Knowledge representation for cognitive robotic systems

Abstract

Cognitive robotics are autonomous systems capable of artificial reasoning. Such systems can be achieved with a logical approach, but still AI struggles to connect the abstract logic with real-world meanings. Knowledge representation and reasoning help to resolve this problem and to establish the vital connection between knowledge, perception, and action of a robot. Cognitive robots must use their knowledge against the perception of their world and generate appropriate actions in that world in compliance with some goals and beliefs. This paper presents an approach to multi-tier knowledge representation for cognitive robots, where ontologies are integrated with rules and Bayesian networks. The approach allows for efficient and comprehensive knowledge structuring and awareness based on logical and statistical reasoning.