Bridging the Sense-Reasoning Gap using the Knowledge Processing Middleware DyKnow

To achieve sophisticated missions an autonomous UAV operating in a complex and dynamic environments must create and maintain situational awareness. It is achieved by continually gathering information from many sources, selecting the relevant information for the current task, and deriving models about the environment and the UAV itself. Often models close to the sensor data, suitable for traditional control, are not sufficient for deliberative services. More abstract models are required to bridge the sense-reasoning gap. This paper presents how DyKnow, a knowledge processing middleware, can bridge the gap in a concrete UAV traffic monitoring application. In the presented example sequences of color and thermal images are used to construct and maintain qualitative object structures modeling the parts of the environment necessary to recognize the traffic behavior of the tracked vehicles in realtime. The system has been implemented and tested both in simulation and on data collected during test flights. 1