Ieee Workshop on Machine Learning for Signal Processing Sensor Fusion in Siemens Car Navigation System
Ieee Workshop on Machine Learning for Signal Processing Sensor Fusion in Siemens Car Navigation System
复制标题
Ieee 西门子汽车导航系统信号处理传感器融合机器学习研讨会
DOI：
--
复制
发表时间：
--
期刊：
影响因子：
--
通讯作者：
Markus Schupfner
中科院分区：
文献类型：
--
作者：
Dragan Ohradovic;H. Lenz;Markus Schupfner
汽车导航系统主要完成三个任务：定位、路由和导航（制导）。汽车的定位是通过适当地结合来自多个传感器和信息源（包括里程表、陀螺仪、GPS 信息和数字地图）的信息来实现的。本文描述了在商用西门子汽车导航系统中实现的两传感器融合步骤。第一步是里程表、陀螺仪和GPS传感信息的融合。汽车运动的动态模型在卡尔曼滤波器中实现，该滤波器以 GPS 信号为教师。在第二步中，使用可用的数字地图来查找道路上最可能的位置。与当前估计的汽车位置仅投影在道路地图上的数字地图的标准应用相反，本文提出的方法将综合车辆路径的特征与来自数字地图的候选道路的特征进行比较。此外，本文还介绍了实验驱动的结果。所开发的汽车导航系统于2002年被Auto Build杂志评选为十大竞争系统中最优秀的汽车导航系统。
Car navigation systems have three main tasks: positioning, routing and navigation (guidance). Positioning of the car is carried out hy appropriately combining information from several senson and information sources including odometers, gyroscopes, the GPS information and the digital map. This paper describes two-sensor fusion steps implemented in the commercial Siemens car navigation systems. The first step is the fusion of the odometer, gyroscope, and GPS sensory information. The dynamic model of the car movement is implemented in a Kalman Filter, which relays on the GPS signal as a teacher. In the second step the available digital map is used to find the most likely position on the roads. Contrary to the standard application of the digital map where the current estimated car position is just projected on the road map, the herein presented approach compares the features of the integrated vehicle path with the features of the candidate roads from the digital map. In addition, this paper presents the results of the experimental drives. The developed car navigation system was awarded in 2002 by Auto Build magazine as the hest car navigation systems among ten competing systems.