paper-with-me

Papers

Loss of Control Prevention of an Agile Aircraft: Dynamic Command Saturation Approach

2024-06-03 · Ege Ç. Altunkaya, Akın Çatak, Emre Koyuncu, İbrahim Özkol

The prevention of the loss of control in agile aircraft during the extreme maneuvers is of concern due to the nonlinear aerodynamics and flight dynamics nature of the aircraft in this study. Within this context, the primary objective is to present an architectural framework and elucidate the methodology for its determination. This architecture enables agile maneuvering aircraft to execute more extreme maneuvers while avoiding departure from stable flight, surpassing maneuverability capabilities of conventional state limiters. Hence, the notion of an incremental attainable moment set is introduced for an instantaneous controllability investigation using demanded control moment coefficients derived in the high-level controller, which is the incremental nonlinear dynamic inversion. In the event of detecting a violation of controllability boundaries, Lyapunov-based dynamic command saturation is employed to limit pilot commands, preventing the aircraft from initiating departure from stable flight. As a result, abrupt and excessive pilot inputs are dynamically softened in-flight, and presumable departure tendencies are mitigated. Consequently, the superiority of the proposed method over conventional state limiters is proven through the flight simulations of agile and abrupt maneuvers, as well as Monte Carlo simulations that demonstrate the expansion of stable maneuverable volumes up to 55%.

📄 PDF Abstract BibTeX arXiv:2406.01246

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

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

2023-12-27 · Gulay Goktas Sever, Umut Demir, Abdullah Sadik Satir, Mustafa Cagatay Sahin 외

In this paper, we present a methodology for constructing data-driven maneuver generation models for agile aircraft that can generalize across a wide range of trim conditions and aircraft model parameters. Maneuver genera…

Imitation LearningTransfer Learning

Active Sidestick Control Integration for Enhanced Aircraft Flight Envelope Protection

2024-06-11 · Çağrı Ege Altunkaya, Fatih Erol, Akın Çatak, Volkan Mert 외

The design of Envelope and Pilot-Induced Oscillation (PIO) Protection Features, and Failure Cases detection and prevention using Active Control Sidestick (ACS) is a challenging task. While helping the pilot to respect th…

Early warning signals for loss of control

2025-12-24 · Jasper J. van Beers, Marten Scheffer, Prashant Solanki, Ingrid A. van de Leemput 외 arxiv

Maintaining stability in feedback systems, from aircraft and autonomous robots to biological and physiological systems, relies on monitoring their behavior and continuously adjusting their inputs. Incremental damage can …

Robust Auto-landing Control of an agile Regional Jet Using Fuzzy Q-learning

2023-02-21 · Mohsen Zahmatkesh, Seyyed Ali Emami, Afshin Banazadeh, Paolo Castaldi

A robust auto-landing problem of a Truss-braced Wing (TBW) regional jet aircraft with poor stability characteristics is presented in this study employing a Fuzzy Reinforcement Learning scheme. Reinforcement Learning (RL)…

Q-Learningreinforcement-learningReinforcement Learning (RL)

TempFuser: Learning Agile, Tactical, and Acrobatic Flight Maneuvers Using a Long Short-Term Temporal Fusion Transformer

2023-08-07 · Hyunki Seong, David Hyunchul Shim

Dogfighting is a challenging scenario in aerial applications that requires a comprehensive understanding of both strategic maneuvers and the aerodynamics of agile aircraft. The aerial agent needs to not only understand t…