Road Following in an Unstructured Desert Environment Based on the EM(Expectation-Maximization) Algorithm

This paper describes the development and performance of a vision system, named PFSS (path finder smart sensor) for autonomous navigation of an unmanned ground vehicle. A monocular camera and vision processing algorithms were used as the sensor system to identify traversable terrain. Unlike the Bayesian based method which was used by Team CIMAR in the 2005 DARPA Grand Challenge, the expectation-maximization (EM) algorithm is applied. The implementation and performance of this approach are reported here