Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
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, …
Comprehensive Study Of Study Of Optimal Synergetic Skip Entries With Dynamic Thrust Vectoring Control, Jeremiah M. Webb
Comprehensive Study Of Study Of Optimal Synergetic Skip Entries With Dynamic Thrust Vectoring Control, Jeremiah M. Webb
Theses and Dissertations
The atmospheric skip entry has been studied since London's presentation in 1962 describing a more fuel efficient means of altering the orbital inclination of satellites. Since London, research over the decades since has traversed many aspects of this field with varying degrees of success. The present research employs the use of modern optimal control software, complex dynamics with minor simplifications, and thrust vectoring to re-approach the aerocruise atmospheric skip entry. Using the aerodynamics of the X-34, the aerocruise problem is first compared to the un-powered aeroglide where it is shown that the aerocruise is capable of increasing the inclination change …
Effects Of Uncertainty Refinement On Satellite Collision Probability, Bruce Thomas Morrison
Effects Of Uncertainty Refinement On Satellite Collision Probability, Bruce Thomas Morrison
Masters Theses
"Due to the drastic increase in orbital debris about the Earth, the likelihood for new and current mission satellites to collide with other objects grows. When a mission satellite is placed in a highly populated orbit in the vicinity of other satellites or debris, it is necessary to consider the probability of collision to assess any possible conjunctions. The computation of the collision probability is heavily dependent on the relative position and velocity of the objects during conjunction, as well as the combined covariance. There are two main types of analytic collision probability computations; the first assumes that the objects …