A Smart Optical Position Sensor with Genetic Programming Technique

An optical measurement system, which uses a light spot or a slit ray system, often requires an optical position sensor. In such a system, because the position of a signal light is the most important and basic information needed, it is necessary for the position sensor to detect the position accurately under any conditions. We proposed an intelligent position sensor that can estimate the actual position of a light spot using a neural network, but the sensor has to go through a relearning process when the surroundings change. In this paper, we propose a new method for measuring the position of a light spot in a real environment utilizing genetic programming. The method doesn't require advance training, unlike the method employing a neural network, and it eliminates the influence of background lights. Therefore, we expect that the application of the proposed sensor will be for online measurement in an actual environment