Implementation of sensor selection and fusion using fuzzy logic

Different sensors may contain degrees of uncertainty and may be only reliable in particular situations, therefore sensor fusion and validation can be critical in complex redundant systems. This paper proposed a generic fuzzy logic algorithm for validation and fusion of uncertain sensor data. The system degrades marginal sensor data elegantly, while still removing obviously questionable data. Sensor data is represented as Gaussian curves. The sensor fusion problem is presented as determining a fused mean and standard deviation for the Gaussian of the output abstract sensor. Four variants of the fuzzy sensor fusion and validation system are presented and examined.