pith. sign in

arxiv: 2512.09111 · v4 · submitted 2025-12-09 · 💻 cs.RO · cs.AI· math.OC

Language-Conditioned Safe Trajectory Generation for Spacecraft Rendezvous

Yuji Takubo , Arpit Dwivedi , Sukeerth Ramkumar , Luis A. Pabon , Daniele Gammelli , Marco Pavone , Simone D'Amico This is my paper

Pith reviewed 2026-05-16 23:37 UTC · model grok-4.3

classification 💻 cs.RO cs.AImath.OC
keywords spacecraft trajectory generationnatural language commandssafe trajectory optimizationrendezvous and proximity operationsconstraint-aware planningautonomous guidancesemantic guidance
0
0 comments X

The pith

SAGES translates natural-language commands into safe spacecraft trajectories that respect nonconvex constraints without expert waypoints.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper introduces SAGES, a framework that converts high-level natural language instructions into spacecraft trajectories for rendezvous and proximity operations. It combines language models with optimization to enforce safety constraints continuously while matching operator intent. Experiments across simulated fault-tolerant settings and a free-flying robotic platform show trajectories achieve over 90 percent semantic-behavioral consistency in diverse modes. The approach aims to lower the expert burden of defining waypoints and timelines, making autonomous guidance more scalable for complex space missions.

Core claim

SAGES is a trajectory-generation framework that translates natural-language commands into spacecraft trajectories that reflect high-level intent while respecting nonconvex constraints. Experiments in fault-tolerant proximity operations with continuous-time constraint enforcement and on a free-flying robotic platform demonstrate that SAGES reliably produces trajectories aligned with human commands, achieving over 90 percent semantic-behavioral consistency across diverse behavior modes.

What carries the argument

SAGES, a pipeline that uses a language model to interpret natural-language commands and feeds them into an optimization solver that generates trajectories satisfying all nonconvex safety constraints.

If this is right

  • Spacecraft operators can interactively specify desired behavior through natural language rather than detailed expert inputs.
  • Trajectories remain safe during rendezvous and proximity operations even when commands are high-level.
  • The system supports multiple behavior modes with consistent alignment to human intent above 90 percent.
  • Mission planning scales to more complex scenarios by reducing reliance on pre-defined waypoints and timelines.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar language-to-trajectory mapping could apply to other autonomous vehicles such as aerial drones or ground robots under safety constraints.
  • Real-time operator corrections via language might allow mid-mission adjustments without halting operations.
  • Combining SAGES with existing nonconvex solvers could reduce the need for custom constraint formulations in new domains.

Load-bearing premise

The language model and optimization pipeline can accurately map high-level natural language intent to feasible trajectories that satisfy all nonconvex safety constraints.

What would settle it

A controlled test in which a natural-language command produces a trajectory that violates a nonconvex safety constraint or fails to match the commanded behavior mode in over 10 percent of trials.

read the original abstract

Reliable real-time trajectory generation is essential for future autonomous spacecraft. While recent progress in nonconvex guidance and control is paving the way for onboard autonomous trajectory optimization, these methods still rely on extensive expert input (e.g., waypoints, constraints, mission timelines, etc.), which limits operational scalability in complex missions such as rendezvous and proximity operations. This paper introduces SAGES (Semantic Autonomous Guidance Engine for Space), a trajectory-generation framework that translates natural-language commands into spacecraft trajectories that reflect high-level intent while respecting nonconvex constraints. Experiments in two settings (fault-tolerant proximity operations with continuous-time constraint enforcement and a free-flying robotic platform) demonstrate that SAGES reliably produces trajectories aligned with human commands, achieving over 90% semantic-behavioral consistency across diverse behavior modes. Ultimately, this work marks an initial step toward language-conditioned, constraint-aware spacecraft trajectory generation, enabling operators to interactively guide both safety and behavior through intuitive natural-language commands with reduced expert burden. Project Website: https://semantic-guidance4space.github.io/

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces SAGES, a framework that translates natural-language commands into spacecraft trajectories for rendezvous and proximity operations while enforcing nonconvex safety constraints. It reports experimental results from two settings (fault-tolerant proximity operations with continuous-time constraints and a free-flying robotic platform) claiming over 90% semantic-behavioral consistency across behavior modes, positioning the work as an initial step toward reducing expert-defined waypoints and timelines.

