Summary
Planning the paths for spacecraft moving near the moon is very tricky because gravity creates complex and chaotic motions. The authors developed a new method called ART-TWIN, which uses a transformer model to quickly create good starting guesses for spacecraft paths, improving how fast and reliably the final routes can be found. This method generates two path sections—one starting from the current position and one from the goal—and connects them in the middle, making it easier to solve the difficult problem of planning these journeys. Tests in simulated missions show ART-TWIN speeds up calculations and increases successful path planning compared to earlier methods.
What this means in practice
- •For space mission planners: Generate faster and more reliable trajectories for spacecraft docking near the moon by using transformer-generated initial guesses.
- •For orbital robotics engineers: Improve autonomous guidance in lunar proximity operations by applying dual-arc transformer methods to handle complex dynamics.
Abstract
Autonomous spacecraft guidance and control requires a fast solution to non-convex trajectory optimization, which can be accelerated by providing a near-optimal initial guess to an optimization protocol, i.e., warm-starting. A robust warm starting method is especially useful for rendezvous, proximity operations, and docking (RPOD) in cislunar space, where the underlying dynamics become severely nonlinear and chaotic compared to those in Earth orbit, especially at perilune. This paper extends the Autonomous Rendezvous Transformer (ART), a transformer-based warm-start trajectory generation method, to cislunar RPOD scenarios for the first time. To accurately and reliably solve the nonconvex optimal control problems (OCPs) posed by these scenarios, a new and enhanced version of ART, ART-TWIN (Two-Way INference), is introduced. Inspired by forward-backward shooting methods used in other trajectory design applications, ART-TWIN autoregressively generates two arcs, one from the initial state and one from the desired terminal state, that are patched together at the midpoint of the timeseries. When evaluated on a set of simulated rendezvous scenarios that are initialized at perilune, ART-TWIN is demonstrated to substantially accelerate convergence and increase feasibility guarantees when used as a warm-start to sequential convex programming (SCP), compared to convex relaxations and the original ART. These results illustrate the necessity of ART-TWIN's dual-arc generation to enable the viability of and gain benefits from using transformer-based warm-start methods in the most challenging areas of the cislunar dynamical regime.