# Transformer-Based Warm-Starting for Feasible and Optimal Terminal Approach to Tumbling Objects with Space Manipulators

arXiv: https://arxiv.org/abs/2606.17317 · HTML: https://mlsanity.com/paper/2606.17317/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 30 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Transformers for Trajectory Optimization with Application to Spacecraft Rendezvous](https://mlsanity.com/paper/2310.13831/) (2023)
- [Transformer-based Model Predictive Control: Trajectory Optimization via Sequence Modeling](https://mlsanity.com/paper/2410.23916/) (2024)
- [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)
- [Successive Convexification with Feasibility Guarantee via Augmented Lagrangian for Non-Convex Optimal Control Problems](https://mlsanity.com/paper/2304.14564/) (2023)
- [Guided Policy Search using Sequential Convex Programming for Initialization of Trajectory Optimization Algorithms](https://mlsanity.com/paper/2110.06975/) (2021)
- [Deep Learning Warm Starts for Trajectory Optimization on the International Space Station](https://mlsanity.com/paper/2505.05588/) (2025)
- [Agile Tradespace Exploration for Space Rendezvous Mission Design via Transformers](https://mlsanity.com/paper/2510.03544/) (2025)
- [Language-Conditioned Safe Trajectory Generation for Spacecraft Rendezvous](https://mlsanity.com/paper/2512.09111/) (2025)
- [Filtering-Linearization: A First-Order Method for Nonconvex Trajectory Optimization with Filter-Based Warm-Starting](https://mlsanity.com/paper/2409.17944/) (2024)

## Built on by (most cited first, 1 of 1)

- [Transformer-Informed Trajectory Optimization for Relative Motion in Cislunar Orbits](https://mlsanity.com/paper/2609.25460/) (2026)

## Abstract (arXiv)

Autonomous capture of a tumbling object with a space manipulator requires trajectory generation under real-time onboard constraints. However, coupled bus-arm dynamics, rotating safety geometry, and visibility requirements make the underlying optimization severely nonconvex, hence expensive to solve and sensitive to initialization. This paper develops a causal-transformer warm-start for the computationally dominant attitude-manipulator stage of a two-stage sequential convex programming (SCP) framework. Across 300 held-out scenarios evaluated on embedded hardware, the learned warm-start reduces the iterations of the second-stage SCP by up to 32% and runtime by 16% while maintaining numerical feasibility and matching the final control cost. Furthermore, linear and flow matching action decoders are compared across action-chunk lengths and training dataset sizes, where the flow matching decoder exhibits stronger training-data efficiency than the linear decoder. When SCP is terminated based on feasibility, the runtime is further reduced while the learned prior suppresses the severe high-cost tail observed with heuristic initialization. These results demonstrate that learned warm-starts can reduce onboard optimization cost while steering SCP toward basins containing feasible, low-cost solutions.