Gene

Control (management)

Step response

Engineering

Marine engineering

Control engineering

Robustness (evolution)

Unmanned surface vehicle

Singularity

Biochemistry

Computer science

Initialization

Settling time

Physics

Trajectory

Mathematics

Astronomy

sort

Underactuation

Mathematical analysis

Artificial intelligence

Information retrieval

Chemistry

Programming language

Control theory (sociology)

Artificial neural network

IEEE Transactions on Neural Networks and Learning Systems

This article is concerned with the fast and accurate trajectory tracking control problem for a sort of underactuated surface vehicle under model uncertainties and environmental disturbances. A novel neural networks (NNs)-based prescribed performance control strategy is proposed to solve the problem. In the control design, a new type of performance function is constructed which provides a way to predefine the settling time and accuracy, straightforward. Then, a pair of barrier functions are employed to combat not only the position error but also the virtual control input. This evades the possible singularity or discontinuity of the control solution. Next, an initialization technique is exploited, removing the requirement for the initial condition of the control system. Finally, two NNs are employed to deal with the unknown ship nonlinearities. The performance analysis not only demonstrates the effectiveness of the proposed approach but also reveals its robustness against disturbances and unknown reference trajectory derivatives. There is, thus, no need to acquire such knowledge or employ specialized tools to handle disturbances. The theoretical findings are illustrated by a simulation study.

Neural Network Control of Underactuated Surface Vehicles With Prescribed Trajectory Tracking Performance