A Seamless DFT/FFT Self-Adaptive Architecture for Embedded Radar Applications

Radar is one of the domains where adaptability is paramount. Depending on the current system state, the radar algorithms must be adapted. However, most systems include static hardware implementations on FPGA or ASIC to process the massive amount of data from multiple sensors in parallel. The classic approach is to configure hardware logic through registers to switch radar modes, requiring to hardwire all configurations. However, in embedded radar systems the hardware resources are very limited and this solution is not optimal. An innovative solution relies on the FPGA reconfigurable nature to use multiple configurations and limit resources overhead. In this paper, we present a dynamic partial reconfiguration (DPR) application for radar processing, which allows to switch between a classic discrete Fourier transform (DFT) sum and a fast Fourier transform (FFT) to enhance Doppler extraction. Our study explores the pros and cons of both methods. Based on these observations, we propose a decision method for enabling an efficient self-adaptive solution. Finally, we provide a case study with a reconfigurable radar implementation which uses the current system state to take full advantage of both Fourier transform methods.