Adaptive multi-sensor integration in uncertain environment with imperfect sensors

An adaptive multisensor/data fusion algorithm which can be employed in an uncertain environment using imperfect sensors is developed. The algorithm assumes little prior information about the sensed environment and the sensors, and adaptively adjusts the weights for the best fusion of inaccurate information provided by the multiple sensors. The term `best´ is used in the sense that the results of the adaptive fusion are as close to the optimal ones as possible