Computer control of an autonomous road vehicle by computer vision

A method for guiding an autonomous vehicle along roadways based on visual signals is described. The vehicle follows a white guideline on a flat road sensed by a CCD (charged coupled device) camera. The camera, mounted behind the windscreen of the vehicle, looks forward and down, detecting an area between 5 and 25 m ahead. An image processor (based on Transputers T800) scans the image for the borderline of the road. The line coordinates detected by the image processor are transmitted via transputer links to a transputer network. The implemented algorithm uses geometric coordinate-transformation and a dynamical model (Kalman filter) to identify the road curvature ahead and the relative position of the vehicle on the road. The reference angle for the electrical steering servo is computed from the lateral deviation, the yaw-angle deviation, the road curvature, and the velocity of the vehicle. All together it takes about 60 ms per image for recognition and control. The method has been tested by simulation and with a VW-Bus Caravelle on typical Autobahn scenes at a velocity of up to 120 km/h