In the Defense industry, radar target simulations play a big hole: they are useful to study critical scenarios, make object classification and study the target signatures. They show to be a major point of technologic independence for countries, once allows creating and evaluating Radar Signatures of complex targets, as aircraft, ships and armored cars, without the need of measuring them. It is a possibility of generating enemys signatures and defining the best approach to react and detect them. However, this kind of simulation is expensive, spend a lot of computational resources and demands a complex environment, which is needed to run the simulations. This study proposes a proof of concept of a radar target simulation, based on a case study of automotive radars (FMCW – 77 GHz) using Generative Adversarial Networks (GANs): an artificial intelligence technique that is used for generating realistic fake data, such as images, audios, texts, and even radar signals. The achieved results show that the GAN approach was able to generate visually realistic radar targets using low computational efforts, oppening a new way to radar target simulations: AI-based simulations. Although being based on automotive targets, all results can be extrapolated to Defense scenarios.
