Emergent Structuring of Interdependent Affordance Learning Tasks

In this paper, we study the learning mechanisms that facilitate autonomous discovery of an effective affordance prediction structure with multiple actions of different levels of complexity. A robot can benefit from a hierarchical structure where pre-learned basic affordances are used as inputs to bootstrap learning of complex affordances. In a developmental setting, links from basic affordances to the related complex affordances should be self-discovered by the robot, along with a suitable learning order. In order to discover the developmental order, we use Intrinsic Motivation approach that can guide the robot to explore the actions it should execute in order to maximize the learning progress. During this learning, the robot also discovers the structure by discovering and using the most distinctive object features for predicting affordances. We implemented our method in an online learning setup, and tested it in a real dataset that includes 83 objects and the discrete effects (such as pushed, rolled, inserted) created by three poke and one stack action. The results show that the hierarchical structure and the development order emerged from the learning dynamics that is guided by Intrinsic Motivation mechanisms and distinctive feature selection approach.