基于单目视觉的SLAM算法研究

利用一种新型的人工路标系统-MR二维码,提出了基于单目视觉和里程计的SLAM方法.首先介绍了MR二维码系统,然后在对机器人运动模型和视觉传感器观测模型进行分析和验证的基础上,给出了一种实用的里程计位置估计误差模型.机器人移动过程中,利用扩展卡尔曼滤波器对视觉信息与里程计信息进行融合.在室内环境下进行了实际实验,实验结果表明该算法可提高机器人定位和构建地图的精度,验证了算法的有效性.

A VISUAL SLAM ALGORITHM BASED ON MONOCULAR VISION

This paper presents a monocular vision and odometer based SLAM algorithm, making use of a novel artificial landmark which is called MR (Mobile Robot) code. A brief introduction of MR code system is given. A practical error model for odometric position estimation is proposed on the basis of analysis and verification of the motion model and observation model. During the movement of the robot, visual information is fused with odometric information by extended Kalman filter. An actual experiment is carried out in indoor environment, and experimental results verify the effectiveness of the algorithm.