摘要： 针对当前多数SLAM数据关联算法存在不能在线修正的问题，提出一种使用动态阈值的启发式图搜索数据关联算法。该方法使用回溯机制实现对错误数据的修正，在搜索过程中使用动态阈值进行门限过滤，减少可能的数据关联的数目，在不降低数据关联正确率的情况下，提高数据关联效率。仿真实验结果表明，该算法可有效地降低运算时间。

关键词: 数据关联, 启发式图搜索, 动态阈值, 在线修正, 回溯

Abstract: Aiming at the problem that most of data association algorithm can’t amend past error associations on line, this paper presents a heuristic graph search algorithm which uses dynamic threshold. The algorithm uses recall to reach amend past error associations and uses dynamic threshold to reduce the number of probable data association. The algorithm doesn’t lower the accuracy of data association but raise the efficiency of data association. Experimental result shows that the algorithm takes less times.

Key words: data association, heuristic graph search, dynamic threshold, correction on line, recall

中图分类号: 

• TP301.6