Object-object interaction affordance learning

This paper presents a novel object–object affordance learning approach that enables intelligent robots to learn the interactive functionalities of objects from human demonstrations in everyday environments. Instead of considering a single object, we model the interactive motions between paired objects in a human–object–objectway. The innate interaction-affordance knowledge of the paired objects are learned from a labeled training dataset that contains a set of relativemotions of the paired objects, human actions, and object labels. The learned knowledge is represented with a Bayesian Network, and the network can be used to improve the recognition reliability of both objects and human actions and to generate proper manipulation motion for a robot if a pair of objects is recognized. This paper also presents an imagebased visual servoing approach that uses the learned motion features of the affordance in interaction as the control goals to control a robot to perform manipulation tasks. © 2013 Elsevier B.V. All rights reserved.