首页> 外文会议>International Conference on Mechatronics and Information Technology >Mobile Robot GPS/DR Integrated Navigation Positioning Technique Research
【24h】

Mobile Robot GPS/DR Integrated Navigation Positioning Technique Research

机译:移动机器人GPS / DR集成导航定位技术研究

获取原文

摘要

GPS is widely used for global positioning system. But GPS signal is easily interrupted when it is used alone. DR (dead reckoning) can calculate the position of mobile robots by using direction and speed sensors. However, DR system error can accumulate over time due to the error of electronic compass and odometer sensors. So DR system can't be used separately for a long time. The integrated navigation system combined GPS with DR will effectively integrated advantages of these two systems, higher positioning precision and reliability. In this paper Kalman filter model for GPS/DR integrated navigation system is set up to filter the GPS and DR data. And then the outputs of Kalman filter are inputted to a BP neural network for training. BP neural network is employed to predict next sampling time GPS output and a new Kalman filter based data fusion method is proposed to do the navigation information fusion with encoders and compass system. Simulation is done to validate the proposed fusion method. The simulation result shows the potential of this fusion method for outside used mobile robot navigation. Finally experiments are done to validate the proposed fusion method.
机译:GPS广泛用于全球定位系统。但是,当单独使用时,GPS信号很容易中断。 DR(DEAD RECKONING)可以使用方向和速度传感器来计算移动机器人的位置。然而,由于电子罗盘和里程表传感器的错误,系统误差会随着时间的推移累积。所以DR系统不能长时间单独使用。集成导航系统组合GPS与DR将有效地集成了这两个系统的优点,较高的定位精度和可靠性。在本文中,GPS / DR集成导航系统的Kalman滤波器模型可设置以过滤GPS和DR数据。然后将卡尔曼滤波器的输出输入到BP神经网络以进行训练。 BP神经网络用于预测下一个采样时间GPS输出,并提出了一种新的卡尔曼滤波器的数据融合方法,用于使用编码器和罗盘系统进行导航信息融合。仿真是为了验证所提出的融合方法。仿真结果表明,这种融合方法的潜力用于外部使用的移动机器人导航。最后进行实验以验证所提出的融合方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号