On the Effectiveness of Retrieval, Alignment, and Replay in Manipulation

Imitation learning with visual observations is notoriously inefficient when addressed with end-to-end behavioural cloning methods. In this letter, we explore an alternative paradigm which decomposes reasoning into three phases. First, a retrieval phase, which informs the robot what it can do with an object. Second, an alignment phase, which informs the robot where to interact with the object. And third, a replay phase, which informs the robot how to interact with the object. Through a series of real-world experiments on everyday tasks, such as grasping, pouring, and inserting objects, we show that this decomposition brings unprecedented learning efficiency, and effective inter- and intra-class generalisation.