“…Previous works in this area have made significant progress towards radar-based odometry [2-4, 9, 11, 14-16, 26, 34, 39] and place recognition [20,22,31,43,46]. However, previous approaches to radar odometry have either relied on handcrafted feature extraction [2-4, 14-16, 26, 34], correlative scan matching [11,39], or a (self-)supervised learning algorithm [9,11] that relies on trajectory groundtruth. Barnes and Posner [9] previously showed that learned features have the potential to outperform hand-crafted features.…”