Using Relational Histogram Features and Action Labelled Data to Learn Preconditions for Means-End Actions

Abstract

Abstract — The outcome of many complex manipulation ac-tions is contingent on the spatial relationships among pairs of objects, e.g. if an object is “inside ” or “on top ” of another. Recognising these spatial relationships requires a vision system which can extract appropriate features from the vision input that capture and represent the spatial relationships in an easily accessible way. We are interested in learning to predict the success of “means end ” actions that manipulate two objects at once, from exploratory actions, and the observed sensorimo-tor contingencies. In this paper, we use relational histogram features and illustrate their effect on learning to predict a variety of “means end ” actions ’ outcomes. The results show that our vision features can make the learning problem significantly easier, leading to increased learning rates and higher maximum performance. This work is in particular important for robots that need to reliably predict the success probability of their multi object manipulating action repertoire in novel scenes. I.