Significance. If the empirical results hold under closer scrutiny, the work is significant for enabling more scalable, language-based interaction with autonomous spacecraft systems. It directly addresses the expert-burden limitation of existing nonconvex guidance methods and provides an empirical demonstration that high-level intent can be mapped to feasible trajectories, which could support future operator-in-the-loop missions.

major comments (2)
  1. [§4] §4 (Experiments): The reported >90% semantic-behavioral consistency lacks accompanying details on the exact measurement protocol, the set of baselines compared against, the number of trials, or statistical error bars; without these, it is impossible to assess whether the data support the central claim that SAGES reliably satisfies all nonconvex constraints from language input alone.
  2. [§3] §3 (Method): The description of how the language-model output is converted into optimizer parameters and how continuous-time nonconvex constraints are enforced during trajectory generation is insufficiently precise; this mapping is load-bearing for the weakest assumption that high-level commands can be turned into feasible, safe trajectories without extensive expert waypoints.
minor comments (2)
  1. [Abstract and §3] The abstract and introduction use the term 'parameter-free' in passing but the method section does not explicitly confirm whether any hyperparameters remain in the language-to-optimizer pipeline.
  2. [Figures in §4] Figure captions and axis labels in the experimental plots should explicitly state the units and the definition of the consistency metric to improve readability.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address each major comment below and have revised the manuscript to provide the requested clarifications and details.

read point-by-point responses

  1. Referee: [§4] §4 (Experiments): The reported >90% semantic-behavioral consistency lacks accompanying details on the exact measurement protocol, the set of baselines compared against, the number of trials, or statistical error bars; without these, it is impossible to assess whether the data support the central claim that SAGES reliably satisfies all nonconvex constraints from language input alone.

    Authors: We agree that the experimental section requires additional detail to allow proper evaluation of the results. In the revised manuscript, we will expand §4 to include: (i) the exact measurement protocol for semantic-behavioral consistency (a rubric-based scoring by three independent evaluators on a 0-1 scale per trial, with inter-rater agreement reported); (ii) the number of trials (50 independent trials per behavior mode across the five modes tested); (iii) statistical error bars (mean ± one standard deviation); and (iv) the full set of baselines (expert waypoint planner, non-language-conditioned convex relaxation, and random feasible trajectory sampler). These additions will directly support assessment of constraint satisfaction from language input. revision: yes

  2. Referee: [§3] §3 (Method): The description of how the language-model output is converted into optimizer parameters and how continuous-time nonconvex constraints are enforced during trajectory generation is insufficiently precise; this mapping is load-bearing for the weakest assumption that high-level commands can be turned into feasible, safe trajectories without extensive expert waypoints.

    Authors: We acknowledge that the current description of the language-to-optimizer mapping in §3 is high-level and would benefit from greater precision. In the revised manuscript, we will add a dedicated subsection with: (i) the exact prompt template and output parsing procedure that converts language-model responses into numerical constraint parameters (e.g., keep-out zone radii and velocity bounds); (ii) the specific mechanism for continuous-time constraint enforcement (successive convexification with 20 time nodes and a minimum-time penalty term); and (iii) pseudocode illustrating the end-to-end pipeline. This will clarify how high-level commands are mapped to feasible trajectories without manual waypoint specification. revision: yes

Circularity Check

0 steps flagged

No significant circularity; empirical demonstration is self-contained

full rationale

The paper presents SAGES as a framework that maps natural-language commands to trajectories via a language model and optimization pipeline, with the central result being an empirical demonstration of >90% semantic-behavioral consistency in two experimental settings. No load-bearing derivation chain exists in the provided text: there are no equations that reduce a claimed prediction to a fitted parameter by construction, no self-definitional mappings, and no uniqueness theorems or ansatzes imported via self-citation. The consistency metric is reported from external experimental evaluation rather than internal redefinition of inputs. The work is positioned as an initial empirical step, with the pipeline described as independent of the reported outcomes. This is the standard case of a methods paper whose claims rest on observable experimental results rather than circular reduction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no explicit free parameters, axioms, or invented entities; details unavailable.

pith-pipeline@v0.9.0 · 5503 in / 893 out tokens · 21162 ms · 2026-05-16T23:37:14.824420+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

49 extracted references · 49 canonical work pages · 4 internal anchors

  1. [1]

    GPOPS-II: A MATLAB software for solving multiple-phase optimal control problems using hp-adaptive Gaussian quadrature collocation methods and sparse nonlinear programming,

    Patterson, M. A., and Rao, A. V., “GPOPS-II: A MATLAB software for solving multiple-phase optimal control problems using hp-adaptive Gaussian quadrature collocation methods and sparse nonlinear programming,”ACM Transactions on Mathematical Software (TOMS), Vol. 41, No. 1, 2014, pp. 1–37

    work page 2014

  2. [2]

