基于中枢模式发生器的机器人行走控制

Locomotion Control of Quadruped Robot Based on Central Pattern Generators

摘要:

基于中枢模式发生器(central pattern generator,CPG)的动物运动控制机理实现四足机器人AIBO的行走控制.利用Kimura振荡神经元构建CPG分布式控制网络，通过多目标遗传算法优化调整CPG网络中的参数，在AIBO上实现类似动物行走(walk)的行走模式.通过Webots仿真和实体实验，验证所设计的CPG控制网络和控制方法的可行性与有效性.

Abstract:

Central pattern generator (CPG) plays an important role in rhythmic motion of animals and is available for biological motion control studies of robots.In this paper,by using Kimura neuron oscillators,a distributed CPG control network is constructed to realize the locomotion control of quadruped robot AIBO.The parameters of the network are adjusted by multi-object genetic algorithm (MOGA) and an animal-like walking gait of AIBO can be realized.Both simulations in Webots and experiments on real AIBO validate the feasibility and efficiency of the constructed CPG control network.