We describe a realtime system for finding and tracking unstructured paths in off-road conditions. The system was designed as part of the recent Darpa Grand Challenge and was tested over hundreds of miles of off-road driving. The unique feature of our approach is to combine geometric projection used for recovering Pitch and Yaw with Learning approaches for identifying familiar "drivable" regions in the scene. The region-based component segments the image to "path" and "non-path" regions based on texture analysis borne out of a learning-by-examples principle. The boundary-based component looks for the path bounding lines assuming a geometric model of a planar pathway bounded by parallel edges taken by a perspective camera. The combined effect of both sub-systems forms a robust system capable of finding the path even in situations where the vehicle is positioned out of the path - a situation which is not common for human drivers but is relevant for autonomous driving where the vehicle may find itself occasionally veering out of the path.