Active execution monitoring using planning and semantic knowledge

Abstract

To cope with the dynamics and uncertainty inherent in real world environments, autonomous mobile robots need to perform execution monitoring for verifying that their plans are executed as expected. Domain semantic knowledge has lately been proposed as a source of information to derive and monitor implicit expectations of executing actions. For instance, when the robot moves into an office, it would expect to see a desk and a chair. Such expectations are checked using the immediately available perceptual information. We propose to extend the semantic knowledge-based execution monitoring to handle situations where some of the required information is missing. To this end, we use AI sensor-based planning to actively search for such information. We show how verifying execution expectations can be formulated and solved as a planning problem involving sensing actions. Our approach is illustrated by showing test scenarios run in an indoor environment using a mobile robot.