kob0105/act_pusht is an open-source imitation-learning model for robotics, designed to predict short action chunks from teleoperated data. It is available on Hugging Face for use in research and development, supporting integration with LeRobot and Colab.
Act Pusht is an Other AI product. It enables researchers and developers to apply imitation learning for robotics action chunking using open-source models. Act Pusht is an open-source project aimed at robotics researchers and developers. The project is open source (Apache-2.0). The product ships for the web and API.
kob0105 builds and maintains Act Pusht, and the product first shipped in 2024. The project is developed in the open on GitHub with 25.7k stars and 164 commits in the last 90 days. Across PulseGate's embedding index, Act Pusht has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are imitation learning, action chunking, and robotics policy.
Latest indexed changes and source events
kob0105/act_pusht discovered by the PulseGate indexer
Other apps tracked under the same category.
