Transformer-Informed Trajectory Optimization for Relative Motion in Cislunar Orbits
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.
Related
- Information-Based Trajectory Planning for Spacecraft-to-Spacecraft Tracking and Navigation in Cislunar Space
- Empirical Trajectory Sparsity Biases Mobility-Informed Epidemic Modeling
- Cubature-Based Statistical Moment Steering for Nonlinear, Non-Gaussian Trajectory Optimization
- Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions
- Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization
BibTeX
@misc{manuel2026transformerinformed,
title = {{Transformer-Informed Trajectory Optimization for Relative Motion in Cislunar Orbits}},
author = {Walter J. Manuel and Yuji Takubo and Simone D'Amico},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.25460},
eprint = {2609.25460},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.25460},
}
RIS
TY - UNPB
TI - Transformer-Informed Trajectory Optimization for Relative Motion in Cislunar Orbits
AU - Walter J. Manuel
AU - Yuji Takubo
AU - Simone D'Amico
PY - 2026
DA - 2026/09/21
PB - arXiv
DO - 10.48550/arxiv.2609.25460
UR - https://arxiv.org/abs/2609.25460
AB - 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.
ER -