用改进的ART-2网络建立移动机器人环境模型的研究

Research on Creating Environment Model for Mobile Robot Using Improved ART-2 Neural Network

  • 摘要: 本文应用自适应共振理论中ART-2神经网络进行移动机器人环境障碍模式识别.ART-2神经网络在处理单方向渐变的模式输入时具有模式漂移的特点,机器人在静态环境中运动依赖这种特点,但在动态环境中模式漂移的特点却会对机器人的安全造成威胁.为此,设计了一种改进的ART-2神经网络,使得移动机器人同时适应在静态和动态环境中安全运动.

     

    Abstract: In the application of ART-2 neural network, it is found that there is a characteristic of pattern drifting when processing the single-direction gradually changing patterns. On one hand,robot depends on the characteristic when moving in static environment,on the other hand,the characteristics may do harm to the safety of robot when moving in dynamic environment. To solve this problem,an improved ART-2 neural network is brought forward which make the robot suitable for moving in static environment as well as in dynamic environment safely.

     

/

返回文章
返回