基于CPG的仿蟹机器人复杂地形步态生成方法

来源期刊:中南大学学报(自然科学版)2016年第12期

论文作者:王刚 韩金华 韩世凯 陈曦 叶秀芬

文章页码:4070 - 4081

关键词:仿蟹机器人;中枢模式发生器(CPG) ;步态生成;复杂地形

Key words:crablike robot; central pattern generator (CPG); gait generation; complex terrain

摘    要:为了提高仿蟹机器人的复杂环境适应性,提出一种基于生物神经反射机理的自适应复杂地形步态生成方法。首先,采用互抑神经元振荡器构建仿蟹机器人CPG运动控制网络模型;其次,利用具有良好逼近能力的前馈神经网络将CPG输出的节律信号映射为步行足足端轨迹;然后,在CPG模型中引入基于力传感器触发的反射机制,实现了机器人自适应复杂地形步态生成;最后,通过仿蟹机器人复杂地形运动控制的实验研究,验证所提出的基于生物神经反射机理的自适应复杂地形步态生成方法的有效性。

Abstract: In order to improve the environmental adaptability of crablike robot in complex terrain, an adaptive gait generation method for complex terrain was proposed based on biological neural reflex mechanism. Firstly, a CPG network model of the crablike robot was built by mutual inhibition neural oscillator. Secondly, the rhythm signals generated by CPG model were mapped to walking leg trajectory by neural network. Then, the reflection mechanism triggered by force sensor was added to CPG model, to realize the adaptive gait generation for complex terrain. Finally, the motion control experiments of crablike robot in complex terrain were carried out to verify the effectiveness of adaptive gait generation method for complex terrain.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号