# Deep Learning Warm Starts for Trajectory Optimization on the International Space Station

arXiv: https://arxiv.org/abs/2505.05588 · HTML: https://mlsanity.com/paper/2505.05588/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 8 May 2025.

## Builds on (most cited first, 17 of 17)

- [OSQP: An Operator Splitting Solver for Quadratic Programs](https://mlsanity.com/paper/1711.08013/) (2017)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [CoCo: Online Mixed-Integer Control via Supervised Learning](https://mlsanity.com/paper/2107.08143/) (2021)
- [Transformers for Trajectory Optimization with Application to Spacecraft Rendezvous](https://mlsanity.com/paper/2310.13831/) (2023)
- [A Survey on Artificial Intelligence Trends in Spacecraft Guidance Dynamics and Control](https://mlsanity.com/paper/1812.02948/) (2018)
- [Closing the Loop on Runtime Monitors with Fallback-Safe MPC](https://mlsanity.com/paper/2309.08603/) (2023)
- [Successive Convexification of Non-Convex Optimal Control Problems and Its Convergence Properties](https://mlsanity.com/paper/1608.05133/) (2016)
- [Towards Robust Spacecraft Trajectory Optimization via Transformers](https://mlsanity.com/paper/2410.05585/) (2024)
- [Constraint-Informed Learning for Warm Starting Trajectory Optimization](https://mlsanity.com/paper/2312.14336/) (2023)
- [Generalizable Spacecraft Trajectory Generation via Multimodal Learning with Transformers](https://mlsanity.com/paper/2410.11723/) (2024)
- [Diffusion Policies for Generative Modeling of Spacecraft Trajectories](https://mlsanity.com/paper/2501.00915/) (2025)
- [Convex Optimization for Trajectory Generation](https://mlsanity.com/paper/2106.09125/) (2021)
- [Advances in Trajectory Optimization for Space Vehicle Control](https://mlsanity.com/paper/2108.02335/) (2021)
- [Trajectory Optimization on Manifolds: A Theoretically-Guaranteed Embedded Sequential Convex Programming Approach](https://mlsanity.com/paper/1905.07654/) (2019)
- [Neural-Rendezvous: Provably Robust Guidance and Control to Encounter Interstellar Objects](https://mlsanity.com/paper/2208.04883/) (2022)
- [Data Lifecycle Management in Evolving Input Distributions for Learning-based Aerospace Applications](https://mlsanity.com/paper/2209.06855/) (2022)
- [The ReSWARM Microgravity Flight Experiments: Planning, Control, and Model Estimation for On-Orbit Close Proximity Operations](https://mlsanity.com/paper/2301.01319/) (2023)

## Built on by (most cited first, 4 of 4)

- [Agile Tradespace Exploration for Space Rendezvous Mission Design via Transformers](https://mlsanity.com/paper/2510.03544/) (2025)
- [Transformer-Based Warm-Starting for Feasible and Optimal Terminal Approach to Tumbling Objects with Space Manipulators](https://mlsanity.com/paper/2606.17317/) (2026)
- [Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions](https://mlsanity.com/paper/2605.19562/) (2026)
- [RL-Guided PAC-NMPC for Probabilistically-Safe Perception-Based Navigation in Unknown Environments](https://mlsanity.com/paper/2609.39854/) (2026)

## Abstract (arXiv)

Trajectory optimization is a cornerstone of modern robot autonomy, enabling systems to compute trajectories and controls in real-time while respecting safety and physical constraints. However, it has seen limited usage in spaceflight applications due to its heavy computational demands that exceed the capability of most flight computers. In this work, we provide results on the first in-space demonstration of using machine learning-based warm starts for accelerating trajectory optimization for the Astrobee free-flying robot onboard the International Space Station (ISS). We formulate a data-driven optimal control approach that trains a neural network to learn the structure of the trajectory generation problem being solved using sequential convex programming (SCP). Onboard, this trained neural network predicts solutions for the trajectory generation problem and relies on using the SCP solver to enforce safety constraints for the system. Our trained network reduces the number of solver iterations required for convergence in cases including rotational dynamics by 60% and in cases with obstacles drawn from the training distribution of the warm start model by 50%. This work represents a significant milestone in the use of learning-based control for spaceflight applications and a stepping stone for future advances in the use of machine learning for autonomous guidance, navigation, & control.