This thesis investigates the application of artificial intelligence to real time control in combination with image analysis techniques. The system consists of a "mouse" and a "cheese" in a two dimensional maze which are viewed by a video camera connected to a frame grabber board in a personal computer (PC). The maze is designed to be alterable during the mouse's navigation towards the "cheese" or target. The pc runs the frame grabber software which analyzes the maze to find the cheese, mouse and movement options during traversal. Parameters about the mouse's position, the maze constraints in the vicinity of the mouse and the general direction of the target are passed to a Prolog search algorithm which makes decisions on the next course of action for the mouse. Parameters on the movement of the mouse are passed via a serial port to a single board computer which controls the mouse's motion with two stepper motors. The intent is to investigate the integration of a simple real time control system with an intelligent host before expanding the system to handle more complex control algorithms where the computational requirements could easily overpower a single processor. This approach allows the possibility of mixing and matching processors for different applications. It also becomes easier to determine whether the Al-image analysis or the real time control activities are the computational bottlenecks and to decide on appropriate corrective measures.
Department, Program, or Center
Electrical Engineering (KGCOE)
Spina, Robert, "Real time maze traversal" (1989). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus