智能机器人系统中局部环境特征的提取

本文基于栅格地图和滚动视窗的控制方法 ,提出了一种提取机器人局部障碍物群环境特征的数据融合新方法 .该方法在多个级别对原始数据进行不同程度的抽象和压缩 ,减少机器人内部模块之间或机器人之间、机器人与控制中心进行通讯的数据量 ,提高系统的动态性能 .同时 ,该方法对复杂环境具有良好的自适应性和实时性 .本文分别列举了仿真实验和物理实验结果 ,表明了机器人采用障碍物群的环境特征提取方法可以成功地完成躲避障碍物和路径规划的任务

A new data fusion method to extract features from the local environment for mobile robot has been developed and implemented. This method, named the group of obstacles, compresses data in a series of levels in order to reduce data quantity for communication between modules in distributed single  robot system, or between all the robots and the central station in multi  robot system. This method based on gird map and active window has strong adaptability and real  time in crowded environment. Enormous simulative and physical experiments are carried out to cope with dynamic environments. Experimental results demonstrate that robot can successfully avoid collision and plan path by using this method in perception of robot.

中国科学院沈阳自动化研究所机器人学研究室基金资助 ( RL 2 0 0 10 )