A method for computer-aided learning a reference map based on measurements of features of a radio network, wherein the measurements are carried out in such a way that, for a mobile object (o), which, via the radio network with a plurality of base stations (bs1, bs2, bs3) of the radio network communicates, at a plurality of unknown object positions (op) of the mobile object (o) respective feature vectors (c.meas) of the radio network is to be measured and, as a result, a series of a plurality of chronologically successive feature vectors (c.meas) for respective object positions (op) to the respective measurement points is obtained, wherein the reference map a plurality of spatial reference positions (rp), based on the series of the respective feature vectors (c) of the radio network to the respective reference positions (rp) of the reference map be learned:a) based on a performs pattern-matching, which the respective feature vectors (c.meas) the series with the feature vectors (c.Rm) at the reference positions (rp) compares the reference map, the respective object positions (op), on which the feature vectors (c.meas) of the radio network were measured, are estimated;b) based on optimization of a cost function optimized estimated object positions (op) are determined, wherein in the optimization of one or more boundary conditions to be taken into consideration, which, by a predetermined movement model for the mobile object (o) are specified, wherein the predetermined movement model using the time sequence of the time of a measurement of the series of one or more restrictions for the movement of the object with respect to the last and / or the future movement of the mobile object (o) determines;c) by means of the optimized estimated object positions (op) updated feature vectors c) of the radio network at the reference positions (rp) of the reference maps are determined.
展开▼