fix(robomme): align docs and tests with nested pixels obs layout

Addresses PR #3311 review feedback:
- Docs: correct observation keys to `pixels/image` / `pixels/wrist_image`
  (mapped to `observation.images.image` / `observation.images.wrist_image`)
  and drop the now-obsolete column-rename snippet.
- Tests: assert `result["pixels"]["image"]` instead of flat `pixels/image`,
  matching the nested layout required by `preprocess_observation()`.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Pepijn
2026-04-20 10:10:23 +02:00
parent cace58536d
commit f086caee20
2 changed files with 11 additions and 13 deletions
+2 -8
View File
@@ -109,15 +109,9 @@ dataset = LeRobotDataset("lerobot/robomme")
### Feature key alignment (training)
The env wrapper exposes `front_rgb` and `wrist_rgb` as observation keys. The `features_map` in `RoboMMEEnv` maps these to `obs_images.front` and `obs_images.wrist` for the policy.
The env wrapper exposes `pixels/image` and `pixels/wrist_image` as observation keys. The `features_map` in `RoboMMEEnv` maps these to `observation.images.image` and `observation.images.wrist_image` for the policy. State is exposed as `agent_pos` and maps to `observation.state`.
The dataset uses `image` and `wrist_image` as column names. When fine-tuning from the dataset, you may need to rename columns to match your policy's expected input keys:
```python
dataset = LeRobotDataset("lerobot/robomme")
# rename dataset columns if needed:
# dataset.hf_dataset = dataset.hf_dataset.rename_column("image", "front_rgb")
```
The dataset's `image` and `wrist_image` columns already align with the policy input keys, so no renaming is needed when fine-tuning.
## Action Spaces