Bayesian Filtering for Location Estimation

Location awareness is an important aspect of many pervasive computing applications. Unfortunately, no location sensor takes perfect measurements, nor is there one sensor that works well in all situations. Thus, it is crucial to represent uncertainty in location information provided by sensors as well as combining information coming from different sensors, possibly of different types. Bayesian filter techniques provide a powerful statistical tool to help manage and operate on measurement uncertainty, multi-sensor fusion, and identity estimation. In this article, we survey Bayes filter implementations and show their application to real-world location estimation tasks common in pervasive computing.