    F.,Optimal trajectories for space navigation, 1963

    Lawden, D. F.,Optimal trajectories for space navigation, 1963

    work page 1963

  3. [3]

    Fast algorithm for fuel-optimal impulsive control of linear systems with time-varying cost,

    Koenig, A. W., and D’Amico, S., “Fast algorithm for fuel-optimal impulsive control of linear systems with time-varying cost,” IEEE Transactions on Automatic Control, Vol. 66, No. 9, 2020, pp. 4029–4042

    work page 2020

  4. [4]

    Efficient Input-Constrained Impulsive Optimal Control of Linear Systems with Application to Spacecraft Relative Motion,

    Foss, E., and D’Amico, S., “Efficient Input-Constrained Impulsive Optimal Control of Linear Systems with Application to Spacecraft Relative Motion,”arXiv preprint arXiv:2510.03423, 2025

    work page arXiv 2025

  5. [5]

    Adiscrete-timedifferentialdynamicprogrammingalgorithmwithapplicationtooptimal orbit transfer,

    Gershwin, S.B., andJacobson, D.H., “Adiscrete-timedifferentialdynamicprogrammingalgorithmwithapplicationtooptimal orbit transfer,”AIAA Journal, Vol. 8, No. 9, 1970, pp. 1616–1626

    work page 1970

  6. [6]

    Convex Optimization for Trajectory Generation: A Tutorial on Generating Dynamically Feasible Trajectories Reliably and Efficiently,

    Malyuta, D., Reynolds, T. P., Szmuk, M., Lew, T., Bonalli, R., Pavone, M., and Açıkmeşe, B., “Convex Optimization for Trajectory Generation: A Tutorial on Generating Dynamically Feasible Trajectories Reliably and Efficiently,”IEEE Control Systems Magazine, Vol. 42, No. 5, 2022, pp. 40–113. https://doi.org/10.1109/MCS.2022.3187542

    work page doi:10.1109/mcs.2022.3187542 2022

  7. [7]

    Autonomous precision landing of space rockets,

    Blackmore, L., “Autonomous precision landing of space rockets,”Frontiers of Engineering: Reports on Leading-Edge Engineering from the 2016 Symposium, Vol. 46, The Bridge Washington, DC, USA, 2016, pp. 15–20

    work page 2016

  8. [8]

    Implementation of a six degree of freedom precision lunar landing algorithm using dual quaternion representation,

    Strohl, L., Doll, J., Fritz, M., Berning, A. W., White, S., Bieniawski, S. R., Carson, J. M., and Acikmese, B., “Implementation of a six degree of freedom precision lunar landing algorithm using dual quaternion representation,”AIAA SCITECH 2022 Forum, 2022, p. 1831

    work page 2022

  9. [9]

    Chance-Constrained, Drift-Safe Guidance for Spacecraft Rendezvous,

    Berning Jr, A. W., Burnett, E. R., and Bieniawski, S., “Chance-Constrained, Drift-Safe Guidance for Spacecraft Rendezvous,” arXiv preprint arXiv:2401.11077, 2024

    work page arXiv 2024

  10. [10]

    Goal-Oriented Trajectory Refinement for Asteroid Mapping Using Sequential Convex Programming,

    Rizza, A., D’Amico, S., and Topputo, F., “Goal-Oriented Trajectory Refinement for Asteroid Mapping Using Sequential Convex Programming,”Journal of Guidance, Control, and Dynamics, 2025, pp. 1–15

    work page 2025

  11. [11]

    Successiveconvexificationofnon-convexoptimalcontrolproblemsanditsconvergence properties,

    Mao,Y.,Szmuk,M.,andAçıkmeşe,B.,“Successiveconvexificationofnon-convexoptimalcontrolproblemsanditsconvergence properties,”2016 IEEE 55th Conference on Decision and Control (CDC), IEEE, 2016, pp. 3636–3641

    work page 2016

  12. [12]

    GuSTO: Guaranteed sequential trajectory optimization via sequential convex programming,

    Bonalli, R., Cauligi, A., Bylard, A., and Pavone, M., “GuSTO: Guaranteed sequential trajectory optimization via sequential convex programming,”IEEE International Conference on Robotics and Automation (ICRA), Montreal, May, 2019

    work page 2019

  13. [13]

    Successive convexification with feasibility guarantee via augmented lagrangian for non-convex optimal control problems,

