In this paper we address the problem of fusing informationfrom biased sensor-data collected by a sensor network.Under the assumption that the biases of the sensors are nuisanceparameters, we propose an algorithm that marginalizesthem out from the estimation problem. The algorithmuses particle filtering to obtain the unknown states of thesystem and Kalman filtering for marginalization of the biases.We apply the proposed algorithm to the problem oftarget tracking using bearings-only measurements acquiredby more than one sensor. The advantage of the consideredmethod over standard particle filtering which does not assumethe presence of biases is illustrated through computersimulations.
展开▼