Quick learning of cause-effects relevant for robot action

Abstract

In this work we propose a new paradigm for the rapid learning of cause-effect relations relevant for task execution. Learning occurs automatically from action experiences by means of a novel constructive learning approach designed for applications where there is no previous knowledge of the task or world model, examples are provided on-line during run time, and the number of examples is small compared to the number of incoming experiences. These limitations pose obstacles for the existing constructive learning methods, where on-line learning is either not considered, a significant amount of prior knowledge has to be provided, or a large number of experiences or training streams are required. The system is implemented and evaluated in a humanoid robot platform using a decision-making framework that integrates a planner, the proposed learning mechanism, and a human teacher that supports the planner in the action selection. Results demonstrate the feasibility of the system for decision making in robotic applications.