admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-15 08:39:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Only move teleop after space press

Browse Source
This commit is contained in:
Pepijn
2025-12-31 12:24:43 +01:00
parent a97255e3d1
commit f15872293d
3 changed files with 143 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/source/rac.mdx
+15 -7
View File
@@ -126,19 +126,27 @@ python examples/rac/rac_data_collection.py \
| Key | Action |
|-----|--------|
| **SPACE** | Start intervention (take control) |
| **SPACE** | Pause policy (teleop mirrors robot, no recording) |
| **c** | Take control (start correction, recording resumes) |
| **→** | End episode (save) |
| **ESC** | Stop recording session |
| **←** | Re-record episode |
| **ESC** | Stop session and push to hub |
**The RaC Protocol:**
1. Watch the policy run autonomously
2. When you see imminent failure, press **SPACE** to intervene
3. **RECOVERY**: Teleoperate the robot back to a good in-distribution state
4. **CORRECTION**: Use teleoperator to complete the subtask
5. Press **→** to save and end episode
2. When you see imminent failure, press **SPACE** to pause
- Policy stops, teleoperator mirrors robot position
- Allows smooth handoff without jarring movements
- No frames recorded during pause
3. Press **c** to take control
- Teleoperator is now free to move
- **RECOVERY**: Teleoperate back to a good state
- **CORRECTION**: Complete the subtask
- All movements are recorded
4. Press **→** to save and end episode
The recovery segment (teleoperating back to good state) is recorded as training data - this teaches the policy how to recover from errors.
The recovery and correction segments teach the policy how to recover from errors.
### Step 3: (Optional) Compute SARM Rewards