Skip to main content

Installation

Teleopit supports multiple installation profiles depending on your use case.

Prerequisites​

  • Python 3.10+
  • Conda (recommended)
conda create -n teleopit python=3.10
conda activate teleopit

Install Profiles​

Inference Only (sim2sim)​

pip install -e .

This is sufficient for offline BVH playback and MuJoCo simulation.

Training​

pip install -e '.[train]'

Adds rsl-rl-lib, mjlab, wandb, swanlab, and training dependencies.

Sim2Real (Hardware Deployment)​

pip install -e '.[sim2real]'

Adds opencv-python. You also need to initialize submodules and build/install the C++ g1_bridge_sdk bridge:

git submodule update --init --recursive
bash scripts/setup/setup_g1_bridge.sh

See G1 Bridge SDK for details.

Pico 4 VR​

pip install -e '.[pico4]'

Teleopit uses the in-process pico_bridge.PicoBridge receiver for Pico tracking. Teleopit targets pico-bridge 0.2.1 and its pico_native tracking semantics. The receiver can run on a workstation PC or the robot onboard computer. See Pico Sim2Sim and Pico Sim2Real for the full setup guides.

Optional LinkerHand control for Pico sim2real uses local third-party packages. Install those packages directly after initializing the submodules:

git submodule update --init --recursive
pip install -e third_party/linkerhand-python-sdk
pip install -e third_party/somehand
scripts/setup/download_somehand_l6_assets.sh

These packages are only required when hands.enabled=true.

Sim2Real Recording​

pip install -e '.[recording]'

Adds the Pico sim2real stack plus the video dependencies used by sim2real_record.yaml. RealSense Python bindings are platform-specific: install pyrealsense2 manually in the active environment when using input.video.source=realsense. On Arm machines, use conda-forge rather than the pip package:

conda install -c conda-forge pyrealsense2

Verify Installation​

python -c "import teleopit; print('teleopit OK')"
python -c "import train_mimic.tasks; print('training OK')"  # if training installed

Next Steps​