This site is an independent community hub, not affiliated with Hugging Face. Official repo: https://github.com/huggingface/lerobot
How to Install and Verify LeRobot in 15 Minutes?
Direct Answer: Pin Python version with Conda, install dependencies from official repo, and verify by outputting the version number.
TL;DR / Key Takeaways
- 1.Must use Python 3.10+ environment for compatibility.
- 2.Recommended on Linux (Ubuntu 22.04), macOS supports partial simulation only.
- 3.Install `feetech-servo-sdk` before connecting hardware (for SO-100).
Supported Hardware: SO-100, Aloha, or Unitree?
Direct Answer: Choose SO-100 for the fastest end-to-end setup. Upgrade to Aloha/Unitree for complex tasks.
| Hardware | Use Case | Est. Cost | Difficulty |
|---|---|---|---|
| SO-100 | Single-arm IL, Beginners | $200 - $300 | Entry Level |
| Aloha | Dual-arm, Fine Manipulation | $10k+ | Advanced Level |
| Unitree G1 | Humanoid, RL | $16k+ | Expert Level |
Source: Hugging Face LeRobot Official Repo + Hardware Vendor Websites | Updated: 2026-03-18
Should I use Linux, macOS, or Windows to install LeRobot?
Direct Answer: Prefer Linux for real hardware. macOS/Windows are better suited for running simulations and reading tutorials first.
| OS | Real Hardware Support | Recommended Use | Risks |
|---|---|---|---|
| Ubuntu 22.04 | Strong | Real Robot Training/Deployment | Drivers/Permissions |
| macOS | Limited | Simulation/Data Processing | Missing hardware drivers |
| Windows | Limited | Learning workflows | WSL/Driver issues |
Source: Community Tests | Updated: 2026-03-18
What environment dependencies must I check before installation to avoid 80% of errors?
Direct Answer: Pin the Python version, confirm GPU/drivers, reserve disk space, and ensure the build toolchain is available.
Software Requirements
- • Ubuntu 20.04/22.04 (Recommended)
- • Python 3.10
- • Conda / Mamba
- • Git
Hardware Requirements
- • NVIDIA GPU (8GB+ VRAM Recommended)
- • 16GB RAM
- • 50GB Free Disk Space
Can I run it without a GPU? Local vs. Cloud GPU: How to choose?
Direct Answer: Yes. Use CPU/low-end GPU for small-scale validation; for stable training and speedup, cloud GPUs are recommended.
| Setup | Speed | Cost | Best For |
|---|---|---|---|
| CPU | Slow | Lowest | Validation/Tuning |
| Local GPU (8GB+) | Medium | One-time hardware | Stable Training |
| Cloud GPU | Fast | Pay-as-you-go | Final Push |
Source: Community Tests | Updated: 2026-03-18
How to make LeRobot installation steps "reproducible"?
Direct Answer: Every step must have a verifiable output (version number/command return/device enumeration). Do not skip steps.
Step 1: Clone Repo and Create Environment
git clone https://github.com/huggingface/lerobot.git cd lerobot conda create -y -n lerobot python=3.10 conda activate lerobot
Step 2: Install Dependencies
pip install -e . pip install opencv-python # Optional, for camera support
Step 3: Verify Installation
python -c "import lerobot; print(lerobot.__version__)"
Tip: Seeing the version output means the installation is successful!
Common Installation Errors & Solutions
Error: 'ModuleNotFoundError: No module named 'feetech_servo_sdk''
Solution: Make sure you ran `pip install -e .`. If it still fails, install the sdk submodule manually.
Error: `CUDA Error: no kernel image is available`
Solution: Your GPU driver is too old or PyTorch version mismatches. Check `nvidia-smi` output.