考虑水下机器人运动控制系统的输入输出均为随时间连续变换的过程量,在过程神经元模型的基础上,结合S函数和预先规划的思想,提出一种过程神经元运动控制模型.在参数学习过程中,引入遍历性的渐变混沌噪声,以增强控制全局的优化能力.海浪和海流外界干扰下机器人仿真实验验证了该方法的有效性,取得了满意的结果.
Both inputs and outputs of autonomous underwater vehicles(AUVs) motion control system are process vector which relates with time.Based on basic process neuron,integrating S function and pre-planning idea,a process neuron control is introduced. At the parameters learning phase,gradually reducing chaotic noise is added to form a powerful globe optimiztion algorithm. The effectiveness of this method is proved by the simulation test with external disturbance of wave and current,and the results are satisfactory.