Exploring the Low-Thrust Transfer Design Space in an Ephemeris Model via Multi-Objective Reinforcement Learning
No abstract provided
Mashiku, Alinda↗
Engineering topics
Bosanac, Natasha
Publications and source records attributed to Bosanac, Natasha.
Exploring the Low-Thrust Transfer Design Space in an Ephemeris Model via Multi-Objective Reinforcement Learning
Multi-Reward Proximal Policy Optimization (MRPPO) is a multi-objective reinforcement learning algorithm used to train multiple policies to uncover solutions within a multi-objective solution space. MRPPO is used in this paper to train policies to construct low-thrust transfers for a SmallSat from the vicinity of 𝐿2 to an 𝐿5 short period orbit in the Sun-Earth-Moon system. First, the policies are trained in this scenario in the circular restricted three-body problem. This information is used to initialize the policies before training in a higher-fidelity ephemeris model; a process known as transfer learning. The recovered segments of the solution space will be compared to fundamental dynamical structures to both examine the results of MRPPO in this complex design scenario and explore the effectiveness of transfer learning.
Mashiku, Alinda K.↗
Multi-objective Reinforcement Learning for Low-thrust Transfer Design Between Libration Point Orbits
No abstract provided
Anderson, Rodney L↗
Multi-objective Reinforcement Learning for Low-thrust Transfer Design Between Libration Point Orbits
Multi-Reward Proximal Policy Optimization (MRPPO) is a multi-objective rein- forcement learning algorithm used to construct low-thrust transfers between pe- riodic orbits in multi-body systems. Previous implementations of MRPPO have relied on a predefined reference transfer to successfully train each policy. In this paper, an algorithmic modification labeled the ‘moving reference’, is introduced to autonomously construct these reference trajectories during training. With this modification, MRPPO is used to recover various low-thrust transfers between two periodic orbits in the Earth-Moon circular restricted three-body problem to solve a multi-objective optimization problem. These results are then compared with the solutions recovered via a gradient descent optimization scheme to validate the performance of MRPPO with the moving reference modification.
Anderson, Rodney L.↗
Multi-objective Reinforcement Learning for Low-thrust Transfer Design Between Libration Point Orbits
Multi-Reward Proximal Policy Optimization (MRPPO) is a multi-objective rein- forcement learning algorithm used to construct low-thrust transfers between pe- riodic orbits in multi-body systems. Previous implementations of MRPPO have relied on a predefined reference transfer to successfully train each policy. In this paper, an algorithmic modification labeled the ‘moving reference’, is introduced to autonomously construct these reference trajectories during training. With this modification, MRPPO is used to recover various low-thrust transfers between two periodic orbits in the Earth-Moon circular restricted three-body problem to solve a multi-objective optimization problem. These results are then compared with the solutions recovered via a gradient descent optimization scheme to validate the performance of MRPPO with the moving reference modification.
Anderson, Rodney L↗
Exploring Transfers Between Earth-Moon Halo Orbits via Multi-Objective Reinforcement Learning
Multi-Reward Proximal Policy Optimization, a multi-objective deep reinforcement learning algorithm, is used to examine the design space of low-thrust trajectories for a SmallSat transferring between two libration point orbits in the Earth- Moon system. Using Multi-Reward Proximal Policy Optimiza- tion, multiple policies are simultaneously and efficiently trained on three distinct trajectory design scenarios. Each policy is trained to create a unique control scheme based on the trajectory design scenario and assigned reward function: a unique combination of weights scaling competing objectives that guide the spacecraft to the target mission orbit, incentivize faster flight times, and penalize propellant mass usage. Then, the policies are evaluated on the same set of perturbed initial conditions in each scenario to generate the propellant mass usages, flight times, and state discontinuities from a reference trajectory for each control scheme. This solution space of low-thrust trajectories for a SmallSat is used to examine the multi-objective trade space for the trajectory design scenario. By autonomously constructing the solution space, insights into the required propellant mass, flight time, and transfer geometry are rapidly achieved.
Mashiku, Alinda K.↗
Exploring Transfers Between Earth-Moon Halo Orbits via Multi-Objective Reinforcement Learning
No abstract provided
Stuart, Jeffrey R.↗
Designing Low-Thrust Enabled Trajectories for a Heliophysics Smallsat Mission to Sun-Earth L5
A small satellite deployed to Sun-Earth L5 could serve as a low-cost platform to observe solar phenomena such as coronal mass ejections. However, the small satellite platform introduces significant challenges in the trajectory design process via limited thrusting capabilities, power and operational constraints, and fixed deployment conditions. To address these challenges, a strategy employing dynamical systems theory is used to design a low-thrust-enabled trajectory for a small satellite to reach the Sun-Earth L5 region. This procedure is demonstrated for a small satellite that launches as a secondary payload with a larger spacecraft destined for a Sun-Earth L2 halo orbit.
