Identification and control of a Tail-Sitter Unmanned Aerial Vehicle

Abstract

Unmanned aerial vehicles (UAVs) are increasingly employed in domains such as military operations, search-and-rescue missions, and surveillance. Recent research efforts have sought to integrate the advantages of fixed-wing and rotor-wing aircraft. Tail-sitter UAVs represent a class of hybrid platforms that combine rotor-wing vertical take-off and landing with fixed-wing forward-flight capability. These vehicles operate in three flight modes: vertical, horizontal, and transition. Depending on the transition mechanism, tail-sitter UAVs can be classified as mono-thrust transitioning (MTT), collective-thrust transitioning (CTT), or differential-thrust transitioning (DTT). Despite their potential, tail-sitter UAVs present substantial challenges in aerodynamic design and flight control, particularly with respect to instability and sensitivity to external disturbances. To address these issues, this work proposes an approach grounded in artificial intelligence and adaptive control principles. In particular, neural networks with tunable parameters, including inputs, weights, and transfer functions, are employed to enhance system robustness across varying operating conditions. Smart citations: https://scite.ai/reports/10.61467/2007.1558.2026.v17i1.1230 Dimensions.Open Alex.