Utilization of Semantic Information for Robust Task Execution by Autonomous Robots

We propose a robot control system utilizing semantic information behind robot-plans. Robots read the semantic information annotated to control programs, and utilize it for proper situation-recognition and rational action-generation. We try to develop a framework based on reusable and sharable representations among robots and humans. To this end, we construct an ontology of task world defining a systematized vocabulary for task models and knowledge processing. We introduce several important ideas for modeling the task world. We demonstrate an example of execution monitoring in a simulated blocks world task. Semantic information serves as a guide for rational and reasonable inference, planning, and diagnosis