SmolVLA RoboTwin stack_bowls_two (50 ep, single instruction)
SmolVLA policy fine-tuned on 50 demonstration episodes of the stack_bowls_two task from RoboTwin 2.0 (demo_clean config), starting from the lerobot/smolvla_robotwin base checkpoint.
Task
- Robot: Agilex dual-arm, end-effector control (16D state, 16D action)
- Cameras: 3 RGB streams —
dual_cam_global,cam_wrist_65,cam_wrist_75(240×320, D435) - Control rate: 10 Hz (LeRobot metadata; underlying RoboTwin sim ≈ 30 Hz, same source for train/eval)
- Fixed instruction:
"stack the bowls"(Strategy A: single instruction, not multi)
Training
| Config | Value |
|---|---|
| Base checkpoint | lerobot/smolvla_robotwin |
| Training data | 50 RoboTwin demonstrations |
| Batch size | 32 |
| Steps | 6000 (~10-25 epochs) |
| Optimizer | AdamW, lr=1e-4 |
| Scheduler | Cosine, warmup=300, decay=6000 |
| Chunk size | 50 |
Evaluation
Evaluated in RoboTwin 2.0 simulator (demo_clean config), 10 episodes, max_steps=400, action_chunk_exec=50.
Success rate: 7/10 (70%)
Usage
from lerobot.policies.smolvla import SmolVLAPolicy
policy = SmolVLAPolicy.from_pretrained("arrow-hf/smolvla-robotwin-stack-bowls-two-50ep")
See LeRobot documentation for inference setup.
Citation
Built on SmolVLA and SmolVLA-RoboTwin pretrained base, fine-tuned on data collected from RoboTwin 2.0.
- Downloads last month
- 16