论文部分内容阅读
利用基于神经网络的复合学习方案实现了机器人操作手末端执行装置的高精度轨迹跟踪.提出了通过对网络输出数据进行补偿以使网络在训练时快速收敛的方法,并推证了广义BP(误差向后传播)算法。它不需要机器人的动力学模型,仿真结果表明,该方法可适用于具有高度非线性和受各种不确定性干扰的复杂系统的控制中。
The high precision trajectory tracking of robot manipulator is realized by using the compound learning scheme based on neural network.The method of compensating the network output data to make the network converge rapidly during training is proposed and the generalized BP (error Backward propagation) algorithm. It does not need the robot’s dynamic model. The simulation results show that this method can be applied to the control of complex systems with highly nonlinear and various uncertainties.