室内移动机器人的视觉定位方法研究

Vision-Based Localization of Indoor Mobile Robot

  • 摘要: 针对地图未知的室内环境下的定位问题,提出了一种基于特征跟踪的视觉里程计方法.利用单目摄像头提取和跟踪环境特征点集,进而根据观测模型利用扩展卡尔曼滤波算法估算出机器人的位姿.办公室环境中的定位实验证明了方法的有效性.

     

    Abstract: This paper proposes a vision-odometer method based on feature tracking to solve the localization problem in indoor environments without a priori map.It extracts and tracks feature point sets in the environment with single camera,and then calculates position and pose of the robot with measurement model and extended Kalman filtering.Experiments in office environment show that the method is effective and efficient.

     

/

返回文章
返回