A knowledge base for learning probabilistic decision making from human demonstrations by a multimodal service robot

Abstract

This paper presents a description logic based system to store and retrieve knowledge used in models for autonomous probabilistic decision making by multimodal service robots. These models are mainly generated by observation and analysis of humans performing tasks, the programming by demonstration methodology. As formal model representation, partially observable Markov decision processes (POMDPs) are utilized as they are a well understood formal framework for decision making considering real world uncertainty in both perception and execution. The approach presented here deals with aspects of organizing knowledge which cannot be retrieved from user demonstrations or which is valid beyond a single task. It is shown how use it in the process of model generation on a real service robot.