LearningFromVideo2026apache-2.0
LearningFromVideo/rollout_eval-push-milk-right
An evaluation dataset of robot rollouts performing a push-milk-right task, created using the LeRobot framework with multi-view RGB observations and end-effector control actions.
Downloads7
Episodes25
Why This Matters for Physical AI
This evaluation dataset demonstrates multi-view imitation learning for manipulation tasks, providing real robot trajectory data essential for benchmarking vision-based control policies.
Technical Profile
- Modalities
- rgbproprioception
- Robot Embodiments
- dk1_follower
- Action Space
- end_effector_delta
- Environment
- lab
- Task Types
- manipulationpush
- Episodes
- 25
- Data Format
- LeRobot
- License
- apache-2.0
Access
Need custom rgb data?
Claru builds purpose-built datasets for lab applications with dense human annotations and quality assurance.
Request a Sample Pack