Neural network based reinforcement learning control of autonomous underwater vehicles with control input saturation
Neural network based reinforcement learning control of autonomous underwater vehicles with control input saturation
复制标题
DOI：
10.1109/control.2014.6915114
复制
发表时间：
2014-07
期刊：
影响因子：
--
通讯作者：
Rongxin Cui;Chenguang Yang;Y. Li;Sanjay K. Sharma
中科院分区：
文献类型：
--
作者：
Rongxin Cui;Chenguang Yang;Y. Li;Sanjay K. Sharma
为了便于数字计算机计算，本文在离散时间内研究了自主式水下航行器（AUV）的轨迹跟踪控制问题。一个强化学习计划，使用两个神经网络，而第一个是补偿控制器的不确定性，第二个是估计的评价函数，使最佳的跟踪性能可以实现的AUV。仿真结果表明，误差收敛到零附近的一个可调邻域，达到了强化学习意义下的优化。
In this paper, the trajectory tracking control of the autonomous underwater vehicle (AUV) has been investigated in discrete time, for ease of digital computer calculation. A reinforcement learning scheme is employed using two neural networks, whereas the first one is to compensate for uncertainties for the controller, and the second one is to estimate the evaluation function, such that optimal tracking performance could be achieve for the AUV. Simulation results show that the errors convergence to a adjustable neighborhood around zero, and optimization has been achieved in the sense of reinforcement learning.