基于ART神经网络的机器人避碰撞系统  

Adaptive Resonance Theory Based Collision Avoidance System

作　　者：马飞[1] 吴耿锋[1] 武彬[1] 樊建[1] 

机构地区：[1]上海大学计算机学院,上海200072

出　　处：《计算机工程》2005年第2期182-184,共3页Computer Engineering

基　　金：上海市科委基金资助项目(015115042):"基于Internet的远程机器人的研究与开发"

摘　　要：针对机器人避碰撞问题,提出了一种基于ART神经网络的避碰撞系统(ARTCAS)。该系统采用划分区间法来描述障碍物状态,把一个全方位避碰撞问题分解为若干个区间内的避碰撞问题。结合ART神经网络学习新知识而不破坏已有知识的特点,实现了一个具有在线学习和躲避以任意速度任意角度运动的障碍物能力的避碰撞系统。It is important for a robot to acquire adaptive behaviors for avoiding moving obstacles. This paper proposes an ART based Collision Avoiding System (ARTCAS). Adopting ART neural network's characteristic of learning new knowledge without forgetting the old ones, ARTCAS has the ability of online learning. By dividing the obstacle's state into many segments, the whole big problem is decomposed into many sub-problems. The simulation experiment shows that robot can adaptively avoid collision with a single moving obstacle in any speed and any direction.

关 键 词：避碰 神经网络 机器人 系统 分区 障碍物 区间 任意角 碰撞问题 在线学习 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置] G633[自动化与计算机技术—控制科学与工程]