Polynomial regressors based data-driven control for autonomous underwater vehicles
- PDF / 1,056,487 Bytes
- 9 Pages / 595.224 x 790.955 pts Page_size
- 17 Downloads / 232 Views
Polynomial regressors based data-driven control for autonomous underwater vehicles Hongran Li1 · Weiwei Xu1 · Heng Zhang1
· Jian Zhang1 · Yi Liu2
Received: 1 October 2019 / Accepted: 16 January 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract This paper proposes a data-driven control approach on the basis of polynomial regressors for autonomous underwater vehicles (AUVs). In contrast to conventional control approach, data-driven control does not require modeling for the systems. It only utilizes the analysis of massive stored dataset to predict the future control input, which can achieve the future output. Generally, the massive stored dataset can be analyzed by short-length vectors linearly. In this paper, a novel point is the improvement of existing data-driven control by polynomial regressors, which improve the control performance of AUVs. By numerical simulations, we illustrate the effectiveness of our proposed approach. Keywords Data-driven control · Autonomous underwater vehicle · Nonlinear motion control · Polynomial regression vectors
1 Introduction Trajectory tracking is one of the key technologies in underwater operations. It can realize the intelligent control of AUVs, which is a typical nonlinear control system. The state equations of AUVs are complex, and difficult to establish accurate models by mathematical methods. Under the current technology, the nonlinear control problems of AUVs limit the further development of intelligent trajectory tracking control. Data-driven control is a data-based control method, in opposition to model-based, that does not require modeling by mathematical methods [1–7]. It utilizes the analysis of previous records of datasets to calculate the future inputs/outputs so as to achieve the predictive control. Since complex hydrodynamic parameters are difficult to obtain by calculation, The most of control methods are difficult to accurately control the AUVs based on mathematical models. Many scholars have done massive This article is part of the Topical Collection: Special Issue on Emerging Trends on Data Analytics at the Network Edge Guest Editors: Deyu Zhang, Geyong Min, and Mianxiong Dong Heng Zhang
[email protected] 1
Jiangsu Ocean University, Lianyungang, China
2
Ericsson (China) Communication Company Ltd, Beijing, China
research on solving the problems, which arise from nonlinear control system of AUVs. In previous studies, to avoid the modeling problem of nonlinear system, the fuzzy control and self-adaptive control were utilized for trajectory tracking of AUVs. For instance, aiming to improve the stability, robustness and effectiveness of AUVs trajectory tracking control, a fuzzy navigation coefficient was proposed by Peng, that was designed for guidance control of AUVs [8]. A fuzzy modeling and control was proposed for AUVs by Hassanein [9], and a fuzzy-based tracking controller design was proposed by Ban [10]. In addition, adaptive control was also widely used, that did not require a dynamic accurate model. All of the ki
Data Loading...
