Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: lerobot
|
| 4 |
+
pipeline_tag: robotics
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
This model was created using [pickup dataset](https://huggingface.co/datasets/arclabmit/lx7r_pickup_dataset)
|
| 8 |
+
|
| 9 |
+
Repo: [BEAVR](https://github.com/ARCLab-MIT/beavr-bot)
|
| 10 |
+
|
| 11 |
+
Paper: [Action Chunking with Transformers for Image-Based Spacecraft Guidance and Control](https://arxiv.org/abs/2509.04628)
|
| 12 |
+
|
| 13 |
+
Example of training the [ACT](https://arxiv.org/abs/2304.13705) neural network with from scratch:
|
| 14 |
+
```bash
|
| 15 |
+
python lerobot/scripts/train.py \
|
| 16 |
+
--policy.type=act \
|
| 17 |
+
--dataset.repo_id=arclabmit/iss_docking_act_model
|
| 18 |
+
```
|