English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we present a methodology for constructing data-driven maneuvergeneration models for agile aircraft that can generalize across a wide range oftrim conditions and aircraft model parameters. Maneuver generation models playa crucial role in the testing and evaluation of aircraft prototypes, providinginsights into the maneuverability and agility of the aircraft. However,constructing the models typically requires extensive amounts of real pilotdata, which can be time-consuming and costly to obtain. Moreover, models builtwith limited data often struggle to generalize beyond the specific flightconditions covered in the original dataset. To address these challenges, wepropose a hybrid architecture that leverages a simulation model, referred to asthe source model. This open-source agile aircraft simulator shares similardynamics with the target aircraft and allows us to generate unlimited data forbuilding a proxy maneuver generation model. We then fine-tune this model to thetarget aircraft using a limited amount of real pilot data. Our approachcombines techniques from imitation learning, transfer learning, andreinforcement learning to achieve this objective. To validate our methodology,we utilize real agile pilot data provided by Turkish Aerospace Industries(TAI). By employing the F-16 as the source model, we demonstrate that it ispossible to construct a maneuver generation model that generalizes acrossvarious trim conditions and aircraft parameters without requiring anyadditional real pilot data. Our results showcase the effectiveness of ourapproach in developing robust and adaptable models for agile aircraft.

An Integrated Imitation and Reinforcement Learning Methodology for Robust Agile Aircraft Control with Limited Pilot Demonstration Data