Perpustakaan Digital ITB

Mobile robot with the autonomous road following ability needs 2 important characteristics, those are, trajectory detection and the movement of the robot based on the result of its trajectory. For the trajectory detection, we develop road following algorithm by processing images from camera sensor. Most autonomous road following technique can only be applied in certain types of road. The algorithm that is usually used makes certain patterns from every road (asphalt road, stony road, land road, etc) and certain color of the road as an input for the system. There are 3 components in this autonomous road following algorithm. First, the detection of several cross horizontal road templates at various distances from the robot is found using reverse optical flow technique by assuming the region currently directly in front of the vehicle is drivable road. Second, these horizontal road templates are matched along horizontal lines at appropriate vertical heights in the current image, providing the locations in the image of regions that match the road’s past appearance. Third, a dynamic programming technique is applied to the template matching responses along each horizontal line in order to find the globally optimal horizontal position of the road at each vertical height, subject to a constraint on the maximum possible curvature of the road. This entire process is continually repeated to renew the previous road data. From this road segmentation that we got, the next process will be done, that is, actuating the robot to follow the road.