【摘要】 多机器人建图是实现机器人自主导航,完成复杂智能任务的关键.其中如何将不同机器人采集的数据融合到全局地图中,成了多机器人建图中的一个核心问题.文中采用独立探索、集中建图的探索策略,提出一种基于改进差异进化算法的多机器人概率栅格地图的融合.该算法在地图相似度的概念基础上,建立相异度函数,利用改进的进化算法搜索策略快速地搜索各局部地图之间的最大重叠部分,实现了多机器人系统栅格地图的融合,有效的解决了相对位置未知情况下的地图创建问题.通过实验验证了该方法正确、可行.更多还原

【Abstract】 Map building for multi-robot is very important to accomplish autonomous navigation and other complex intelligent tasks,and the core question of multi-robot mapping is how to integrate the data of the different robots into a single global map.A novel approach to occupancy grid map merging for multi-robot based on differential evolution was presented.The approach let all robots operate individually and then tried to merge the different local grid maps into a single global one.On the basis of the similarity metric and dissimilarity function,the improved differential evolution algorithm were used to effectively search the maximum overlapping region at which the local maps can be joined together.,and the map building in complex environments was realized without any knowledge about their relative positions.Experimental results show the effectiveness and feasibility of our approach.更多还原