【摘要】 针对视觉伺服控制识别速度慢、精度低的问题，提出一种基于反向传播(BP)神经网络和遗传算法的视觉伺服控制算法。该算法对机器人与图象复合雅可比矩阵建模得到初始的BP神经网络视觉伺服控制器，采用遗传算法对控制器的初始权重和阈值进行训练，得到混合优化的视觉控制模型。该算法可以有效地将遗传算法良好的全局搜索能力与BP神经网络的精确局部搜索功能相结合。实验结果表明，收敛速度加快的同时误差下降为原来的4.6%,为机器人控制提供了一种简单有效的方法。更多还原

【Abstract】 Aimed at the problem of slow recognition speed and low precision of vision servo control, a vision servo control algorithm based on the back propagation(BP) neural network and genetic algorithm(GA) is proposed. This algorithm modeled the composite Jacobian matrix of the robot and the image to obtain the initial BP neural network visual servo controller. The genetic algorithm was used to train the initial weight and threshold of the controller, so that a hybrid and optimized visual control model was obtained. This algorithm could effectively combine the good global search ability of GA with the precise local search function of BP neural network. The experimental results show that the error reduces to 4.6%, while the convergence rate speeds up. This paper has provided a simple effective method for the robot control.更多还原