CALVIN
Simulated benchmark for long-horizon, language-conditioned Franka Panda manipulation: 4 envs, 34 tasks, 24h of play.
| Year | 2022 |
|---|---|
| Total hours | 24 |
| Embodiments | franka_panda |
| Modalities | depth, ee_pose, language, proprioception, tactile, rgb |
| Task categories | manipulation |
| License | MIT |
| Access | open — commercial use permitted |
| Maintainer | University of Freiburg |
CALVIN (Composing Actions from Language and Vision) is an open-source PyBullet-simulated benchmark for learning long-horizon, language-conditioned continuous-control manipulation policies with a Franka Panda arm. It spans four tabletop environments (A, B, C, D), 34 manipulation tasks, and ~1000 crowd-sourced language annotations, with evaluation rollouts chaining five consecutive language-specified sub-tasks. The dataset provides ~6 hours of teleoperated 'play' data per environment (24h total) with static and gripper RGB-D cameras, tactile images, and proprioception.