Sfx: An Architecture For Action-oriented Sensor Fusion

Sensor fusion has an important role in the navigation of autonomous mobile robots. Our research has generated a generic and robust process model based on the action-oriented perception paradigm. The autonomous execution and exception handling abilities of this model have been implemented as the Sensor Fusion Effects (SFX) architecture. The key aspects of this implementation are the sensing plan, the uncertainty management mechanism, the application of feedback from the sensing process to individual sensors, the detection of exceptions to the sensing plan, and handling of those exceptions. This paper gives an overview of the SFX architecture, concentrating on the sensing plan as the central control structure guiding autonomous execution. This paper also reports on experiments using sensor data collected from our mobile robot which demonstrate the use of the sensing plan representation, the execution sequence, the application of feedback, and how feedback improves the overall sensing capabilities of the robot.