Globally rising demand for transportation by rail is pushing existing infrastructure to its capacity limits, necessitating the development of accurate, robust, and high-frequency positioning systems to ensure safe and efficient train operation. As individual sensor modalities cannot satisfy the strict requirements of robustness and safety, a combination thereof is required. We propose a path-constrained sensor fusion framework to integrate various modalities while leveraging the unique characteristics of the railway network. To reflect the constrained motion of rail vehicles along their tracks, the state is modeled in 1D along the track geometry. We further leverage the limited action space of a train by employing a novel multi-hypothesis tracking to account for multiple possible trajectories a vehicle can take through the railway network. We demonstrate the reliability and accuracy of our fusion framework on multiple tram datasets recorded in the city of Zurich, utilizing Visual-Inertial Odometry for local motion estimation and a standard GNSS for global localization. We evaluate our results using ground truth localizations recorded with a RTK-GNSS, and compare our method to standard baselines. A Root Mean Square Error of 4.78 m and a track selectivity score of up to 94.9 % have been achieved.

翻译：全球日益增长的铁路交通需求已将现有基础设施推向容量极限，因此亟需开发精确、鲁棒且高频的定位系统，以保障列车安全高效运行。由于单一传感器模态无法满足鲁棒性与安全性的严苛要求，必须采用多模态组合方案。我们提出一种路径约束传感器融合框架，在整合多种模态的同时充分利用铁路网络的独特特性。为反映轨道车辆沿铁轨运动的约束特性，状态模型沿轨道几何结构建立一维表示。我们进一步利用列车有限的动作空间，通过采用新型多假设跟踪方法，考虑车辆在铁路网络中可能行驶的多条轨迹。通过苏黎世市采集的多组有轨电车数据集，我们验证了该融合框架的可靠性与精度——其中采用视觉-惯性里程计进行局部运动估计，并采用标准GNSS实现全局定位。利用RTK-GNSS记录的真实定位数据评估结果，并与标准基线方法进行对比。本方法实现了4.78米的均方根误差及高达94.9%的轨道选择评分。