Modeling Robot Differences by Leveraging a Physically Shared Context

Abstract

Knowledge sharing, either implicit or explicit, is crucial during development as evidenced by many studies into the transfer of knowledge by teachers via gaze following and learning by imitation. In the future, the teacher of one robot may be a more experienced robot. There are many new difficulties, however, with regard to knowledge transfer among robots that develop embodiment-specific knowledge through individual solo interaction with the world. This is especially true for heterogeneous robots, where perceptual and motor capabilities may differ. In this paper, we propose to leverage similarity, in the form of a physically shared context, to learn models of the differences between two robots. The second contribution we make is to analyze the cost and accuracy of several methods for the establishment of the physically shared context with respect to such modeling. We demonstrate the efficacy of the proposed methods in a simulated domain involving shared attention of an object.