Open Access. Powered by Scholars. Published by Universities.®
- Institution
Articles 1 - 4 of 4
Full-Text Articles in Engineering
A Reinforcement Learning Approach To Spacecraft Trajectory Optimization, Daniel S. Kolosa
A Reinforcement Learning Approach To Spacecraft Trajectory Optimization, Daniel S. Kolosa
Dissertations
This dissertation explores a novel method of solving low-thrust spacecraft targeting problems using reinforcement learning. A reinforcement learning algorithm based on Deep Deterministic Policy Gradients was developed to solve low-thrust trajectory optimization problems. The algorithm consists of two neural networks, an actor network and a critic network. The actor approximates a thrust magnitude given the current spacecraft state expressed as a set of orbital elements. The critic network evaluates the action taken by the actor based on the state and action taken. Three different types of trajectory problems were solved, a generalized orbit change maneuver, a semimajor axis change maneuver, …
Characterization And Optimization Of A Propeller Test Stand, Colin Bruce Leighton Benjamin
Characterization And Optimization Of A Propeller Test Stand, Colin Bruce Leighton Benjamin
Mechanical & Aerospace Engineering Theses & Dissertations
In recent history, there has been a rapid rise in the use of drones, and they are expanding in popularity each year. The widespread use and future capabilities of these unmanned aerial vehicles (UAVs) will call for increased study and classification of propellers to maximize their performance. As a result, it is necessary to have continuity in the development, maximization, and optimization of propeller test stand’s capability to collect accurate and precise measurements. It is of significant advantage to have the capability of accurately characterizing a propeller based on its thrust and torque. In this study, a propeller test stand …
Comparison Of Novel Heuristic And Integer Programming Schedulers For The Usaf Space Surveillance Network, Kanit Dararutana
Comparison Of Novel Heuristic And Integer Programming Schedulers For The Usaf Space Surveillance Network, Kanit Dararutana
Theses and Dissertations
Space is a highly congested and contested domain begetting the importance of prioritizing the Space Situational Awareness (SSA) mission. With increased dependence on space assets, scheduling and tasking of the Space Surveillance Network (SSN) is vitally important to maintaining space dominance. According to the 2004 USSTRATCOM Strategic Directive 505-1 (SD 505-1) the SSN uses centralized tasking, with decentralized scheduling. Enhancing SSA within available resources is paramount, and the development of a centralized SSN scheduler to maximize performance is crucial. This research develops and compares novel scheduling models to a model reflecting the 2004 SD 505-1. Novel schedulers were developed to …
Multi-Objective Optimization Mission Design For Small-Body Coverage Missions, David William Hinckley
Multi-Objective Optimization Mission Design For Small-Body Coverage Missions, David William Hinckley
Graduate College Dissertations and Theses
Missions concerning small-body celestial objects are of growing interest due to the resources and information they can provide. Such missions require detailed information about the surface of the body for interactions, such as landing on the surface, as well as predicting the gravity field of the object. This work provides a means of optimizing the mission elements of trajectory and imaging target schedules so that the level of knowledge of the surface can be increased. The information required to increase one's knowledge of the surface is described as a set of conditions placed on the collection of images taken of …