The feasibility of neural networks to control dynamic systems is examined. Control of a one-dimensional problem is initially investigated to develop an understanding of the structure and simulation of the neural networks. A nondimensional problem is also explored to apply a single neural network design to controlling a class of systems with a wide variety of modeling parameters. Finally, these techniques are applied to control a space vehicle to transfer, intercept, and rendezvous with another orbiting vehicle using the Clohessy-Wiltshire equations of relative motion in two dimensions. A combination of open-loop and closed-loop neural network controllers is shown to work effectively for this problem. Noise is added to the neural network inputs to demonstrate the robustness of these networks. / Ph. D.

Long range path planning for an autonomous ground vehicle with minimal a-priori data is still very much an open problem. Previous research has demonstrated that least cost paths generated from aerial LIDAR and GIS data could play a role in automatically determining suitable routes over otherwise unknown terrain. However, most of this research has been theoretical. Consequently, there is very little literature the effectiveness of these techniques in plotting paths of an actual autonomous vehicle. This research aims to develop an algorithm for using aerial LIDAR and imagery to plan paths for a full size autonomous car. Methods of identifying obstacles and potential roadways from the aerial LIDAR and imagery are reviewed. A scheme for integrating the path planning algorithms into the autonomous vehicle existing systems was developed and eight paths were generated and driven by an autonomous vehicle. The paths were then analyzed for their drivability and the model itself was validated against the vehicle measurements. The methods described were found to be suitable for generating paths both on and off road. / Master of Science

The number of objects occupying orbital regimes beyond Geosynchronous Earth Orbit and cislunar space are expected to grow in the coming years; Especially with the Moon reemerging as latest frontier in the race for space exploration and technological superiority. In order to support this growth, new methods of autonomously navigating in cislunar space are necessary to reduce demand and reliance on ground based tracking infrastructure. Periodic orbits about the first libration point offer favorable vantage points for scientific or military spacecraft missions involving the Earth or Moon. This thesis develops a new autonomous spacecraft navigation method for cislunar space and analyzes its performance applied to Lyapunov and halo orbits around $L_1$. This method uses existing lunar ranging retroreflectors (LRRR) installed on the Moon's surface in the 1960s and 1970s. A spacecraft can make laser ranging measurements to the LRRR to estimate its orbit states. A simulation platform was created to test this concept in the circular restricted three body problem and evaluate its performance. This navigation method was found to be successful for a subset of Lyapunov and halo orbits when cycling the five measurement targets. Simulation data showed that sub-kilometer position estimation and sub 2 centimeter per second velocity accuracies are achievable without receiving any state updates from external sources. / Master of Science / The number of objects occupying the space between the Earth and Moon (cislunar space) is expected to grow in the coming years as the Moon regains popularity in the latest race for space exploration and technological superiority. In order to support this growth, new methods of determining a spacecraft's position and velocity while in this region of space are necessary to reduce demand and dependence on Earth based methods, which have historically relied upon. Repeating orbits around the equilibrium point between the Earth and Moon provide valuable observation points for scientific and military spacecraft missions. This thesis develops a new spacecraft navigation method for cislunar space and analyzes how well it performs in two different types of orbits, Lyapunov and halo orbits. This method uses existing laser reflector panels that were installed on the Moon's surface in the 1960s and 70s. A spacecraft can use these panels to make range or distance measurements in order to estimate its position and velocity. Software was written to simulate the motion of a spacecraft as it is acted on by gravity from the Earth and Moon. Different scenarios were then simulated and used to test this concept and evaluate its performance. Lunar laser ranging was found to be successful for a some Lyapunov and halo orbits when switching between the five different reflector panels on the Moon. Data generated from the simulations show that position can be estimated with errors less than SI{1}{kilo meter}, and velocity error on the order of a few centimeters per second, all without receiving any additional information from Earth based systems.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.