未知环境下移动机器人自主搜索技术研讨.pdfVIP

th Proceedings of the 25 Chinese Control Conference 7-11 August, 2006, Harbin, Heilongjiang 未知环境下移动机器人自主搜索技术研究 肖潇，方勇纯，贺锋，马博军 南开大学机器人与信息自动化研究所,天津,300071 E-mail: mabj@robot.nankai.edu.cn 摘 要: 本文将全区域搜索技术与基于动态模板匹配的目标识别方法相结合，提出了一种适用于未知环境的目标 物体自主搜索方法，实现了移动机器人在陌生环境下的目标搜索任务。具体而言，移动机器人利用声纳和全景摄 像头作为传感器来感知周围环境，并利用模糊逻辑方法来进行局部路径规划，在此基础上通过全区域搜索技术实 现对空间的遍历，并采用动态模板匹配方法来实现目标物体的识别及其方位的确定。本文所提出的目标物体自主 搜索方法可以从任意位置开始进行，算法对于陌生环境具有良好的适应性。论文最后通过实验结果证实了算法的 良好性能。 关键词: 移动机器人系统,模糊逻辑,全区域搜索,动态模板匹配 A Study of Intelligent Searching Mobile Robots under Unknown Environment Xiao X, Fang Y., He F., Ma B. J. Institute of Robotics and Automatic Information Systems, Nankai University, Tianjin, 300071 E-mail: mabj@robot.nankai.edu.cn Abstract: This paper presents an intelligent searching strategy for mobile robots consisting of a fuzzy-logic based searching algorithm over the unknown environments, and a dynamic template matching method to recognize and position the target. Specifically, sonar and omni-directional camera are utilized as sensors to detect the surrounding environments, based on which a fuzzy logic algorithm is adopted for local path planning to achieve a thorough search over the concerned area. Simultaneously, an image processing algorithm referred to as dynamic template matching method is proposed to recognize the target and determine its position. The designed searching strategy possesses various advantages including that it can start from any initial position without any prior requirements, and it exhibits exceptional adaptive abilities over unstructured environments. Experimental results are provided to demonstrate the performanc