基于神经网络的进化机器人路径规划方法研究
首发时间:2009-01-15
摘要:针对动态、未知环境下移动机器人路径规划,利用神经网络构建移动机器人传感器输入和执行器输出之间的映射关系,提出了一种基于递归神经网络的进化机器人路径规划算法,该算法利用基于实数编码的多种群并行遗传算法进化神经网络权值,给出了算法的具体步骤,并与基于标准前馈网络的路径规划方法进行了比较。通过仿真实验证明该算法是行之有效的。
For information in English, please click here
Research on Path Planning for Evolutionary Robots Based on Neural Network
Abstract:To investigate path planning for mobile robot in dynamic and unknown environments, the mapping relation is constructed between input of sensors and output of actuator based on neural network in this paper. An algorithm of path planning is presented based on recurrent neural network for evolutionary robots. The weights of neural network are evolved via real-coded-based multi-population parallel genetic algorithm. The detailed process to apply the algorithm is presented. And the algorithm is compared with standard feed-forward networks-based method of path planning. The experimental results indicate that the proposed approach is feasible.
Keywords: Evolutionary Robotics Path Planning Parallel Genetic Algorithms Recurrent Neural Networks
论文图表:
引用
No.2787537878012320****
同行评议
勘误表
基于神经网络的进化机器人路径规划方法研究
评论
全部评论0/1000