Formula Student Driverless (FSD) requires students to design and build a driverless vehicle to race on track, which incurs great demands on the odometry solution. High accuracy odometry plays a significant role in Simultaneous Localization and Mapping (SLAM) and automatic navigation mission. This paper proposes an odometry method based on Camera-Lidar-IMU information fusion and Factor-Graph optimization. It solves the problem of observation of speed and pose transformation in high speed racing scenes with sparse features. Firstly, a YoloV3-tiny object detector is used to identify cone objects captured through camera sensor, which is used to segment the object points from the Lidar pointcloud. Then, the object points are registered by utilizing the inertial measurement unit (IMU) pre-integration result as rough estimation, to obtain increment of pose transformation in horizontal plane. And a Ground Normal Vector Registration method is developed using ground points to solve increment of vertical pose transformation. These two transformation results are coupled to get a real-time odometry. At last, the odometry results and observations are optimized at the back-end with the Factor-Graph algorithm. Experiments show that the method presented in this paper performs well in real environment, and achieves high accuracy and provides a good reference for vehicle SLAM and navigation.

公式学生无人驾驶（FSD）要求学生设计和制造无人驾驶车辆以在赛道上行驶，这对里程表解决方案提出了很高的要求。高精度里程计在同时定位和制图（SLAM）和自动导航任务中起着重要作用。提出了一种基于Camera-Lidar-IMU信息融合和因子图优化的测距方法。它解决了在具有稀疏特征的高速赛车场景中观察速度和姿势变换的问题。首先，YoloV3-tiny对象检测器用于识别通过摄像头传感器捕获的圆锥对象，该对象用于分割来自激光雷达点云的对象点。然后，通过将惯性测量单元（IMU）的预积分结果用作粗略估计来记录目标点，以获得水平面姿态变换的增量。并利用地面点开发了地面法向矢量配准方法，以解决垂直姿态变换的增量。将这两个转换结果耦合在一起以获得实时里程表。最后，通过因子图算法在后端优化里程计结果和观测值。实验表明，本文提出的方法在真实环境下表现良好，精度较高，为车辆SLAM和导航提供了很好的参考。里程图结果和观测值在后端使用Factor-Graph算法进行了优化。实验表明，本文提出的方法在真实环境下表现良好，精度较高，为车辆SLAM和导航提供了很好的参考。里程图结果和观测值在后端使用Factor-Graph算法进行了优化。实验表明，本文提出的方法在真实环境下表现良好，精度较高，为车辆SLAM和导航提供了很好的参考。