一种基于MAP估计的移动机器人视觉自定位方法

提出一种能够工作在三维路标环境中的视觉自定位系统. 机器人通过 MAP 估计器融合里程计和单向摄象机的图像信息递归估计其自身位姿状态. 本文构建了传感器的非线性模型并且在系统运行中嵌入和跟踪机器人运动和视觉信息的不确定性. 本文从概率几何观点阐述传感信息不确定性, 用 unscented 变换传播经过非线性变换的相关系统信息. 考虑到处理能力, 机器人在地图元素的投影特征附近提取相应图像特征并通过统计距离描述数据关联程度. 本文的一系列系统性实验证明了该系统的稳定性和精确性.

A MAP Approach for Vision-based Self-localization of Mobile Robot

An on-the-fly, self-localization system is developed for mobile robot which is operative in a 3D environment with elaborative 3D landmarks. The robot estimates its pose recursively through a MAP estimator that incorporates the information collected from odometry and unidirectional camera. We build the nonlinear models for these two sensors and maintain that the uncertainty manipulation of robot motion and inaccurate sensor measurements should be embedded and tracked throughout our system. We describe the uncertainty framework in a probabilistic geometry viewpoint and use unscented transform to propagate the uncertainty, which undergoes the given nonlinear functions. Considering the processing power of our robot, image features are extracted in the vicinity of corresponding projected features. In addition, data associations are evaluated by statistical distance.Finally, a series of systematic experiments are conducted to prove the reliable and accurate performance of our system.sor fusion, unscented transformation, uncertainty propaga