Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 4 of 4
Full-Text Articles in Engineering
Six-Degree-Of-Freedom Optimal Feedback Control Of Pinpoint Landing Using Deep Neural Networks, Omkar S. Mulekar, Hancheol Cho, Riccardo Bevilacqua
Six-Degree-Of-Freedom Optimal Feedback Control Of Pinpoint Landing Using Deep Neural Networks, Omkar S. Mulekar, Hancheol Cho, Riccardo Bevilacqua
Student Works
Machine learning regression techniques have shown success at feedback control to perform near-optimal pinpoint landings for low fidelity formulations (e.g. 3 degree-of-freedom). Trajectories from these low-fidelity landing formulations have been used in imitation learning techniques to train deep neural network policies to replicate these optimal landings in closed loop. This study details the development of a near-optimal, neural network feedback controller for a 6 degree-of-freedom pinpoint landing system. To model disturbances, the problem is cast as either a multi-phase optimal control problem or a triple single-phase optimal control problem to generate examples of optimal control through the presence of disturbances. …
Stability Of Deep Neural Networks For Feedback-Optimal Pinpoint Landings, Omkar S. Mulekar, Hancheol Cho, Riccardo Bevilacqua
Stability Of Deep Neural Networks For Feedback-Optimal Pinpoint Landings, Omkar S. Mulekar, Hancheol Cho, Riccardo Bevilacqua
Student Works
The ability to certify systems driven by neural networks is crucial for future rollouts of machine learning technologies in aerospace applications. In this study, the neural networks are used to represent a fuel-optimal feedback controller for two different 3-degree-of-freedom pinpoint landing problems. It is shown that the standard sum-ofsquares Lyapunov candidate is too restrictive to assess the stability of systems with fuel-optimal control profiles. Instead, a parametric Lyapunov candidate (i.e. a neural network) can be trained to sufficiently evaluate the closed-loop stability of fuel-optimal control profiles. Then, a stability-constrained imitation learning method is applied, which simultaneously trains a neural network …
Alternatives To Reducing Aviation Fuel-Burn With Technology: Fully Electric Autonomous Taxibot, Denzil Neo
Alternatives To Reducing Aviation Fuel-Burn With Technology: Fully Electric Autonomous Taxibot, Denzil Neo
Student Works
Aircraft taxiing operations in the aerodrome were identified to consume the most jet fuel apart from the cruise phase of the flight. This was also well supported by various research associating taxi operations at large, congested airports, with high jet fuel consumption, high carbon emissions, and noise pollution. Existing literature recognised the potential to address the environmental issues of aerodrome taxi operations by operating External or Onboard Aircraft Ground Propulsion Systems (AGPS). Designed to power aircraft with sources other than their main engines, external Aircraft Ground Power Systems (AGPS) have shown the potential to significantly cut jet fuel consumption and …
Certification Basis For A Fully Autonomous Uncrewed Passenger Carrying Urban Air Mobility Aircraft, Steve Price
Certification Basis For A Fully Autonomous Uncrewed Passenger Carrying Urban Air Mobility Aircraft, Steve Price
Student Works
The Urban Air Mobility campaign has set a goal to efficiently transport passengers and cargo in urban areas of operation with autonomous aircraft. This concept of operations will require aircraft to utilize technology that currently does not have clear regulatory requirements. This report contains a comprehensive analysis and creation of a certification basis for a fully autonomous uncrewed passenger carrying rotorcraft for use in Urban Air Mobility certified under Title 14 Code of Federal Regulations Part 27. Part 27 was first analyzed to determine the applicability of current regulations. The fully electric propulsion system and fully autonomous flight control system …