An efficient neural network approach to tracking control of an autonomous surface vehicle with unknown dynamics

• Published in: Expert systems with applications Vol. 40; no. 5; pp. 1629 - 1635
• Main Authors: Pan, Chang-Zhong, Lai, Xu-Zhi, Yang, Simon X., Wu, Min
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.04.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Autonomous; Autonomous surface vehicles; Computer science; control theory; systems; Computer simulation; Control theory. Systems; Exact sciences and technology; Learning; Lyapunov stability; Neural networks; Nonlinear dynamics; Robotics; Robots; Surface vehicles; Tracking control; Unknown dynamics; Vehicles; Lyapunov stability; Autonomous surface vehicles; Tracking control; Unknown dynamics; Neural networks; Robots; Autonomous system; Uncertainty; Tracking; Error estimation; Moving robot; Lyapunov method; Vehicle dynamics; Robotics; Remote teaching; Uncertain system; Indirect method; Efficiency; Off line; Learning algorithm; Stability; Neural network; Distributed control; Tracking(movable target); Non linear effect; Motion control; Artificial intelligence; Lyapunov function
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2012.09.008

► The tracking control problem of autonomous surface vehicles is addressed. ► An efficient neural network approach is proposed for real-time tracking control. ► The network has a single-layer structure by utilising vehicle regressor dynamics. ► The learning algorithm derived from Lyapunov stability analysis is efficient. ► Satisfactory tracking performance is achieved through on-line learning. This paper proposes an efficient neural network (NN) approach to tracking control of an autonomous surface vehicle (ASV) with completely unknown vehicle dynamics and subject to significant uncertainties. The proposed NN has a single-layer structure by utilising the vehicle regressor dynamics that expresses the highly nonlinear dynamics in terms of the known and unknown dynamic parameters. The learning algorithm of the NN is simple yet computationally efficient. It is derived from Lyapunov stability analysis, which guarantees that all the error signals in the control system are uniformly ultimately bounded (UUB). The proposed NN approach can force the ASV to track the desired trajectory with good control performance through the on-line learning of the NN without any off-line learning procedures. In addition, the proposed controller is capable of compensating bounded unknown disturbances. The effectiveness and efficiency are demonstrated by simulation and comparison studies.