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
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.