Instructions to use Menlo/asimov1-locomotion-0818 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Asimov
How to use Menlo/asimov1-locomotion-0818 with Asimov:
# Run the policy in a browser simulation of the Asimov 1 humanoid (no GPU needed) git clone https://github.com/menloresearch/humanoid-policy-viewer cd humanoid-policy-viewer npm install npm run hf Menlo/asimov1-locomotion-0818
- Notebooks
- Google Colab
- Kaggle
Add how to run and inputs/outputs to the model card
Browse filesAdds a "How to run" section with the one-command viewer (npm run hf Menlo/asimov1-locomotion-0818, no GPU needed) and an "Inputs and outputs" section describing the 78 observations and 23 joint actions.
README.md
CHANGED
|
@@ -10,4 +10,33 @@ license: bsd-3-clause
|
|
| 10 |
- `policy.onnx` is the exported policy for inference, producing joint-position actions.
|
| 11 |
- `agent.yaml` records the actor-critic and AMP training settings, including the motion data configuration.
|
| 12 |
- `env.yaml` records the simulation and locomotion task settings, including observations, actions, commands, and rewards.
|
| 13 |
-
- Training and evaluation code: [menloresearch/isaac_asimov](https://github.com/menloresearch/isaac_asimov).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
- `policy.onnx` is the exported policy for inference, producing joint-position actions.
|
| 11 |
- `agent.yaml` records the actor-critic and AMP training settings, including the motion data configuration.
|
| 12 |
- `env.yaml` records the simulation and locomotion task settings, including observations, actions, commands, and rewards.
|
| 13 |
+
- Training and evaluation code: [menloresearch/isaac_asimov](https://github.com/menloresearch/isaac_asimov).
|
| 14 |
+
|
| 15 |
+
## How to run
|
| 16 |
+
|
| 17 |
+
Run the policy in a browser simulation of Asimov 1 with
|
| 18 |
+
[humanoid-policy-viewer](https://github.com/menloresearch/humanoid-policy-viewer).
|
| 19 |
+
It needs Node, git and bash, and no GPU:
|
| 20 |
+
|
| 21 |
+
```bash
|
| 22 |
+
git clone https://github.com/menloresearch/humanoid-policy-viewer
|
| 23 |
+
cd humanoid-policy-viewer
|
| 24 |
+
npm run hf Menlo/asimov1-locomotion-0818
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
+
This downloads the policy, starts the viewer and opens it in your browser.
|
| 28 |
+
Drive the robot with the velocity sliders, push it, or run the benchmark suite.
|
| 29 |
+
|
| 30 |
+
## Inputs and outputs
|
| 31 |
+
|
| 32 |
+
- **Input:** 78 values at 50 Hz: base angular velocity, projected gravity,
|
| 33 |
+
velocity command (`vx, vy, wz`), joint positions and velocities, and the
|
| 34 |
+
previous action. All of these are available on the real robot.
|
| 35 |
+
- **Output:** 23 joint position actions (legs, waist and arms; the neck is not
|
| 36 |
+
driven). Each target is `default_joint_pos + action_scale * action`, with
|
| 37 |
+
both values in `env.yaml`.
|
| 38 |
+
- Trained in Isaac Lab (PhysX); the viewer simulates it in MuJoCo.
|
| 39 |
+
|
| 40 |
+
The full observation order and joint list are in the viewer's
|
| 41 |
+
[supported policies](https://github.com/menloresearch/humanoid-policy-viewer/blob/main/docs/huggingface.md#supported-policies)
|
| 42 |
+
doc.
|