The article introduces Radarize, a self-contained Simultaneous Localization and Mapping (SLAM) pipeline for indoor environments. It uses only a low-cost commodity single-chip mmWave radar. The approach leverages unique radio frequency phenomena, such as doppler shift-based odometry, to improve performance. The method was evaluated on a large-scale dataset of 146 trajectories across 4 campus buildings, showing that it outperforms state-of-the-art radar-based approaches by approximately 5x in terms of odometry and 8x in terms of end-to-end SLAM. This is measured by absolute trajectory error (ATE), without the need for additional sensors such as IMUs or wheel odometry. It is particularly suitable for low lighting conditions and featureless environments, and offers increased privacy.
Publication date: 21 Nov 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2311.11260
