Adaptive Dynamic Programming Based on Parallel Control Theory for Underwater Vehicles

Parallel control theory can provide an effective solution for the control problem of complex system with unknown models and time-varying characteristics. The adaptive dynamic programming (ADP) method, which combines reinforcement learning and dynamic programming algorithms, is the most advanced method for implementing parallel control theory. In this paper, we systematically review the ADP-based parallel control theory, as well as how it can be developed for underwater vehicles. First, the foundation and fundamental principles of parallel control are outlined in detail. Second, the ADP method under parallel control theory is presented, along with an overview of ADP method in the control of underwater vehicles. At last, we review the latest development and forecast the prospects of ADP-based underwater vehicle parallel control.