A Hidden Markov Model for pedestrian navigation

Abstract

We present an algorithm for pedestrian navigation optimized for smart mobile platforms using the present low-cost sensors and the limited processing power. The algorithm is based on a Hidden Markov Model that combines Wi-Fi positioning and dead reckoning. The hidden states are the positions of the Wi-Fi fingerprints in the database. The state transition includes dead reckoning based on step length estimation from acceleration measurements and compass heading calculated from magnetic field measurements. In the measurement update a database correlation of the actual Wi-Fi signal strength measurements with the stored values in the fingerprints has been performed. In simulations and tests we demonstrate that in this way ambiguities common in Wi-Fi positioning can be reduced. Therefor, higher accuracy and robustness can be achieved.

The ARPEGEO project: A new look at cellular RSSI fingerprints for localization

“…This could take the form of RSSI measurements from other frequency bands, for instance, or of data imported from other "imperfect" sensors, such as magnetometers, accelerometers, and the like. Adding memory to the system, to enable the use of dynamic trajectory approaches such as particle filters or Markov models [5,20], will undoubtedly also be useful.…”

A Hidden Markov Model for urban navigation based on fingerprinting and pedestrian dead reckoning

“…The accuracy indoors is significantly higher. Using the HMM indoors and outdoors instead of Wi-Fi fingerprinting higher accuracy can be achieved, see also [7]. In and around the office building the Wi-Fi coverage is almost optimal.…”

“…We evaluated the benefit of including dead reckoning in the HMM compared to just Wi-Fi fingerprinting in [7]. Through simulations we investigated the possible improvements.…”

“…In [7] dead reckoning has been included successfully in a HMM based on Wi-Fi positioning. In this paper we extend the HMM for Wi-Fi positioning.…”

Wi-Fi azimuth and position tracking using directional received signal strength measurements

“…So, the speed vector of a pedestrian calculated from consecutive positions has a very low accuracy. The positioning accuracy can be improved by combining Wi-Fi positioning with dead reckoning, using low cost sensors as proposed in [4], [5]. For pedestrians, dead reckoning can be improved by step detection, as analyzed in [6].…”