关节式移动机器人自主越障中基于模糊神经网络的障碍识别方法  

Obstacle Recognition Method Based on Fuzzy-Neuro Network for Articulated Mobile Robot Autonomous Negotiation

作　　者：徐正飞[1] 杨汝清[1] 仲昕[1] 

机构地区：[1]上海交通大学机器人研究所,上海200030

出　　处：《上海交通大学学报》2002年第3期289-292,共4页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金资助项目 ( 6 9975 0 14 )

摘　　要：提出了一种关节式移动机器人自主越障时的障碍识别方法 ,该方法利用模糊神经网络对障碍物进行识别 ,确定障碍的类型和特征 ,并以此来控制移动机器人越障和避障时的行进速度和摆臂的动作 ,开发了在未知环境中障碍物辨识的模糊神经网络系统 .实验证明 。An obstacle recognition approach was presented, which uses fuzzy neuro network to recognize the obstacles and determine the pattern and feature. It is then used to control the obstacle avoidance and negotiation for an articulated mobile robot. A fuzzy neuro network system was developed for the obstacle recognition and negotiation in unknown environment. The feasibility and effectiveness of the proposed method is demonstrated by testing on our experimental articulated mobile robot.

关 键 词：关节式移动机器人 自主越障 模糊神经网络 障碍识别 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]