Simultaneous Multi-Information Fusion and Parameter Estimation for Robust 3-D Indoor Positioning Systems
Typical WLAN based indoor positioning systems take the received signal strength (RSS) as the major information source. Due to the complicated indoor environment, the RSS measurements are hard to model and too noisy to achieve a satisfactory 3-D accuracy in multi-floor scenarios. To enhance the performance of WLAN positioning systems, extra information sources could be integrated. In this paper, a Bayesian framework is applied to fuse multi-information sources and estimate the spatial and time varying parameters simultaneously and adaptively. An application of this framework, which fuses pressure measurements, a topological building map with RSS measurements, and simultaneously estimates the pressure sensor bias, is investigated. Our experiments indicate that the localization performance is more accurate and robust by using our approach.
|Zugehörige Institution(en) am KIT
||Institut für Anthropomatik (IFA)
KITopen ID: 1000034854
||Proceedings of the 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2008),Seoul, Republic of Korea, August, 2008
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page