A discriminating feature tracker for vision-based autonomous driving

Abstract

A new vision-based technique for autonomous driving is described. This approach explicitly addresses and compensates for two forms of uncertainty: uncertainty about changes in road direction and uncertainty in the measurements of the road derived in each image. Autonomous driving has been demonstrated on both local roads and highways at speeds up to 100 km/h. The algorithm has performed well in the presence of non-ideal road conditions including gaps in the lane markers, sharp curves, shadows, cracks in the pavement, and wet roads. It has also performed well in rain, dark, and nighttime driving with headlights.