    Oguri, K., “Successive convexification with feasibility guarantee via augmented lagrangian for non-convex optimal control problems,”Proc. IEEE Conf. on Decision and Control, IEEE, 2023, pp. 3296–3302

    work page 2023

  14. [14]

    Fast homotopy for spacecraft rendezvous trajectory optimization with discrete logic,

    Malyuta, D., and Açıkmeşe, B., “Fast homotopy for spacecraft rendezvous trajectory optimization with discrete logic,”Journal of Guidance, Control, and Dynamics, Vol. 46, No. 7, 2023, pp. 1262–1279. 26

    work page 2023

  15. [15]

    Successive convexification for real-time six-degree-of-freedom powered descent guidance with state-triggered constraints,

    Szmuk, M., Reynolds, T. P., and Açıkmeşe, B., “Successive convexification for real-time six-degree-of-freedom powered descent guidance with state-triggered constraints,”Journal of Guidance, Control, and Dynamics, Vol. 43, No. 8, 2020, pp. 1399–1413

    work page 2020

  16. [16]

    Successive convexification for optimal control with signal temporal logic specifications,

    Mao, Y., Acikmese, B., Garoche, P.-L., and Chapoutot, A., “Successive convexification for optimal control with signal temporal logic specifications,”Proceedings of the 25th ACM International Conference on Hybrid Systems: Computation and Control, 2022, pp. 1–7

    work page 2022

  17. [17]

    Chance-constrained optimal path planning with obstacles,

    Blackmore, L., Ono, M., and Williams, B. C., “Chance-constrained optimal path planning with obstacles,”IEEE Transactions on Robotics, Vol. 27, No. 6, 2011, pp. 1080–1094

    work page 2011

  18. [18]

    Nonlinear uncertainty control with iterative covariance steering,

    Ridderhof, J., Okamoto, K., and Tsiotras, P., “Nonlinear uncertainty control with iterative covariance steering,”2019 IEEE 58th Conference on Decision and Control (CDC), IEEE, 2019, pp. 3484–3490

    work page 2019

  19. [19]

    Sequential chance-constrained covariance steering for robust cislunar trajectory design under uncertainties,

    Kumagai, N., and Oguri, K., “Sequential chance-constrained covariance steering for robust cislunar trajectory design under uncertainties,”AAS/AIAA Astrodynamics Specialist Conference, 2024

    work page 2024

  20. [20]

    Multiplicative Approach to Constrained Stochastic Attitude Control with Application to Rendezvous and Proximity Operations,

    Takubo, Y., and D’Amico, S., “Multiplicative Approach to Constrained Stochastic Attitude Control with Application to Rendezvous and Proximity Operations,”AAS/AIAA Astrodynamics Specialist Conference, Broomfield, CO, USA, 2024

    work page 2024

  21. [21]

    Continuous-time successive convexification for constrained trajectory optimization,

    Elango, P., Luo, D., Kamath, A. G., Uzun, S., Kim, T., and Açıkmeşe, B., “Continuous-time successive convexification for constrained trajectory optimization,”Automatica, Vol. 180, 2025, p. 112464

    work page 2025

  22. [22]

    Autonomous Formation Flying in Low Earth Orbit

    D’Amico, S., “Autonomous Formation Flying in Low Earth Orbit.” PhD Thesis, Delft University, 2010

    work page 2010

  23. [23]

    R., Gurfil, P., How, J., and Breger, L.,Spacecraft formation flying: Dynamics, control and navigation, Vol

    Alfriend, K., Vadali, S. R., Gurfil, P., How, J., and Breger, L.,Spacecraft formation flying: Dynamics, control and navigation, Vol. 2, Elsevier, 2009

    work page 2009

  24. [24]

    Autonomous Guidance Navigation and Control of the VISORS Formation-Flying Mission,

    Guffanti, T., Bell, T., Low, S. Y., Murray-Cooper, M., and D’Amico, S., “Autonomous Guidance Navigation and Control of the VISORS Formation-Flying Mission,”2023 AAS/AIAA Astrodynamics Specialist Conference, Big Sky, MT., 2023

    work page 2023

  25. [25]

    Space Interferometry Formation Design using Relative Orbital Elements: the STARI Mission,

    Rizza, A., Foss, E., Monnier, J., Cutler, J. W., and D’Amico, S., “Space Interferometry Formation Design using Relative Orbital Elements: the STARI Mission,”2026 IEEE Aerosapce Conference (accepted), 2026

    work page 2026

  26. [26]

