Diffusion models improve fuel optimal spacecraft trajectory calculations
Diffusion-Based Multiple-Shooting Indirect Optimal Control for Fuel-Optimal Spacecraft Trajectory Generation
Machine Learning
Summary
Getting a spacecraft from Earth to Mars using the least fuel is a tough problem because the best paths require complex calculations. The authors combined a new kind of AI called diffusion models with traditional math used in spacecraft route planning. This mix helps find better routes more reliably, especially for tricky long journeys with on-off engine firing patterns. Their method was tested on a simulated Earth-to-Mars trip and worked better than previous advanced methods.
What this means in practice
- •For spacecraft mission planners: Generate fuel-efficient spacecraft trajectories with improved reliability for long low-thrust missions like Earth-Mars transfers.
- •For robotics control engineers: Use diffusion-based indirect control methods to improve convergence in solving complex control problems with bang-bang inputs.
Authors
Saeid Tafazzol, Ehsan Taheri, Ryne Beeson
Abstract
Diffusion-based generative models (DMs) have found applications in control problems, and in particular robotics, where the DMs enable exploration of possible control solutions. A critical shortcoming of these applications is that they have lacked optimality guarantees. This is a problem for their potential use in fuel-optimal spacecraft trajectories that are characterized with long time-horizons and bang-bang profiles. Alternatively, indirect optimal control methods ensure explicit satisfaction of necessary conditions, but are highly sensitive to the initial costate estimation needed to solve the resulting Hamiltonian boundary-value problems (HBVPs). To alleviate this sensitivity and enlarge the convergence domain of HBVPs, advanced indirect methods have been developed that use smoothing approaches and continuation. We propose a diffusion-based multiple shooting indirect control method that combines the exploration capability of DMs with indirect method to generate fuel-optimal spacecraft trajectories. We benchmark our method against an advanced indirect method on a fuel-optimal Earth-Mars low-thrust transfer problem, showing higher convergence robustness than the advanced indirect method that is based on random costate initialization. Code and visualizations are available at https://saeidtafazzol.github.io/Diffusion_Indirect_Control/.