Generic 4D flight guidance based on differential flatness

International audienceWith the increase of traffic density, it appears of interest to design more versatile guidance systems for civil transportation aircraft. In this paper, a new approach is proposed to design a guidance system able to achieve 4D trajectory tracking. Flight guidance dynamics are shown to be implicit differentially flat with respect to the inertial position of an aircraft. To overcome the numerical difficulty implied by this implicit property, artificial neural networks are introduced to capture the differential relationship between guidance parameters and attitude control inputs. A corrective term is also introduced to take into account the effects of model approximation, neural network errors and disturbances