期刊
ROBOTICS
卷 10, 期 1, 页码 -出版社
MDPI
DOI: 10.3390/robotics10010023
关键词
IMU noise; sensor fusion; SLAM; state-estimation; monocular visual-inertial; odometry
类别
资金
- NSERC Discovery Grant
This paper introduces a novel method for visual-inertial odometry for land vehicles, which is robust to variations in terrain and achieves better accuracy than existing fusion methods. The method utilizes epipolar constraints for pose correction and real-time environment mapping.
In this paper, we present a novel method for visual-inertial odometry for land vehicles. Our technique is robust to unintended, but unavoidable bumps, encountered when an off-road land vehicle traverses over potholes, speed-bumps or general change in terrain. In contrast to tightly-coupled methods for visual-inertial odometry, we split the joint visual and inertial residuals into two separate steps and perform the inertial optimization after the direct-visual alignment step. We utilize all visual and geometric information encoded in a keyframe by including the inverse-depth variances in our optimization objective, making our method a direct approach. The primary contribution of our work is the use of epipolar constraints, computed from a direct-image alignment, to correct pose prediction obtained by integrating IMU measurements, while simultaneously building a semi-dense map of the environment in real-time. Through experiments, both indoor and outdoor, we show that our method is robust to sudden spikes in inertial measurements while achieving better accuracy than the state-of-the art direct, tightly-coupled visual-inertial fusion method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据