Stuart, Jeffrey↗
Trajectory Design for a Cislunar Cubesat Leveraging Dynamical Systems Techniques: The Lunar Icecube Mission
Lunar IceCube is a 6U CubeSat that is designed to detect and observe lunar volatiles from a highly inclined orbit. This spacecraft, equipped with a low-thrust engine, will be deployed from the upcoming Exploration Mission-1 vehicle in late 2018. However, significant uncertainty in the deployment conditions for secondary payloads impacts both the availability and geometry of transfers that deliver the spacecraft to the lunar vicinity. A framework that leverages dynamical systems techniques is applied to a recently updated set of deployment conditions and spacecraft parameter values for the Lunar IceCube mission, demonstrating the capability for rapid trajectory design.
Bosanac, Natasha↗
Trajectory Design for a Cislunar Cubesat Leveraging Dynamical Systems Techniques: The Lunar Icecube Mission
Lunar IceCube is a 6U CubeSat that is designed to detect and observe lunar volatiles from a highly inclined orbit. This spacecraft, equipped with a low-thrust engine, will be deployed from the upcoming Exploration Mission-1 vehicle in late 2018. However, significant uncertainty in the deployment conditions for secondary payloads impacts both the availability and geometry of transfers that deliver the spacecraft to the lunar vicinity. A framework that leverages dynamical systems techniques is applied to a recently updated set of deployment conditions and spacecraft parameter values for the Lunar IceCube mission, demonstrating the capability for rapid trajectory design.
Bosanac, Natasha↗
The Lunar IceCube Mission Challenge: Attaining Science Orbit Parameters from a Constrained Approach Trajectory
The challenges of targeting specific lunar science orbit parameters from a concomitant Sun-Earth/Moon system trajectory are examined. While the concept of ballistic lunar capture is well-studied, achieving and controlling the time evolution of the orbital elements to satisfy mission constraints is especially problematic when the spacecraft is equipped with a low-thrust propulsion system. Satisfying these requirements on the lunar approach and capture segments is critical to the success of the Lunar IceCube mission, a 6U CubeSat that will prospect for water in solid (ice), liquid, and vapor forms and other lunar volatiles from a low-periapsis, highly inclined elliptical lunar orbit.
Folta, David C.↗
The Lunar IceCube Mission Challenge: Attaining Science Orbit Parameters from a Constrained Approach Trajectory
The challenges of targeting specific lunar science orbit parameters from a concomitant Sun-EarthMoon system trajectory are examined. While the concept of ballistic lunar capture is well-studied, achieving and controlling the time evolution of the orbital elements to satisfy mission constraints is especially problematic when the spacecraft is equipped with a low-thrust propulsion system. Satisfying these requirements on the lunar approach and capture segments is critical to the success of the Lunar IceCube mission, a 6U CubeSat that will prospect for water in solid (ice), liquid, and vapor forms and other lunar volatiles from a low-periapsis, highly inclined elliptical lunar orbit.
Folta, David C.↗
Trajectory Design Tools for Libration and Cis-Lunar Environments
Innovative trajectory design tools are required to support challenging multi-body regimes with complex dynamics, uncertain perturbations, and the integration of propulsion influences. Two distinctive tools, Adaptive Trajectory Design and the General Mission Analysis Tool have been developed and certified to provide the astrodynamics community with the ability to design multi-body trajectories. In this paper we discuss the multi-body design process and the capabilities of both tools. Demonstrable applications to confirmed missions, the Lunar IceCube Cubesat lunar mission and the Wide-Field Infrared Survey Telescope (WFIRST) Sun-Earth L2 mission, are presented.
Earth-Moon↗
The Lunar IceCube Mission Design: Construction of Feasible Transfer Trajectories with a Constrained Departure
Lunar IceCube, a 6U CubeSat, will prospect for water and other volatiles from a low-periapsis, highly inclined elliptical lunar orbit. Injected from Exploration Mission-1, a lunar gravity assisted multi-body transfer trajectory will capture into a lunar science orbit. The constrained departure asymptote and value of trans-lunar energy limit transfer trajectory types that re-encounter the Moon with the necessary energy and flight duration. Purdue University and Goddard Space Flight Center's Adaptive Trajectory Design tool and dynamical system research is applied to uncover cislunar spatial regions permitting viable transfer arcs. Numerically integrated transfer designs applying low-thrust and a design framework are described.
Cis-lunar↗
An Earth-Moon System Trajectory Design Reference Catalog
As demonstrated by ongoing concept designs and the recent ARTEMIS mission, there is, currently, significant interest in exploiting three-body dynamics in the design of trajectories for both robotic and human missions within the Earth-Moon system. The concept of an interactive and 'dynamic' catalog of potential solutions in the Earth-Moon system is explored within this paper and analyzed as a framework to guide trajectory design. Characterizing and compiling periodic and quasi-periodic solutions that exist in the circular restricted three-body problem may offer faster and more efficient strategies for orbit design, while also delivering innovative mission design parameters for further examination.
Libration Orbits↗
MIT January Operational Internship Experience
This viewgraph presentation describes the MIT January Operational Internship Experience (JOIE) program. The topics include: 1) Landing and Recovery; 2) Transportation; 3) Shuttle Processing; 4) Constellation Processing; 5) External Tank; 6) Launch Pad; 7) Ground Operations; 8) Hypergolic Propellants; 9) Environmental; 10) Logistics; 11) Six Sigma; 12) Systems Engineering; and 13) Human Factors.
Bosanac, Natasha↗