Aiming at the speed of BPnn(BP neural network) is slow and it cannot meet the real-time request in complex multiple input conditions,a method of partitioning BPnn into several smaller subnets in order to obtain more efficient computation is proposed. Using the improved BPnn to the trajectory tracking problem of mobile robot with unknown parameters and interferences,an improved computed-torque control by the integration of a kinematic controller and a dynamic controller is proposed. The kinematic controller is designed by the backstepping technology and the dynamic controller is optimized by the improved BPnn. MATLAB numerical simulations are provided to show the effectiveness and correctness of the suggested approach.%针对BPnn(BP神经网络)在复杂多输入情况下,样本训练速度慢,不能满足实时性要求的缺点,提出了一种把神经网络分割成若干子网分别进行训练来获取更高计算效率的方法.将改进的BPnn应用于移动机器人在未知参数和不确定干扰下的轨迹跟踪控制问题中,提出了一种运动控制器和动力学控制器相结合的改进的计算力矩控制方法,用后退算法设计运动学控制器,用改进的BPnn优化动力学控制器.通过MATLAB数值仿真证明了算法的有效性和正确性.
展开▼
