Author Information

Shiloh CuffeFollow

group

What campus are you from?

Daytona Beach

Authors' Class Standing

Shiloh Cuffe, Senior Quinten Acchione, Senior

Lead Presenter's Name

Shiloh Cuffe

Faculty Mentor Name

Di Wu

Abstract

Trajectory optimization is an essential component of mission planning and space mission control. Mission planning involves developing a trajectory that allows a spacecraft to complete objectives, like performing orbital maneuvers, rendezvous missions, or planetary impacts, while also minimizing resource utilization and avoiding physical and functional violation of constraints. In interplanetary mission planning, a vehicle must travel to another planet using the same concepts. This task requires a reliable trajectory planning algorithm that could handle uncertainties in the environment. Traditional methods utilizing models and numerical methods have been used to solve these problems before. While these approaches are efficient in that they are suitable for integration with spacecraft systems, they suffer from being limited by their precomputed models and assumptions, reducing their ability to handle unexpected outcomes in the mission environment. Through applying reinforcement learning (RL) techniques and genetic algorithms to trajectory optimization problems, spacecraft are more responsive to environmental conditions and can dynamically respond to unexpected conditions.

Did this research project receive funding support from the Office of Undergraduate Research.

No

Share

COinS
 

Interplanetary Trajectory Optimization with Artificial Intelligence

Trajectory optimization is an essential component of mission planning and space mission control. Mission planning involves developing a trajectory that allows a spacecraft to complete objectives, like performing orbital maneuvers, rendezvous missions, or planetary impacts, while also minimizing resource utilization and avoiding physical and functional violation of constraints. In interplanetary mission planning, a vehicle must travel to another planet using the same concepts. This task requires a reliable trajectory planning algorithm that could handle uncertainties in the environment. Traditional methods utilizing models and numerical methods have been used to solve these problems before. While these approaches are efficient in that they are suitable for integration with spacecraft systems, they suffer from being limited by their precomputed models and assumptions, reducing their ability to handle unexpected outcomes in the mission environment. Through applying reinforcement learning (RL) techniques and genetic algorithms to trajectory optimization problems, spacecraft are more responsive to environmental conditions and can dynamically respond to unexpected conditions.

 

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.