Is this project an undergraduate, graduate, or faculty project?

Undergraduate

Project Type

group

Campus

Daytona Beach

Authors' Class Standing

Dawson Jones, Senior Rogelio Gracia Otalvaro, Graduate Student

Lead Presenter's Name

Dawson Jones

Lead Presenter's College

DB College of Aviation

Faculty Mentor Name

Bryan Watson

Abstract

The space economy is projected to grow to 1.8 trillion USD by 2030, according to the World Economic Forum and McKinsey & Company. As space operations become more common and diversified, the hazardous nature of the environment is worsened by the growing number of complex actors. Currently, ground segments manage these hazards and risks, but they are faced with potential operation challenges such as communications delays, communication issues due to single event upsets, and orbital perturbations. Additional environmental challenges that further complicate these operations might be satellite collisions, anti-satellite weaponry, orbital debris, and uncontrolled space. Furthermore, the increasing number of actors in space is likely to outpace the growth of personnel in this field and the infrastructure to support them. To address these challenges, one possible solution is the use of machine learning (ML) solutions in space to reduce the personnel needed and infrastructure to support them and increase autonomy. A key innovation in this field would be dynamic automated spacecraft coupling. In these scenarios, automated models would determine the optimal approach, implement the necessary actions to couple with the target object, and be capable of aborting if anomalies compromise the safety of the coupling. This study seeks to determine the viability of such a model using Proximal Policy Optimization along R-bar, V-bar, and Z-bar approaches in a 6-degree-of-freedom environment, implementing abort scenarios based on a predefined keep-out zone around the target objective.

Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?

No

Share

COinS
 

Machine Learning for Near-Proximity Operations

The space economy is projected to grow to 1.8 trillion USD by 2030, according to the World Economic Forum and McKinsey & Company. As space operations become more common and diversified, the hazardous nature of the environment is worsened by the growing number of complex actors. Currently, ground segments manage these hazards and risks, but they are faced with potential operation challenges such as communications delays, communication issues due to single event upsets, and orbital perturbations. Additional environmental challenges that further complicate these operations might be satellite collisions, anti-satellite weaponry, orbital debris, and uncontrolled space. Furthermore, the increasing number of actors in space is likely to outpace the growth of personnel in this field and the infrastructure to support them. To address these challenges, one possible solution is the use of machine learning (ML) solutions in space to reduce the personnel needed and infrastructure to support them and increase autonomy. A key innovation in this field would be dynamic automated spacecraft coupling. In these scenarios, automated models would determine the optimal approach, implement the necessary actions to couple with the target object, and be capable of aborting if anomalies compromise the safety of the coupling. This study seeks to determine the viability of such a model using Proximal Policy Optimization along R-bar, V-bar, and Z-bar approaches in a 6-degree-of-freedom environment, implementing abort scenarios based on a predefined keep-out zone around the target objective.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.