Digital Commons Network^™

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. …

Orbital Debris Mitigation: Exploring Cubesat Drag Sail Technology, Robinson Raphael

Student Works

In an era marked by remarkable advancements in space exploration and research, the advent of satellite technology has contributed accordingly to the lives of people here on Earth. Through applications that tie into broadband connectivity, weather forecasting, disaster management, etc., the occupancy in orbital domains like Low-Earth Orbit (LEO) only continues to grow. However, the presence of orbital debris emerges as a significant concern, posing threats to both operational satellites and future space missions. Resulting as a consequence due to decades of activities since the launch of Sputnik 1 in 1957, as more countries ventured into space so did the …

State Space Modeling And Estimation Of Flexible Structure Using The Theory Of Functional Connections, Carlo Lombardi, Riccardo Bevilacqua

Student Works

In this work, we present a novel method to model the dynamics of a continuous structure based on measurements taken at discrete points. The method is conceived to provide new instruments to address the problem of flexible dynamics modeling in a spacecraft, where an effective mathematical representation of the non-rigid behavior of the is of critical importance in the design of an effective and reliable attitude estimation and control system. Both the measurements and the model that describes the structure can be affected by uncertainty. The purpose of the developed method is to estimate the position and the velocity of …

Using Machine Learning To Predict Hypervelocity Fragment Propagation Of Space Debris Collisions, Katharine Larsen, Riccardo Bevilacqua

Student Works

The future of spaceflight is threatened by the increasing amount of space debris, especially in the near-Earth environment. To continue operations, accurate characterization of hypervelocity fragment propagation following collisions and explosions is imperative. While large debris particles can be tracked by current methods, small particles are often missed. This paper presents a method to estimate fragment fly-out properties, such as fragment, velocity, and mass distributions, using machine learning. Previous work was performed on terrestrial data and associated simulations representing space debris collisions. The fragmentation of high-velocity fragmentation can be modeled by terrestrial fragmentation tests, such as static detonations. Recently, stereoscopic …

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 …

Predicting Dynamic Fragmentation Characteristics From High-Impact Energy Events Utilizing Terrestrial Static Arena Test Data And Machine Learning, Katharine Larsen, Riccardo Bevilacqua, Omkar S. Mulekar, Elisabetta L. Jerome, Thomas J. Hatch-Aguilar

Student Works

To continue space operations with the increasing space debris, accurate characterization of fragment fly-out properties from hypervelocity impacts is essential. However, with limited realistic experimentation and the need for data, available static arena test data, collected utilizing a novel stereoscopic imaging technique, is the primary dataset for this paper. This research leverages machine learning methodologies to predict fragmentation characteristics using combined data from this imaging technique and simulations, produced considering dynamic impact conditions. Gaussian mixture models (GMMs), fit via expectation maximization (EM), are used to model fragment track intersections on a defined surface of intersection. After modeling the fragment distributions, …

Urban Air Mobility (Uam) Flight Path: Literature Review And Conceptual Design Of Uam Corridor Virtual Lane System Using “Tracks”, Immanuel Bankole

Student Works

As the Urban Air Mobility (UAM) industry grows and becomes more popular, most of the conversations in the public domain are focused on the (electric Vertical Take-off and Landing) eVTOL aircraft and the physical infrastructure that will support these eVTOL aircraft. However, there is a lack of research on UAM traffic management and flight paths taken by aircraft between locations.

The United States (U.S.) Federal Aviation Administration has proposed the use of corridors to minimize the interaction between UAM operations and traditional air traffic as eVTOL aircraft perform flight activities. The government also acknowledges the need for additional structures (such …

Solar Sailing Adaptive Control Using Integral Concurrent Learning For Solar Flux Estimation, Luis Enrique Mendoza Zambrano, Riccardo Bevilacqua

Student Works

In the interest of exploiting natural forces for propellant-less spacecraft missions, this investigation proposes an adaptive control strategy to account for unknown parameters in the dynamic modeling of a reflectivity-controlled solar sail spacecraft. A Lyapunov-based control law along with integral concurrent learning is suggested to accomplish and prove global exponential tracking of the estimated parameters and states of interest, without satisfying the common persistence of excitation condition, which in most nonlinear systems cannot be guaranteed a priori. This involves estimating the solar flux or irradiance from the Sun to account for uncertainty and variation over time in this value. To …

Dual Quaternion Relative Dynamics For Gravity Recovery Missions, Ryan Kinzie, Riccardo Bevilacqua, Seo Dongeun

Student Works

A dual quaternion modeling approach is compared to traditional modeling methods for formation flying spacecraft utilized for gravity recovery missions. A modeling method that has traditionally been used for gravity recovery missions is presented which models the motion of two formation flying spacecraft and a test mass. This is followed by the dual quaternion-based formulation for the equations of motion of the twelve degree-of-freedom coupled relative dynamics of formation flying spacecraft and a test mass. Lastly, utilizing data products from the Gravity Recovery and Climate Experiment Follow-On mission, a comparison of these two modeling methods is presented which proves the …

Experimental Validation Of Inertia Parameters And Attitude Estimation Of Uncooperative Space Targets Using Solid State Lidar, Alessia Nocerino, Roberto Opromolla, Giancarmine Fasano, Michele Grassi, Spencer John, Hancheol Cho, Riccardo Bevilacqua

Student Works

This paper presents an experimental activity aimed at assessing performance of techniques for inertia and attitude parameters estimation of an uncooperative but known space target. The adopted experimental set-up includes a scaled-down 3D printed satellite mock-up, a spherical air bearing and a low-cost solid-state LIDAR. The experimental facility also comprises a motion capture system to obtain a benchmark of the pose (position and attitude) parameters and an ad-hoc designed passive balancing system to keep the centre of mass as close as possible to the centre of rotation. The LIDAR-based 3D point clouds, collected while the target rotates on the spherical …

Fostering Safer Evacuations Aboard Commercial Aircraft: A Problem-Solution Analysis, George Skinner

Student Works

This problem-solution analysis analyzes factors impeding safe and orderly evacuations for the Federal Aviation Administration (FAA). Although rarely used, evacuation procedures are critical for keeping passengers safe during emergency situations. However, there are flaws in these procedures and many factors exist which make aircraft evacuations slow and dangerous. During a situation in which time is of the essence, these impediments can make the difference between an incident and a fatal accident. This report focuses on data gathered through full-scale evacuation simulations and analyzes shortcomings and strengths in three accidents. This information is then compared to current procedures and regulations that …

Noise Reduction Techniques In Commercial Aircraft Cabins, Hashem Hashem

Student Works

Main sources of noise heard inside an aircraft cabin:

• Engines
• Airframe & control surfaces
• Window vibrations
• Passenger announcements & activities.

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 …