基于环境特征的SLAM算法分析与评价  

Analysis and Evaluation of SLAM Algorithm Based on Environmental Characteristics

作　　者：吕权 李文至 籍颖[1] 

机构地区：[1]河北农业大学信息科学与技术学院,河北保定

出　　处：《软件工程与应用》2017年第5期135-144,共10页Software Engineering and Applications

基　　金：河北省教育厅项目(QN2014095);国家留学基金委资助。

摘　　要：为了研究机器人的SLAM算法在不同环境下的适应能力,以实验仿真数据为依据,对当前普遍存在的几种SLAM算法在Matlab软件中进行仿真对比分析。首先对EKF-SLAM算法和 UKF-SLAM算法进行比较分析,分析结果表明:UKF-SLAM算法相对于EKF-SLAM算法在不同的几种环境特征中具有较好的时间复杂性和鲁棒性。再将性能较好的UKF-SLAM算法与Fast SLAM算法仿真对比,仿真结果表明:在相对大环境和强噪声环境中,Fast SLAM算法具有较好的估计性能,同时时间复杂性低。In order to study robot SLAM algorithm of adaptive capacity in different environments, based on the experimental simulation data, this paper presents the simulation and comparison of several kinds of robot algorithms in Matlab software. First comparing analysis of EKF-SLAM and UKF-SLAM algorithms, analysis results show that UKF-SLAM algorithm with respect to the EKF-SLAM algorithm in different environments has better time complexity and robustness. Then comparing UKF-SLAM algorithm with better performance and Fast SLAM algorithm simulation, the simulation results show that, under the relative environment and the strong noise environment, Fast SLAM algorithm has better estimation performance, while time complexity is low.

关 键 词：机器人 SLAM 环境特征 

分 类 号：TP2[自动化与计算机技术—检测技术与自动化装置]