基于径向基神经网络的环境建模方法
首发时间:2017-09-19
摘要:为解决移动机器人对未知环境建模的问题,本文提出一种以径向基神经网络为基础,建立连续栅格地图的方法。首先利用机器人测距传感器得到的距离信息,以及定位系统得到的位置信息计算得到的占据点来训练径向基神经网络,然后建立空白栅格图,把每个栅格中心点坐标输入网络以得到连续的栅格地图。与传统栅格地图相比,该方法用非离散量来表示栅格占据状态,可以提供任意分辨率的地图,其次它可以捕获障碍物之间的自然的统计关系,从而有更好的鲁棒性和泛化能力。本文利用Matlab进行仿真验证,实验证明该方法可以对环境精确建模,且速度较快。
For information in English, please click here
A ENVIRONMENT MODELING METHOD BASED ON RADIAL BASIS FUNCTION NEURAL NETWORK
Abstract:In order to solve the problem of modeling the unknown environment of mobile robot, a method of building continuous occupancy map based on radial basis function neural network is proposed. The training data is calculated by both the distance information and the position information gathering by robot sensor, and we use this data to train radial basis function neural network. And then we use the center coordinates of each grid input network to obtain continuous grid map. Compared with the traditional occupancy map, the method does not need to represent the amount of discrete grid occupied state, can provide any resolution of the map, then it can capture the statistical relationship between the obstacles of nature, which has better robustness and generalization ability. In this paper, Matlab is used to verify the simulation results. The experiment shows that the method can model the environment accurately, and the speed is faster.
Keywords: radial basis function neural network;occupancy map;environment modeling
基金:
引用
No.****
同行评议
共计0人参与
勘误表
基于径向基神经网络的环境建模方法
评论
全部评论0/1000