Imitation Learning and Attentional Supervision of Dual-Arm Structured Tasks

Abstract

In this work, we present an approach to imitation learning and flexible execution of dual-arm structured tasks. The proposed framework exploits imitation learning and attentional supervision to learn both a set of motion primitives and the associated tasks structure. During the teaching phase, attentional supervision allows the teacher to exploit attention manipulation, like object and verbal cueing, to facilitate the demonstration. In this phase, motion data are automatically segmented, annotated and learned in a compact form for on-line motion generation. During the execution phase, the learned task structure is exploited to synchronize left and right arm movements and to adapt task execution to the operative context. The proposed approach is demonstrated in a simulated kitchen scenario considering a pizza preparation task.