Unmanned surface ship optimal trajectory tracking control method based on reinforced learning method

Abstract

The invention provides an unmanned surface ship optimal trajectory tracking control method based on a reinforced learning method. The unmanned surface ship optimal trajectory tracking control method based on the reinforced learning method comprises the following steps: S1, establishing an unmanned surface ship system mathematical model and a desired trajectory system mathematical model without considering a disturbance condition; S2, establishing a dead zone mathematical model, so as to obtain an unmanned surface ship system mathematical model introducing the dead zone; and further obtaining an tracking error system; S3, establishing an identifier system; and S4, evaluating whether the control strategy meets the requirements or not through an optimal cost function; if the control strategymeets the requirements, outputting the control strategy to the unmanned surface ship system as an optimal control strategy; and if the control strategy does not meet the requirements, evaluating whether the regenerated control strategy meets the requirements or not through the optimal cost function, and repeating the above process until the optimal control strategy is obtained and output to the unmanned surface ship system. The invention solves the technical problem that the unmanned ship optimal control method in the prior art does not consider the dead zone or completely unknown system dynamics, and the accuracy and robustness of the control system are reduced.

Description

technical field [0001] The invention relates to the fields of ship control engineering and ship automation navigation, in particular, to an optimal trajectory tracking control method for an unmanned surface ship based on a reinforcement learning method. Background technique [0002] At present, in the field of ship trajectory tracking control, the control method designed to enable unmanned ships to achieve high-precision trajectory tracking is the core content of the research. It can not only enable the safe and effective operation of the unmanned surface vehicle, but also enhance its robustness and complete the established tasks accurately and stably. Common unmanned ship tracking control algorithms include PID, sliding mode, neural network, etc. [0003] Trajectory tracking control system of unmanned surface vessel is a typical nonlinear control system. The traditional solution to the optimal control problem of nonlinear control system is to solve the Hamilton-Jacobi-Bel...

AI Technical Summary

Problems solved by technology

[0021] According to the above proposal, the existing optimal control method based on the reinforcement learning method mainly solves the optimal control of nonlinear systems with known system states, and does not consider unmanned surface vehicles with dead zones or completely unknown system dynamics. Control problems, which lead to the technical problems of reducing the accuracy and robustness of the actual control system, and provide an optimal trajectory tracking control method for unmanned surface vehicles based on reinforcement learning methods

Images