Map building with radar and motion sensors for automated highway vehicle navigation

Driving autonomous vehicles on the highway is one of the most important coming applications of autonomous mobile robots. Many vision based systems have been developed for highway navigation and their success in experiments have been reported. While they have impressive success, they cannot as yet handle all conditions of weather, illumination, and traffic. Thus it is still necessary to develop other navigation methods to enable redundant and robust navigation systems. In contrast to road-following applications, off-road navigation usually cannot rely on simple tracking of visual cues, and therefore must use position-based and landmark-based navigation, such as in [4, 5]. Our long;term goal is to integrate this style of position-based navigation with visual road following in order to build a more robust and reliable road navigation system. In this paper, we describe the first part of that project: constructing a, navigation system that can build maps of highways and landmarks, and use tl-lose feature for position-based navigation. Speed and yaw rate gyro Sensors are used for vehicle motion detection, and a. millimeter wave radar system is used for landmark detection. To achieve position estimation and error correction, we use an extended Kalman filter. First, a map is built without previous knowledge of landmarks while human drives the vehicle. Then, at the stage of autonomous navigation, the previously produced map is used for position estimation. The experimental results show that a map produced by the proposed method call be used for later navigation, and that vehicle position is estimated accurately.