A real-time Road Boundary Detection Algorithm Based on Driverless Cars

In this study, aiming at road boundary detection problem of driverless cars in structured and semi-structured roads, the paper proposed a new real-time road boundary detection algorithm based on driverless cars as a platform. The algorithm firstly included following steps: calibration, layered and median filtering according to the obtained LIDAR point cloud data, and then extract the left and right road boundary points of each layer. The extracted road boundary points are then straight line fitted using RANSAC algorithm. Finally, straight line is tracked using KALMAN filtering, then achieve real-time road boundary detection. The test results show that this boundary detection algorithm has the high accuracy and reliability and is able to accurately accomplish the boundary detection task, which can satisfy the requirements of real-time system. And this algorithm has been applied successfully in "The future challenge competition for driverless cars" in 2014 year and has obtained the third place.