基于EKF的全景视觉机器人SLAM算法

研究全景视觉机器人同时定位和地图创建（SLAM）问题。针对普通视觉视野狭窄, 对路标的连续跟踪和定位能力差的问题, 提出了一种基于改进的扩展卡尔曼滤波（EKF）算法的全景视觉机器人SLAM方法, 用全景视觉得到机器人周围的环境信息, 然后从这些信息中提取出环境特征, 定位出路标位置, 进而通过EKF算法同步更新机器人位姿和地图库。仿真实验和实体机器人实验结果验证了该算法的准确性和有效性, 且全景视觉比普通视觉定位精度更高。

SLAM algorithm of mobile robot with omnidirectional vision based on EKF

This paper researched the SLAM algorithm of omnidirectional vision robot, and presented an improved simultaneous localization and mapping method based on extended Kalman filter to avoid the disadvantage of general vision, including narrow vision range, low continuous track and positioning precision to landmark. It extracted the environment feature from the environment information around the mobile robot got by onmidirectional vision, then located the landmark, finally, updated the position and attitude of the mobile robot and the map library synchronously by using the EKF algorithm. Simulation results and real robot experiment results indicate the effectiveness and accuracy of the proposed approach, and the better positioning precision than general vision is proved.