The problem addressed in the present paper is the design of a controller based on an evolutionary neural network for autonomous flight in quadrotor systems. The controller's objective is to govern the quadcopter in such a way that it reaches a specific position, bearing on attitude limitations during flight and upon reaching a target. Given the complex nature of quadcopters, an appropriate neural network architecture and a training algorithm were designed to guide a quadcopter toward a target. The designed controller was implemented as a single multi-layer perceptron. On the basis of the quadcopter's current state, the developed neurocontroller produces the correct rotor speed values, optimized in terms of both attitude-limitation compliance and speed. The neural network training was completed using a custom evolutionary algorithm whose design put particular emphasis on the cost function's definition. The developed neurocontroller was tested in simulation to drive a quadcopter to autonomously follow a complex path. The obtained simulated results show that the neurocontroller manages to effortlessly follow several types of paths with adequate precision while maintaining low travel times.
Design and Simulation of a Neuroevolutionary Controller for a Quadcopter Drone / Mariani, M; Fiori, S. - In: AEROSPACE. - ISSN 2226-4310. - ELETTRONICO. - 10:5(2023). [10.3390/aerospace10050418]
Design and Simulation of a Neuroevolutionary Controller for a Quadcopter Drone
Fiori, S
2023-01-01
Abstract
The problem addressed in the present paper is the design of a controller based on an evolutionary neural network for autonomous flight in quadrotor systems. The controller's objective is to govern the quadcopter in such a way that it reaches a specific position, bearing on attitude limitations during flight and upon reaching a target. Given the complex nature of quadcopters, an appropriate neural network architecture and a training algorithm were designed to guide a quadcopter toward a target. The designed controller was implemented as a single multi-layer perceptron. On the basis of the quadcopter's current state, the developed neurocontroller produces the correct rotor speed values, optimized in terms of both attitude-limitation compliance and speed. The neural network training was completed using a custom evolutionary algorithm whose design put particular emphasis on the cost function's definition. The developed neurocontroller was tested in simulation to drive a quadcopter to autonomously follow a complex path. The obtained simulated results show that the neurocontroller manages to effortlessly follow several types of paths with adequate precision while maintaining low travel times.File | Dimensione | Formato | |
---|---|---|---|
aerospace-10-00418-v2.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza d'uso:
Creative commons
Dimensione
1.27 MB
Formato
Adobe PDF
|
1.27 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.