The position sensitive detector (PSD) is photo-electronic sensor which can detect the position of a light spot travelling over its surface, and convert the position of light spot to simple electric current signal. The most important problem to use the PSD is how to overcome the influence of background light action on the PSD. Based on the PSD analyses, it is found that the signal of PSD is nonlinear when there exist background light. A method for background light compensation of photo-electric position detector based on the artificial neural network is presented in this paper. In order to compensate background light over a full range, the neural network is trained to properly represent the nonlinear mapping between sensor reading and their represent output accurately at different background light. It is revealed from the computer simulation that the influence of background light fluctuation can be eliminated effectively, and a desired linear relationship between the sensor input and the neural network output can be obtained.