Associating word descriptions to learned manipulation task models

This paper presents a method to associate meanings to words in manipulation tasks. We base our model on an affordance network, i.e., a mapping between robot actions, robot perceptions and the perceived effects of these actions upon objects. This knowledge is acquired by the robot in an unsupervised way by self-interaction with the environment. When a human user is involved in the process and describes a particular task, the robot can form associations between the (co-occurrence of) speech utterances and the involved objects, actions and effects. We extend the affordance model to incorporate a simple description of speech as a set of words. We show that, across many experiences, the robot is able form useful word-to-meaning associations, even without considering grammatical structure in the learning process and in the presence of recognition errors. Word-to-meaning associations are then used to instruct the robot to perform tasks and also allow to incorporate context in the speech recognition task.