Document Type
Conference Item
Publication Date
11-1-2010
Abstract
Designing a reliable flight control for an autonomous helicopter requires a high performance dynamics model. This paper studies the recurrent neural network nonlinear model identification of a small scale helicopter. We have selected a Nonlinear AutoRegressive with eXogenous Inputs Series- Parallel (NARXSP) network model which identifies the dynamics model of an unmanned aerial helicopter from real flight data. The identification process is conducted by using the well known Levenberg-Marquardt learning algorithm. The obtained dynamics model shows good fitness with the actual data. This accuracy might be used to realize a reliable flight control for an autonomous helicopter.
Keywords
Dynamics model, Recurrent Neural Network (RNN), System Identification, Small-Scale Helicopter
Event Title
Trends in Electronics Conference
Event Location
Fukuoka, Japan
Event Dates
21-24 Nov 2010
Event Type
conference