This paper presents an end-to-end radar odometry system which delivers robust, real-time pose estimates based on a learned embedding space free of sensing artefacts and distractor objects. The system deploys a fully differentiable, correlation-based radar matching approach. This provides the same level of interpretability as established scan-matching methods and allows for a principled derivation of uncertainty estimates. The system is trained in a (self-)supervised way using only previously obtained pose information as a training signal. Using 280km of urban driving data, we demonstrate that our approach outperforms the previous state-of-the-art in radar odometry by reducing errors by up 68% whilst running an order of magnitude faster.

本文提出了一种端到端的雷达里程计系统，其基于学习的嵌入空间提供鲁棒、实时的姿态估计，不受感知失真和干扰因素影响。该系统采用全微分、基于相关性的雷达匹配方法，具有与传统扫描匹配方法相同的可解释性，并允许进行不确定性估计。使用自监督训练信号，我们用280公里的城市驾驶数据证明了我们的方法优于先前的雷达里程计最新技术，误差降低了高达68％，运行速度提高了一个数量级。

Masking by Moving: 从位姿信息中学习无干扰雷达视觉里程计