An off-axis flight vision display system design using machine learning

We propose an off-axis flight vision display system design with a free-form surface using machine learning to simulate the visual distance variation during take-off and landing training for pilots. This is realized by ray tracing ZEMAX software, where we build optimize series of initial systems that meet corresponding optical specifications. A deep neural network used train regression model, which specifically designed predict fitted polynomial model system. Our results demonstrate can be transformed into problem further optimized abundant data, providing avenue more powerful complex imaging systems.