欠驱动机械臂是一类控制器数目少于系统自由度的非完整系统。针对欠驱动机械臂Acrobot,采用标准BP算法和改进BP算法设计了神经网络平衡控制器,仿真实验结果表明,改进的BP算法能有效地克服标准BP算法的缺陷,使系统的均方误差大大减小,并具有容易实现以及计算量小的优点。
Underactuated manipulator is a non-complete system of which the number of controller is less than the degrees of freedom. The underaetuated manipulator Acrobot, standard-based BP algorithm and improved BP algorithm are applied to design the balance controller of neural network. Simulation results show that the improved BP algorithm can effectively overcome the shortcomings of the standard BP algorithm, and the mean-square errors of the system are significantly reduced, with the advantage of easy implementation and little calculation .