Learning and Composing Primitive Skills for Generalisable Dual-arm Manipulation

Anthropomorphic robots need to master dual-arm manipulation skills to autonomously deal with the rapidly changing, dynamic and unpredictable real-world environments where they have to. Given the expertise of humans in conducting these activities, it is natural to study humans’ motions to use the resulting knowledge in robotic control. With this in mind, this work leverages human knowledge to formulate a more general, real-time, and less task-specific framework for dual-arm manipulation. Such a framework builds a library of primitive skills from human demonstrations, which are combined sequentially and simultaneously to confront novel scenarios. The proposed framework is evaluated on the iCub humanoid robot and several synthetic experiments, by conducting a dual-arm pick-and-place task of a parcel in the presence of unexpected obstacles. Results suggest the suitability of the method for robust and generalisable dual-arm manipulation.