An Action Chunking Transformer policy trained in LeRobot on human demonstrations of the simulated ALOHA bimanual cube-transfer task.
lerobot/diffusion_pusht
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelImitation policy263M paramsEst. Edge GPUEstimated minimum compute for inference: Jetson Orin class, 8–16 GB shared memory. Not a benchmark.Apache 2.0Single arm
About
A Diffusion Policy checkpoint trained in LeRobot to push a T-shaped block into a target pose in the 2D PushT simulation.
Why it matters for physical AI
It is the standard reference checkpoint for diffusion-based visuomotor policies, and many robot learners start from it.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
hf download lerobot/diffusion_pushtUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.