METHOD AND SYSTEM FOR INDOOR GEOLOCATION USING AN IMPULSE RESPONSE FINGERPRINTING TECHNIQUE

摘要

The location of people, mobile terminals and equipment in a mine is of greatcurrentinterest. In an indoor environment such as a mine (may be generalised to anyindoorenvironment), the multipath caused by reflection from walls, ceiling, floorandobjects, and the non-line of sight (NLOS) due to the blockage of the shortestdirectpath between the transmitter and receiver are the main sources of rangemeasurement errors. The unreliable measurements of location metrics such asRSS,AOA and TOA/TDOA yield to the deterioration of the positioning performance.Hence, alternatives to the traditional parametric geolocation techniques haveto beconsidered.In this paper, we present a novel method for mobile station location usingwidebandchannel measurements' results applied to an artificial neural network (ANN).Theproposed system (WBNN-Locate) learns off-line the location 'signatures' fromtheextracted location dependent features of the measured channel impulseresponsesdata (any relevant location dependent parameter may also be used) for LOS andNLOS situations. It then matches on-line the observation received from amobilestation against the learned set of 'signatures' to accurately locate itsposition.With this approach, multipath becomes useful since it improves location'signatures'characterisation, and the presence of a line of sight (LOS) is no longeressential,unlike in other geolocation techniques. The proposed location system has thecharacteristic to operate with a single fixed station and may be applied to athree-dimensional environment.The error median distance and the 90th percentile of the error distance foundwiththis technique were 1.2 m and 2 m, respectively.