An Integrated Approach to Indoor and Outdoor Localization

We have developed a method of indoor localization and tracking that com-bines multiple sensor measurements to remove dependence on any one informa-tion source. A two-step process is proposed that performs an initial localization es-timate, followed by particle filter based t racking. Initial localization is performed using WiFi and image observations. For tracking we fuse information from WiFi, magnetic, and inertial sensors. We demonstrate the feasibility of this system using fingerprint m aps t hat a re c ollected w ith a s ingle walkthrough o f t he building at normal walking pace. In addition to a smartphone or tablet, only a foot mounted inertial measurement unit (IMU) is needed for database generation. Only a smart-phone is needed for positioning after database generation. The positioning method presented uses sensors available on most mobile devices and requires no new in-frastructure to be placed in the building. We have tested our approach in two locations: the Stoneridge Mall in Pleasanton, California, and the Doe Library at the UC Berkeley campus. We achieve an average location error of 2.6m across both locations. 3 DISTRIBUTION A: Distribution approved for public release.