摘要
现有多机器人协作构建地图的方法对环境和机器人位置信息有着较高要求,因而在实际应用中存在一定局限性。针对这一问题,提出了一种基于遗传算法的改进方法。该方法采用独立探索、集中建图的探索策略,对环境建立局部栅格地图并予以融合。在地图融合过程中,无须考虑机器人位置信息,而是以栅格地图相似度为度量标准,利用改进的遗传算法快速、高效地搜索各局部地图之间的最大重叠部分,进而予以融合。实验结果验证了该方法的可行性和有效性。
The typical multi-robot map-building approaches have high requirements for environments and robots＇ localization information, so they have certain limitation in practical applications. To solve this problem, this paper proposed a novel im- proved approach. The approach let all robots operate individually and then tried to merge the different local grid maps into a single global one. Without using any pose information of the robots, performed the process of map merging by measuring the similarity between grid maps. It used an improved genetic algorithm to effectively search the＇ maximum overlap at which the lo- cal maps could be joint together. Experimental results show the feasibility and effectiveness of this approach.
出处
《计算机应用研究》
CSCD
北大核心
2009年第4期1289-1291,共3页
Application Research of Computers
基金
国防基础科研资助项目(A1420060159)
关键词
多机器人
复杂环境
地图构建
遗传算法
multi-robot
complex environments
map-building
genetic algorithm
