论文部分内容阅读
采用遗传算法搜索单步周期和单步步长组成的参数空间获得最优的参数组合,以实现双足机器人稳定和低耗行走。首先是通过基于倒立摆理论规划机器人的各关节位置曲线,来驱动CATIA和ADAMS软件建立机器人三维模型,进而建立稳定性和能效性函数,然后通过均值自适应法实现权重分配来实现两个目标函数的综合,并采用一种新的适应度定义形式设计适应度函数,最后应用遗传算法获得最优解,仿真结果表明,稳定性和能耗性能有了明显的改善。
Genetic algorithm is used to search the parameter space consisting of single-step cycle and single-step step to obtain the optimal combination of parameters to achieve stable and low-cost walk of biped robot. The first is to set up the robot’s 3D model by planning the robot’s joint position curve based on the inverted pendulum theory, and then establish the stability and energy efficiency function, and then realize the two objective functions through the mean-adaptive method to realize the weight distribution. The fitness function is designed by a new form of fitness definition. Finally, the genetic algorithm is used to obtain the optimal solution. The simulation results show that the stability and energy consumption performance have been significantly improved.