UAV Model-based Flight Control with Artificial Neural Networks: A Survey
- PDF / 1,123,909 Bytes
- 23 Pages / 595.224 x 790.955 pts Page_size
- 15 Downloads / 154 Views
UAV Model-based Flight Control with Artificial Neural Networks: A Survey Weibin Gu1
· Kimon P. Valavanis1 · Matthew J. Rutherford1 · Alessandro Rizzo2
Received: 5 February 2020 / Accepted: 23 June 2020 © Springer Nature B.V. 2020
Abstract Model-Based Control (MBC) techniques have dominated flight controller designs for Unmanned Aerial Vehicles (UAVs). Despite their success, MBC-based designs rely heavily on the accuracy of the mathematical model of the real plant and they suffer from the explosion of complexity problem. These two challenges may be mitigated by Artificial Neural Networks (ANNs) that have been widely studied due to their unique features and advantages in system identification and controller design. Viewed from this perspective, this survey provides a comprehensive literature review on combined MBC-ANN techniques that are suitable for UAV flight control, i.e., low-level control. The objective is to pave the way and establish a foundation for efficient controller designs with performance guarantees. A reference template is used throughout the survey as a common basis for comparative studies to fairly determine capabilities and limitations of existing research. The endresult offers supported information for advantages, disadvantages and applicability of a family of relevant controllers to UAV prototypes. Keywords Model-based control (MBC) · Artificial neural network (ANN) · Flight control · Hybridization · Unmanned aerial vehicle (UAV)
1 Introduction 1.1 Motivation and Rationale Model-Based Control (MBC) techniques have found great applicability in the controller design for Unmanned Aerial Vehicles (UAVs). This is because control-oriented modeling, being the core of MBC techniques, allows for a systematic way to controller synthesis that basically facilitates the design and development process by reducing the effort to the tuning and calibration processes. Moreover, the focus of MBC techniques is on guaranteeing system stability and performance, improving robustness with respect to uncertainties and disturbances, and finding the optimally designed controller. Recent findings are presented in Feedback Linearization (FL), a.k.a. Nonlinear Dynamic This work is partially supported by an NSF Grant, CMMI-DCSD1728454, Compagnia di San Paolo, and by an Amazon Research Award granted to Dr. A. Rizzo. Weibin Gu
weibin [email protected]
Extended author information available on the last page of the article.
Inversion (NDI) [1], Adaptive Control [2], Model Predictive Control (MPC) [3], Sliding Mode Control (SMC) [4], Backstepping Control [5] and H∞ Robust Control [6]. Despite promising results, a challenge MBC-based designs suffer from, is their dependence on the accuracy of the mathematical model of the real plant [7]. A poorly derived or defined model, due to imprecise system knowledge and ubiquitous exogenous disturbances, may adversely impact subsequent controller synthesis that leads to unacceptable performance or even instability. Such uncertainties and disturbances may be classified as: –
–
–
Parametric u
Data Loading...
