基于联邦滤波进行立体相机/IMU/里程计运动平台组合导航定位

Mobile Platform Localization by Integration of Stereo Cameras,IMU and Wheel Qdometer Based on Federated Filter

在无GPS信号的受限环境中,基于序列立体影像的运动平台视觉定位精度较高,能够改正航迹推算方法的误差累积,但在纹理贫乏或光照不足的环境下容易定位失败。为提高受限环境下运动平台定位的精度与稳健性,提出一种基于联邦滤波的立体相机、惯性测量单元（inertial measurement unit,IMU）及里程计组合导航方法。该方法在联邦滤波中利用IMU分别同里程计与立体相机构成子滤波器,有效避免立体视觉定位失效而导致的系统定位失败,提高了定位稳健性。地下巷道实验结果证明,所提方法能有效提高运动平台导航定位的精度,并且在立体视觉定位失效的情况下仍能实现连续定位。

In a GPS-denied environment,visual odometry based on sequential stereo images can be applied to correction of accumulated localization errors from dead-reckoning.Visual odometry however,preforms.poorly or even fails under poor texture or illumination conditions.To achieve high precision and robust localization,a federated filter based localization method is proposed that integrates stereo cameras,the IMU,and wheel odometer.The two sub filters in the federated filter,constructed by a IMU integrated with the wheel odometer and stereo cameras provide robust localization when visual odometry fails.Experimental results in an underground field demonstrates robust performance and improvement in localization accuracy.