An architecture for autonomous vehicle navigation

The Autonomous Land Vehicle group at CMU has developed an intelligent mobile sensor-equipped robot capable of following simple roads. The system extracts edges from camera images, determines the most likely road position, and steers the robot to track the road. The first demonstrations are discussed, and the hardware is briefly described, with attention given to the vehicle, sensors, and computers. An overview of the sensor interpretation process is given, and experience with a real implementation is considered. Particular emphasis is placed on the blackboard architecture which ties all the processes together.