计算机与现代化

• 人工智能 • 上一篇    下一篇

基于改进模糊自适应扩展卡尔曼滤波的机器人SLAM算法

  

  1. 河海大学物联网工程学院,江苏常州213022
  • 收稿日期:2013-12-02 出版日期:2014-03-24 发布日期:2014-03-31
  • 作者简介:王楚(1989-),女,江苏扬州人,河海大学物联网工程学院硕士研究生,研究方向:机器人SLAM; 倪建军(1978-),男,安徽黄山人,副教授,硕士生导师,博士,研究方向:神经网络,多机器人系统; 殷霞红(1989-),女,江苏泰州人,硕士研究生,研究方向:多机器人。
  • 基金资助:
    国家自然科学基金资助项目(61203365); 江苏省自然科学基金资助项目(BK2012149); 中央高校基本科研业务费专项基金资助项目(2011B04614)

Robot Simultaneous Localization and Mapping AlgorithmBased on Improved Fuzzy Adaptive Kalman Filter

  1. College of Internet of Things Engineering, Hohai University, Changzhou 213022, China
  • Received:2013-12-02 Online:2014-03-24 Published:2014-03-31

摘要: 机器人SLAM问题是目前机器人研究领域中的重点,如何减少定位误差,有效地改善算法的鲁棒性,提高机器人定位和地图创建的准确性是研究的关键。针对这个问题,本文提出一种基于改进模糊自适应扩展卡尔曼滤波的SLAM算法,通过模糊自适应控制模型控制系统噪声和观测噪声。仿真实验结果表明,本文算法有效地解决卡尔曼滤波器的发散问题,可以有效减少机器人定位误差。

关键词: SLAM问题, 定位误差, 模糊自适应控制模型, 机器人

Abstract: Robot simultaneous localization and mapping (SLAM) problem is a very important issue in the robotic field. The main tasks of SLAM include how to reduce the localization error, improve the robustness of the algorithms effectively and improve the accuracy of robot simultaneous localization and mapping. Aim at this problem, an improved fuzzy adaptive extended Kalman filter (EKF) is proposed. In the proposed approach, a fuzzy adaptive control model is used to adjust the system noise and observation noise. Finally, some simulation experiments are conducted, and the experimental results show that the proposed approach can solve the divergence of Kalman filter and reduce the robot localization error effectively.

Key words: SLAM problem, localization error, fuzzy adaptive control model, robot

中图分类号: