A community-driven platform for robotics enthusiasts to share and explore creative projects built with the phospho Junior Dev Kit.
This repository contains demo code and community projects developed using the phospho Junior Dev Kit. Whether you're a beginner or an experienced developer, you can explore existing projects or contribute your own creations.
-
Get Your Dev Kit: Purchase your Phospho Junior Dev Kit at robots.phospho.ai. Unbox it and set it up following the instructions in the box.
-
Control your Robot: Donwload the Meta Quest app, connect it to your robot, start teleoperating it.
-
Record a Dataset: Record a dataset using the app. Do the same gesture 30-50 times (depending on the task complexity) to create a dataset.
-
Install the Package:
pip install --upgrade phosphobot- Train a Model: Use Le Robot to train a policy on the dataset you just recorded.
git clone https://github.com/huggingface/lerobot.git
cd lerobot
pip install -e .Add the configs/policy/act_so100_phosphobot.yamlfile from this repository to the lerobot/configs/policy directory in the lerobot repository.
Launch the training script with the following command from the lerobot repository (change the device to cuda if you have an NVIDIA GPU, mps if you use a MacBook Pro Sillicon, and cpu otherwise):
sudo python lerobot/scripts/train.py \
--dataset.repo_id=<HF_USERNAME>/<DATASET_NAME> \
--policy.type=<act or diffusion or tdmpc or vqbet> \
--output_dir=outputs/train/phoshobot_test \
--job_name=phosphobot_test \
--device=cpu \
--wandb.enable=trueFor the full detailed instructions, refer to the guide available here.
Connect with other developers and share your experience in our Discord community
Explore projects created by our community members in the code_examples directory. Each project includes its own documentation and setup instructions.
- Documentation: Read the documentation
- Community Support: Join our Discord server
- Issues: Submit problems or suggestions through GitHub Issues
MIT License
Made with 💚 by the Phospho community