Heading Reference‐Assisted Pose Estimation

You are here: Homepage > Search

Heading Reference‐Assisted Pose Estimation

Liu, Xinghua / Jiang, Rui / Chen, Badong / Sam Ge, Shuzhi

In this chapter, heading reference‐assisted pose estimation (HRPE) is proposed to compensate for inherent drift in visual odometry (VO) on ground vehicles, where an estimation error is prone to grow while the vehicle is making turns or in environments with poor features. By introducing a particular orientation as a heading reference , a pose estimation framework is presented to incorporate measurements from heading reference sensors into VO. A graph formulation is then proposed to represent the pose estimation problem under the commonly used graph optimization model. Simulations and experiments on the KITTI data set and our self‐collected sequences have been conducted to verify the accuracy and robustness of the proposed scheme. KITTI sequences and manually generated heading measurements with Gaussian noise are used in the simulations, where rotational drift error is observed to be bounded. Compared with pure VO, the proposed approach greatly reduces the average translational localization error from 153.85 to 24.29 m and 23.80 m in self‐collected stereo visual sequences with traveling distances over 4.5 km at processing rates of 19.7 and 11.1 Hz for the loosely coupled and tightly coupled models, respectively.