摘要
该文研究了部分结构化室内环境中自主移动机器人同时定位和地图构建问题.基于激光和视觉传感器模型的不同,加权最小二乘拟合方法和非局部最大抑制算法被分别用于提取二维水平环境特征和垂直物体边缘.为完成移动机器人在缺少先验地图支持的室内环境中的自主导航任务,该文提出了同时进行扩展卡尔曼滤波定位和构建具有不确定性描述的二维几何地图的具体方法.通过对应用于SmartROB-2移动机器人平台所获得的实验结果和数据的分析讨论,论证了所提出方法的有效性和实用性.
Localization and map building are two essential tasks for an autonomous mobile robot＇s indoor navigation without a priori map. This paper provides a method for mobile robot indoor simultaneous localization and mapping using laser range finder and monocular vision. Due to variant sensor modeling for laser range finder and CCD camera, weighted least square fitting and non-local maximum suppression algorithm are used to extract certain 2- D horizontal environmental features and vertical edges respectively. We also present an approach to complete EKF localization and metric map building simultaneously based on the result of lines merging and feature fusion. Experiment results with the SmartROB-2 mobile robot and data analysis show the method＇s validity and practicability.
出处
《自动化学报》
EI
CSCD
北大核心
2005年第6期925-933,共9页
Acta Automatica Sinica
基金
中科院沈阳自动化所机器人学重点实验室基金(RL200204)和辽宁省高等学校学科拔尖人才基金(2003-54)资助
关键词
同时定位和地图构建
自主移动机器人
扩展卡尔曼滤波
不确定性描述
Simultaneous localization and mapping （SLAM）, autonomous mobile robots,extended Kalman filter （EKF）, uncertainty representation
