模糊神经网络在智能轮椅避障中的应用  

Application of fuzzy neural networks in intelligentwheelchair ′s obstacles avoiding

作　　者：贾松敏[1] 高立文[1] 樊劲辉[1] 严骏[1] 

机构地区：[1]北京工业大学电子信息与控制工程学院,北京100124

出　　处：《华中科技大学学报（自然科学版）》2013年第5期77-81,共5页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(61175087;61105033);国家教育部留学回国人员科研启动基金资助项目;北京市自然科学基金重点项目(KZ201110005004)

摘　　要：针对传统的基于模糊逻辑的智能轮椅避障方法参数选取依赖设计者经验的问题,提出了一种能够自主学习的模糊神经网络智能轮椅避障控制算法.该算法结合模糊逻辑和神经网络各自的优点,并采用状态控制变量记录全向轮椅的运动状态,解决使用者期望目标方向和轮椅避障方向的选择问题,优化了避障路径,更好地满足用户对智能轮椅的舒适性需求.仿真和实物实验证明:该算法提高了避障的智能性和使用者的乘用舒适性,适用于智能轮椅的避障控制.In traditional method to avoid obstacles for intelligen t wheelchairs,the fuzzy logic based-design of parameters depends on the design er′ experiences.Thus,on the basis of fuzzy neural networks,a self-learning obstacle avoidance algorithm of intelligent wheelchairs was proposed.The algori thm combined fuzzy logic and neural networks with their respective advantages,a nd state control variables were used to record omni-wheelchair state of motion to solve the selection problem of the user expecting target direction and wheelc hair obstacle avoidance direction.Obstacle avoidance path was optimized to bett er meet the needs of the users in the comfort and security of the intelligent wh eelchair.Simulation and physical experiments show that the algorithm improves t he intelligence of obstacle avoidance and comfort of the wheelchair and can be u sed in the wheelchair obstacle avoidance controls.

关 键 词：智能轮椅 避障 模糊神经网络 麦克纳姆轮 状态控制变量 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]