Ontology Based Object Categorization for Robots

Meaningfully managing the relationship between representations and the entities they represent remains a challenge in robotics known as grounding. Useful insights can be found by approaching robotic systems development specifically with the grounding and symbol grounding problem in mind. In this paper we use Semantic Web technologies to provide a powerful extension to existing proposals for grounding robotic systems and have consequently developed OBOC, the first robotic software system with an ontology-based vision subsystem. OBOC has been tested and evaluated in the robot soccer domain against an internationally recognized RoboCup system. The architecture can be extended from not just vision but to also enhance decision making and support tasks such as information retrieval, reasoning, planning, communication and collaboration. The interoperability and openness of the Semantic Web technologies that underlie this approach increase the ability for robots to introspect, communicate and be inspected—benefits that ultimately lead to more grounded systems with open-ended intelligent behaviour and scope for collaboration.