Inferring High-Level Behavior from Low-Level Sensors

Abstract. We present a method of learning a Bayesian model of a traveler moving through an urban environment. This technique is novel in that it simultaneously learns a unified model of the traveler’s current mode of transportation as well as his most likely route, in an unsupervised manner. The model is implemented using particle filters and learned using Expectation-Maximization. The training data is drawn from a GPS sensor stream that was collected by the authors over a period of three months. We demonstrate that by adding more external knowledge about bus routes and bus stops, accuracy is improved.

• Type: Conference
• Year: 2003
• Where: HUC
• Authors: Donald J. Patterson, Lin Liao, Dieter Fox, Henry A. Kautz
• Keywords: Bayesian Model, GPS Sensor Stream, HUC 2003, Traveler’s Current Mode