you need and the deployment technique.

Compare complete setups

Hours/day
Days/year
Years
Trainings/yr

Cost

Hardware bought, training and cloud inference, and electricity, in US dollars.

HardwareTraining & cloud inferenceElectricity

CO2

Manufacturing (rough), training, and operation of the robot and its computers, in kg CO2e.

ManufacturingTrainingOperation

Indicative CO₂ scenario, not a verified product footprint. Electricity factors use Ember’s 2025 generation data. Manufacturing factors remain generic assumptions. Read the sources, exact values and limits →

How these numbers are computed

    Your setup at a glance

    Your chosen learning path, hardware, assumptions and next steps.

    Save your selected setup, estimates and sources. No sign-in needed.

    Get started

    Why this setup for your project

    Written by an AI model from your description and your setup. Products, numbers and commands come only from this page.

    You changed the setup since this was written.

    Your first commands

    
          

    Run pip install lerobot and hf auth login first. Full walkthrough: .

    Hugging Face tools for you

      SimReady objects on the Hugging Face Hub