Camera-odometer calibration and fusion using graph based optimization

	Camera-odometer calibration and fusion using graph based optimization
	He YJ(贺一家)1,2 ; Guo Yue(郭跃)1,2 ; Ye Aixue(叶爱学)1,2 ; Yuan Kui(原魁)1,2
	2018-03
会议名称	2017 IEEE International Conference on Robotics and Biomimetics (ROBIO)
会议日期	2017-12
会议地点	澳门
摘要	Monocular visual odometry (vo) estimates the camera motion only up to a scale which is prone to localization failure when the light is changing. The wheel encoders can provide metric information and accurate local localization. Fusing camera information with wheel odometer data is a good way to estimate robot motion. In such methods, calibrating camera-odometer extrinsic parameters and fusing sensor information to perform localization are key problems. We solve these problems by transforming the wheel odometry measurement to the camera frame that can construct a factor-graph edge between every two keyframes. By building factor graph, we can use graph-based optimization technology to estimate camera odometer extrinsic parameters and fuse sensor information to estimate robot motion. We also derive the covariance matrix of the wheel odometry edges which is important when using graph-based optimization. Simulation experiments are used to validate the extrinsic calibration. For real-world experiments, we use our method to fuse the semi-direct visual odometry (SVO) with wheel encoder data, and the results show the fusion approach is effective.
关键词	Sensor Fusion Localization
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/21066
专题	智能制造技术与系统研究中心_智能机器人
作者单位	1.中国科学院自动化研究所 2.中国科学院大学
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	He YJ,Guo Yue,Ye Aixue,et al. Camera-odometer calibration and fusion using graph based optimization[C],2018.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
08324650.pdf（354KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载