Neural Network Design and Training for Longitudinal Flight Control of a Tilt-Rotor Hybrid Vertical Takeoff and Landing Unmanned Aerial Vehicle

This paper considers a hybrid vertical take-off and landing (VTOL) unmanned aerial vehicle (UAV). By tilting its propellers, the aircraft can transition from rotary-wing (RW) multirotor mode to fixed-wing (FW) mode and vice versa. A novel architecture of a neural network-based controller (NNC) is pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Guillaume Ducard, Gregorio Carughi
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/8/12/727
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850059026110349312
author Guillaume Ducard
Gregorio Carughi
author_facet Guillaume Ducard
Gregorio Carughi
author_sort Guillaume Ducard
collection DOAJ
description This paper considers a hybrid vertical take-off and landing (VTOL) unmanned aerial vehicle (UAV). By tilting its propellers, the aircraft can transition from rotary-wing (RW) multirotor mode to fixed-wing (FW) mode and vice versa. A novel architecture of a neural network-based controller (NNC) is presented. An “imitative learning” approach is employed to train the NNC to mimic the response of an expert but computationally expensive model predictive controller (MPC). The resulting NNC approximates the MPC’s solution while significantly decreasing the computational cost. The NNC is trained on the longitudinal axis. Successful simulations and real flight tests prove that the NNC is suitable for the longitudinal axis control of a complex nonlinear system such as the tilt-rotor VTOL UAV through a sequence of transitions between the RW mode to the FW mode, and vice versa, in a forward flight.
format Article
id doaj-art-fe1665f74f20413796fd09ecba7a4cd8
institution DOAJ
issn 2504-446X
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-fe1665f74f20413796fd09ecba7a4cd82025-08-20T02:50:59ZengMDPI AGDrones2504-446X2024-12-0181272710.3390/drones8120727Neural Network Design and Training for Longitudinal Flight Control of a Tilt-Rotor Hybrid Vertical Takeoff and Landing Unmanned Aerial VehicleGuillaume Ducard0Gregorio Carughi1Laboratoire d’Informatique, Signaux et Systèmes de Sophia Antipolis, Université Côte d’Azur, 06903 Nice, FranceInstitute for Dynamics, Systems and Control (IDSC), ETH Zürich, 8092 Zürich, SwitzerlandThis paper considers a hybrid vertical take-off and landing (VTOL) unmanned aerial vehicle (UAV). By tilting its propellers, the aircraft can transition from rotary-wing (RW) multirotor mode to fixed-wing (FW) mode and vice versa. A novel architecture of a neural network-based controller (NNC) is presented. An “imitative learning” approach is employed to train the NNC to mimic the response of an expert but computationally expensive model predictive controller (MPC). The resulting NNC approximates the MPC’s solution while significantly decreasing the computational cost. The NNC is trained on the longitudinal axis. Successful simulations and real flight tests prove that the NNC is suitable for the longitudinal axis control of a complex nonlinear system such as the tilt-rotor VTOL UAV through a sequence of transitions between the RW mode to the FW mode, and vice versa, in a forward flight.https://www.mdpi.com/2504-446X/8/12/727machine learningimitative learningneural network-based controlunified flight controltilt-rotor VTOL UAVconvertible VTOL UAV
spellingShingle Guillaume Ducard
Gregorio Carughi
Neural Network Design and Training for Longitudinal Flight Control of a Tilt-Rotor Hybrid Vertical Takeoff and Landing Unmanned Aerial Vehicle
Drones
machine learning
imitative learning
neural network-based control
unified flight control
tilt-rotor VTOL UAV
convertible VTOL UAV
title Neural Network Design and Training for Longitudinal Flight Control of a Tilt-Rotor Hybrid Vertical Takeoff and Landing Unmanned Aerial Vehicle
title_full Neural Network Design and Training for Longitudinal Flight Control of a Tilt-Rotor Hybrid Vertical Takeoff and Landing Unmanned Aerial Vehicle
title_fullStr Neural Network Design and Training for Longitudinal Flight Control of a Tilt-Rotor Hybrid Vertical Takeoff and Landing Unmanned Aerial Vehicle
title_full_unstemmed Neural Network Design and Training for Longitudinal Flight Control of a Tilt-Rotor Hybrid Vertical Takeoff and Landing Unmanned Aerial Vehicle
title_short Neural Network Design and Training for Longitudinal Flight Control of a Tilt-Rotor Hybrid Vertical Takeoff and Landing Unmanned Aerial Vehicle
title_sort neural network design and training for longitudinal flight control of a tilt rotor hybrid vertical takeoff and landing unmanned aerial vehicle
topic machine learning
imitative learning
neural network-based control
unified flight control
tilt-rotor VTOL UAV
convertible VTOL UAV
url https://www.mdpi.com/2504-446X/8/12/727
work_keys_str_mv AT guillaumeducard neuralnetworkdesignandtrainingforlongitudinalflightcontrolofatiltrotorhybridverticaltakeoffandlandingunmannedaerialvehicle
AT gregoriocarughi neuralnetworkdesignandtrainingforlongitudinalflightcontrolofatiltrotorhybridverticaltakeoffandlandingunmannedaerialvehicle