FMB (Functional Manipulation Benchmark)
Berkeley real-world Franka Panda benchmark: 22,550 expert demos of grasping, repositioning, and assembly with RGB-D, proprioception, and force/torque.
| Year | 2024 |
|---|---|
| Episodes | 22,550 |
| Total hours | 31 |
| Embodiments | franka_panda |
| Modalities | depth, ee_pose, force_torque, language, proprioception, rgb |
| Task categories | manipulation |
| License | CC-BY-4.0 |
| Access | open — commercial use permitted |
| Maintainer | UC Berkeley (RAIL / Robotic AI & Learning Lab) |
FMB is a real-world robotic manipulation benchmark from UC Berkeley's RAIL lab for studying functional manipulation, where a Franka Panda arm composes skills (grasping, repositioning, assembly/insertion) using 3D-printed objects on assembly boards. It comprises 22,550 expert demonstration trajectories across single-object and multi-object multi-stage tasks, recorded from 2 global and 2 wrist Intel RealSense D405 cameras (RGB + depth) plus proprioception and end-effector force/torque. Raw data ships as .npy dictionaries with code to convert into RLDS for training imitation-learning baselines.