mulligan2026apache-2.0
real-square-d2-r04-eval-b01-mulligan-idql-policy-rollouts
Policy rollout dataset from the Mulligan benchmark containing 50 episodes of a real robot performing square manipulation tasks using an IDQL policy trained on real data.
Downloads143
Episodes50
Hours0.217
Technical Profile
- Modalities
- rgb
- Robot Embodiments
- franka
- Action Space
- 7-DoF: vel_x, vel_y, vel_z, vel_roll, vel_pitch, vel_yaw, gripper_action
- Environment
- lab
- Task Types
- manipulation
- Episodes
- 50
- Total Hours
- 0.217
- Data Format
- parquet
- 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