Abstract:
Public transit stations and hubs can be difficult to navigate for people with visual and cognitive impairments. RouteMe2 is a system that I am building to provide microrouting and guidance in these environments. Microroutes are pedestrian routes at a small spatial scale with detailed spatial information.
A critical component of this system is outdoor self-localization. This localization module is designed to function in challenging situations of the types that are often found at transit stations. Specifically, I address the case of an outdoor transit station with poor GPS reception due to tall nearby buildings that may obscure view of one or more satellites — a.k.a shading. Shading is very common in urban environments, and is a major cause of GPS failure. In order to mitigate the effect of shading, I propose a new approach that uses a small number of Bluetooth low energy (BLE) beacons to increase self-localization accuracy by means of statistical fusion with data from GPS, paired with a Bayes discrete filter tracker. A number of experiments were conducted at San Jose Diridon light rail station to quantitatively assess the performance of the proposed system.
In my future work I will deploy the model in a larger and more complex setting in Palo Alto transit station in a large-scale experiment with blind travelers. I intend to study the possibility of reducing the number of beacons thereby reducing the model’s operation cost. In addition, beacons are operated with batteries whose life-time is not deterministic and varies based on different factors including transmission power and advertising interval i.a. I will further research on detecting broken or discharged beacons to increase the reliability of the model.