Dataset Hub

The Open Vocab Mobile Manipulation (OVMM) dataset involves mobile manipulation tasks with initial configurations, goal specifications, and candidate goals. The initial configuration includes the initial poses of objects, the agent's start position and orientation. The goal specification defines moving objects of a specific category from a source container to a target container. The candidate goals section details instances of objects and containers related to the task.

The EgoMimic dataset contains extensible data for imitation learning, especially human and robot data captured via first‑person video. The dataset includes examples of grocery, laundry, and bowl‑placement tasks.