Open Access. Powered by Scholars. Published by Universities.®
Navigation, Guidance, Control and Dynamics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Adaptive Control (1)
- Command & data handling (1)
- Communications & telemetry (1)
- Electrical power systems (1)
- Finite Excitation (1)
-
- Gravity recovery missions (1)
- Guidance navigation & control (1)
- Imitation Learning (1)
- Imitation learning (1)
- Integral Concurrent Learning (1)
- Lyapunov Stability (1)
- Machine learning techniques (1)
- Modeling methods (1)
- Optimal Control (1)
- Optimal control problems (1)
- Orbit types (1)
- Propulsion (1)
- Solar Irradiance (1)
- Solar Sailing (1)
- Spacecraft (1)
- Thermal control (1)
Articles 1 - 5 of 5
Full-Text Articles in Navigation, Guidance, Control and Dynamics
Six-Degree-Of-Freedom Optimal Feedback Control Of Pinpoint Landing Using Deep Neural Networks, Omkar S. Mulekar, Hancheol Cho, Riccardo Bevilacqua
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
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 …
Solar Sailing Adaptive Control Using Integral Concurrent Learning For Solar Flux Estimation, Luis Enrique Mendoza Zambrano, Riccardo Bevilacqua
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
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 …
Spacecraft Systems & Navigation, Christopher Vanacore
Spacecraft Systems & Navigation, Christopher Vanacore
Student Works
This textbook is steered towards higher educational course entailed in Commercial Space Operations. This textbook will be covering in detail Orbital Satellites, and Spacecraft. These topics are discussed according to their application, design, and environment. The power system, shielding and communication systems are reviewed along with their missions, space, environment and limitations. Any vehicle, whether manned or unmanned, intended for space travel is a spacecraft. A spacecraft's required systems and equipment depend on the information it will acquire and the tasks it will perform. Although their levels of sophistication vary widely, they re all subject to the harsh conditions of …