基于迭代观测更新的移动机器人视觉导航  

Mobile Robot Visual Navigation with Iterative Measurement Updating

作　　者：许亚芳 孙作雷[1] 曾连荪[1] 张波[2] 

机构地区：[1]上海海事大学机器辨识与交互研究组,上海201306 [2]中国科学院上海高等研究院,上海201210

出　　处：《信息与控制》2015年第6期739-744,752,共7页Information and Control

基　　金：国家自然科学基金资助项目(61105097;51279098;61401270);上海市教育委员会科研创新项目(13YZ081);上海海事大学创新基金资助项目(GK2013085)

摘　　要：针对移动机器人导航问题,采用视觉导航手段,通过辨识人工特征来获取环境观测基准.利用灰度值方差法检测二维图像特征点,并基于二维到三维的空间逆映射实现视觉特征点从相面坐标到世界坐标的转换,以此建立观测模型,并将其融入贝叶斯数据融合框架.为缓解模型线性化所引入的误差,提出迭代观测更新策略,通过持续优化滤波更新的初始点,提升系统联合后验概率估计的精度,进而改进对机器人位姿与环境基元的状态估计质量.使用搭载了机器视觉的机器人平台在真实环境中进行了轨迹总长为505 m实地实验,验证了本文所提出算法优于传统算法的性能.In this study, we use an algorithm for treating visual features as environmental observations, using a visual navigation technology for mobile robot navigation. 2D visual features are recognized using the gray-value variance method, and their coordinates are transformed from the image-plane frame to a world frame, based on the mapping relation between 2D and 3D space. The procedure results in a measurement model, which is integrated into a Bayesian data fusion framework. To reduce the error stemming from linearization, we pmpose an iterative observation updating strategy. By iteratively rectifying the initial state of the filtering update routine, we improve the accuracy of the estimated joint posterior and the estimate quality of the robot pose and environmental primitive. Furthermore, we carried out a field test, covering a 505 m trajectory in a practical environment using a mobile robot platform mounted with computer vision, and demonstrated that the proposed algorithm outperforms the traditional method.

关 键 词：视觉特征辨识 灰度值方差 迭代观测更新 机器人导航 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]