MODELING SENSOR CONFIDENCE FOR SENSOR INTEGRATION TASKS

This paper addresses the problem of determining the reliability of individual sensors in a multi-sensor robotic system in an unknown environment. The inherent difficulty in this problem is that the decision must be based solely upon the data from the sensors themselves. While some previous research has considered unstructured environments (see Refs 1 and 2 for examples) little if any consideration has been given to totally unknown environments. This problem has usually been avoided by assuming that the sensors would not provide erroneous data or ignoring sensors when they appeared to provide erroneous data. We believe a more robust solution is to consider each sensor's performance over time compared to other sensors, and from this determine a measure of confidence in each sensor. This allows sensors which temporarily provide erroneous data to be accommodated. A system which can determine the reliability of its sensors is more robust since it can wisely decide which sensors are most appropriate for a given task and can also determine whether sensor conflicts are the result of poorly performing sensors.