Options
2013
Conference Paper
Titel
Seamless indoor outdoor positioning using Bayesian sensor data fusion on mobile and embedded devices
Abstract
As one of the seven “Beyond Tomorrow Projects” the project GeMo (Gemeinschaftlich-E-Mobilität) wants to provide technical solutions for the shared use of electric mobility. The vision behind this project is that in 2050 almost only electric vehicles will be driving within larger European cities and the coordination and sharing of mobility resources will be a major task. Fraunhofer IIS’s contribution to this project is the development of localization services, which run on mobile user devices as well as on embedded hardware platforms inside cars and provide seamless indoor and outdoor positioning by integrating technologies like GNSS, Wi-Fi fingerprinting and dead reckoning based on inertial sensors. The paper describes the theoretical foundations based on Bayesian reasoning and the well-established realization of these ideas in terms of the particle filter, which uses Monte Carlo sampling to estimate probability distributions of the actual state. The probabilistic motion and measurements models are discussed, which serve as inputs to the filtering algorithm. The experimental results are presented together with a description of the setup and equipment. The achieved positioning uncertainty in indoor and outdoor environments with focus on the transition regions is discussed.