Commercial Space Operations Commons^™

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

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, …

Self-Acquisition Of Liquid Propellant Versatile Arsenal Of Resources Endeavour (S.A.L.V.A.R.E.), Vittorio Baraldi, Nikki Smith-Cielo, Sotirios Zormpas

Student Works

Unlocking the mysteries of Mars’s past and future habitability is just within humanity’s grasp. With a multitude of inherent similarities to Earth, Mars is one of the most promising locations to extend humankind’s reach in manned space exploration. As humanity is at the summit of taking the next leap for mankind by preparing the first crewed missions to Mars, a need that must be met is to significantly reduce the mass necessary to deliver to the surface.

The Self-Acquisition of Liquid propellant Versatile Arsenal of Resources Endeavour (SALVARE) project details a mission for creating the first Mars water-based In-Situ Resources …

Comprehensive Report On Extraterrestrial Resource Extraction, Robinson Raphael

Student Works

The prospect of asteroid mining provides a plethora of riches that include metals and water. As the number of discovered asteroids continues to grow, opportunities arise to commercialize these resources within Near-Earth Asteroids (NEAs). With urgent applications on Earth and in space, NEAs allow for a surge in sales. Planning forward, Astroider Aerospace Systems follows a mission split into four phases. Phase 1 develops a series of spacecraft using existing technologies, titled as Near-Earth Asteroid Miners and Near-Earth Asteroid Surveyors. Phase 2 first launches the surveyors to candidate NEAs, prospecting them for ores. To identify potential celestial bodies for this …