FMCW radar2radar Interference Detection with a Recurrent Neural Network

FMCW radar sensors receive target reflections from the environmental surrounding at frequencies around 77 GHz. The increasing number of sensors on the road operating in this frequency range leads to a higher likelihood of unfavorable radar-to-radar interference. Consequences can be the appearance of artificial targets or the degradation of the noise spectrum, where targets with a small RCS might disappear. We use a Neural Network-based outlier detection method to identify corrupted samples in the time domain signal after the ADC. The architecture consists of a recurrent Neural Network with Long-Short-Term-Memory cells to extract the temporal information. The small network and the stream processing make it suitable for embedded devices. The semi-supervised trained network can detect various interference patterns with reduced training effort. We evaluate the system in a complete pipeline with zeroing mitigation on simulated randomized FMCW data. The method increases the Signal-to-Noise-Ratio ratio by up to 30 dB in the presence of interference and increases the overall system performance and reliability.