Indoor position determination using location fingerprinting and vehicle sensor data

In this paper we present a system for position determination of vehicles in indoor areas such as parking garages or underground parking lots. By combining location fingerprinting using Bluetooth signal strengths and relative positioning using vehicle sensor data (speed and yaw rate) in a collective filter arrangement, an ubiquitous and stable vehicle positioning is provided. Hereby, both a Kalman filter and a particle filter were investigated and compared. By further incorporating signals from Global Navigation Satellite Systems in outdoor areas, a seamless outdoor-indoor positioning could be achieved. With the presented techniques, an accuracy of <; 2 m is feasible at a low financial effort.