本文以一级倒立摆系统和二级倒立摆系统作为实验平台，针对极点配置中极点不易寻找、LQR控制中权值难于确定和拟人控制从定性到定量转化的瓶颈问题，应用遗传算法对控制器进行参数优化，一方面充分利用各自的优势来共同提高控制器的性能，另一方面将人从费时费力的试凑试验中解脱出来。-In this paper, an inverted pendulum and double inverted pendulum system as the experimental platform, pole for pole configuration is not easy to find, LQR control weight and to be difficult to determine the control of the transformation from qualitative to quantitative bottlenecks, genetic algorithm controller parameter optimization, on the one hand make full use of their advantages to jointly improve the performance of the controller, on the other hand will be from the laborious trial and error testing in earnest.