Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper addresses the challenge of optimizing satellite constellation design for coverage and revisit objectives by introducing differentiable relaxations of traditionally non-differentiable metrics. They create a fully differentiable pipeline from orbital elements to mission-level objectives by using soft sigmoid visibility, noisy-OR aggregation, leaky integrator revisit gap tracking, and LogSumExp soft-maximum, composed with a differentiable orbit propagator. Experiments demonstrate that this gradient-based method efficiently recovers Walker-Delta geometry and discovers Molniya-like orbits, outperforming simulated annealing, genetic algorithms, and differential evolution in terms of evaluation budget and revisit performance.
Unlock efficient satellite constellation design: gradient-based optimization now rivals metaheuristics, finding optimal orbits in a fraction of the evaluations.
Satellite constellation design requires optimizing orbital parameters across multiple satellites to maximize mission specific metrics. For many types of mission, it is desirable to maximize coverage and minimize revisit gaps over ground targets. Existing approaches to constellation design either restrict the design space to symmetric parametric families such as Walker constellations, or rely on metaheuristic methods that require significant compute and many iterations. Gradient-based optimization has been considered intractable due to the non-differentiability of coverage and revisit metrics, which involve binary visibility indicators and discrete max operations. We introduce four continuous relaxations: soft sigmoid visibility, noisy-OR multi-satellite aggregation, leaky integrator revisit gap tracking, and LogSumExp soft-maximum, which when composed with the $\partial$SGP4 differentiable orbit propagator, yield a fully differentiable pipeline from orbital elements to mission-level objectives. We show that this scheme can recover Walker-Delta geometry from irregular initializations, and discovers elliptical Molniya-like orbits with apogee dwell over extreme latitudes from only gradients. Compared to simulated annealing (SA), genetic algorithm (GA), and differential evolution (DE) baselines, our gradient-based method recovers Walker-equivalent geometry within ${\sim}750$ evaluations, whereas the three black-box baselines plateau at with significantly worse revisit even with roughly four times the evaluation budget.