Instructions to use simaai/ACT-SO101-PickPlace with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use simaai/ACT-SO101-PickPlace with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
ACT SO-101 Pick-and-Place
An ACT policy trained to place a grey eraser in a white basket and compiled for the SiMa.ai Modalix DevKit.
| Property | Value |
|---|---|
| Training checkpoint | Step 100,000 |
| Output | 100 actions x 6 joints |
| Precision | BF16 |
| Compiled graphs | 6 |
| Toolchain | Model Compiler 3.0.0, Palette SDK 3.0.0, LLiMa 0.6.0 |
| Bundle ID | act-so101-grey-eraser-pickplace-100k-bf16-219727d9 |
This repository contains the deployable compiled bundle, reference fixtures, and SO-101 runtime assets. It does not contain the training checkpoint or dataset.
Requirements
- Modalix DevKit running Palette SDK 3.0.0 and LLiMa 0.6.0
- PoLiMa with SDK 3.0 support
- SO-101 follower with two USB cameras matching the training views
See the PoLiMa installation guide and SO-101 setup guide.
Download and deploy
hf download simaai/ACT-SO101-PickPlace --local-dir ACT-SO101-PickPlace
cd ACT-SO101-PickPlace
sha256sum --check SHA256SUMS
read -r -p "DevKit login (username@address): " devkit_login
polima deploy --bundle ./bundle --devkit "$devkit_login" --start
Deployment starts the inference server but does not start robot motion.
Validate inference
polima run --bundle ./bundle --devkit "$devkit_login" --fixture --repeat 20
The packaged fixture passed compiled-device fidelity validation. On the SDK 3.0 reference DevKit, 20 measured plans after three warm-ups had a median model latency of 13.5 ms, cosine similarity 0.999992, and maximum absolute error 0.0147 against the reference output. This fixture test does not move the robot or measure physical task success.
Training data
The policy used 769 demonstrations from SO-101 Grey Eraser Pick-and-Place. The complete dataset contains 961 episodes and 272,853 frames.
Limitations
This policy is specific to the reference robot, object, basket, and camera views. Changes to geometry, framing, lighting, or calibration can affect behavior. Text changes do not teach ACT a new task at runtime.
License
Apache-2.0. See LICENSE.