cagataydevcc-by-4.0-generated-with-nvidia-isaac
Allegro hand in-hand cube reorientation, partially trained (Isaac Lab, recorded with strands-robots)
A 16-DoF Allegro hand performs in-hand cube reorientation in NVIDIA Isaac Lab simulation, trained with PPO for 1500 iterations achieving 0.55 success rate. Dataset contains 12 episodes with 3351 frames recorded at 30 fps with RGB imagery and 147-D state observations.
Downloads67
Technical Profile
- Modalities
- rgbproprioception
- Robot Embodiments
- Allegro Hand
- Environment
- simulation
- Task Types
- dexterous_manipulationin_hand_reorientation
- Data Format
- LeRobot
- License
- cc-by-4.0-generated-with-nvidia-isaac
Access
Need custom rgb data?
Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.
Request a Sample Pack