mulligan2026MIT

Thread Nut: round 2 evaluation

Real-robot held-out evaluation dataset for the Mulligan paper, containing episodes from evaluation sessions with multiple policy variants tested on a thread nut task across 50 trials with two camera views.

Downloads1K
Episodes150
Hours0.6654

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
150
Total Hours
0.6654
Data Format
parquet
License
MIT
Part of the Thread Nut: round 2 evaluation family

Access

Need custom rgb data?

Claru builds purpose-built datasets for lab applications with dense human annotations and quality assurance.

Request a Sample Pack

Related Datasets