    Safe and Optimal N-Spacecraft Swarm Reconfiguration in Non-Keplerian Cislunar Orbits,

    Takubo, Y., Manuel, W., Foss, E., and D’Amico, S., “Safe and Optimal N-Spacecraft Swarm Reconfiguration in Non-Keplerian Cislunar Orbits,”Journal of Guidance, Control, and Dynamics, 2025. Accepted for publication

    work page 2025

  27. [27]

    A goal-oriented autonomous controller for space exploration,

    Ceballos, A., Bensalem, S., Cesta, A., De Silva, L., Fratini, S., Ingrand, F., Ocon, J., Orlandini, A., Py, F., Rajan, K., et al., “A goal-oriented autonomous controller for space exploration,”ASTRA, Vol. 11, 2011

    work page 2011

  28. [28]

    Language conditioned imitation learning over unstructured data

    Lynch,C.,andSermanet,P.,“Languageconditionedimitationlearningoverunstructureddata,”arXivpreprintarXiv:2005.07648, 2020

    work page arXiv 2005

  29. [29]

    A Survey of Reinforcement Learning Informed by Natural Language

    Luketina, J., Nardelli, N., Farquhar, G., Foerster, J., Andreas, J., Grefenstette, E., Whiteson, S., and Rocktäschel, T., “A survey of reinforcement learning informed by natural language,”arXiv preprint arXiv:1906.03926, 2019

    work page internal anchor Pith review Pith/arXiv arXiv 1906

  30. [30]

    OpenVLA: An Open-Source Vision-Language-Action Model

    Kim, M. J., Pertsch, K., Karamcheti, S., Xiao, T., Balakrishna, A., Nair, S., Rafailov, R., Foster, E., Lam, G., Sanketi, P., et al., “Openvla: An open-source vision-language-action model,”arXiv preprint arXiv:2406.09246, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  31. [31]

    Vision-language-action models for robotics: A review towards real-world applications,

    Kawaharazuka, K., Oh, J., Yamada, J., Posner, I., and Zhu, Y., “Vision-language-action models for robotics: A review towards real-world applications,”IEEE Access, 2025

    work page 2025

  32. [32]

    Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program,

    Carrasco, A., Rodriguez-Fernandez, V., and Linares, R., “Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program,”Advances in Space Research, 2025

    work page 2025

  33. [33]

    Visual language models as operator agents in the space domain,

    Carrasco, A., Nedungadi, M., Rodriguez-Fernandez, V., and Linares, R., “Visual language models as operator agents in the space domain,”AIAA SCITECH 2025 Forum, 2025, p. 1543

    work page 2025

  34. [34]

    Fine-Tuned Language Models as Space Systems Controllers,

    Zucchelli, E. M., Wu, D., Briden, J., Hofmann, C., Rodriguez-Fernandez, V., and Linares, R., “Fine-Tuned Language Models as Space Systems Controllers,”arXiv preprint arXiv:2501.16588, 2025

    work page arXiv 2025

  35. [35]

    Space-LLaVA: A Vision-Language Model Adapted to Extraterrestrial Applications,

    Foutter, M., Gammelli, D., Kruger, J., Foss, E., Bhoj, P., Guffanti, T., D’Amico, S., and Pavone, M., “Space-LLaVA: A Vision-Language Model Adapted to Extraterrestrial Applications,”2025 IEEE Aerospace Conference, 2025, pp. 1–23. https://doi.org/10.1109/AERO63441.2025.11068757. 27

    work page doi:10.1109/aero63441.2025.11068757 2025

  36. [36]

    Transformers for Trajectory Optimization with Application to Spacecraft Rendezvous,

    Guffanti, T., Gammelli, D., D’Amico, S., and Pavone, M., “Transformers for Trajectory Optimization with Application to Spacecraft Rendezvous,”IEEE Aerospace Conference, 2024, pp. 1–13. https://doi.org/10.1109/AERO58975.2024.10521334

    work page doi:10.1109/aero58975.2024.10521334 2024

  37. [37]

    Transformer-based model predictive control: trajectory optimization via sequence modeling,

    Celestini, D., Gammelli, D., Guffanti, T., D’Amico, S., Capello, E., and Pavone, M., “Transformer-based model predictive control: trajectory optimization via sequence modeling,”IEEE Robotics and Automation Letters, Vol. 9, 2024, pp. 9820–9827. https://doi.org/10.1109/LRA.2024.3466069

    work page doi:10.1109/lra.2024.3466069 2024

  38. [38]

    Towards Robust Spacecraft Trajectory Optimization via Transformers,

    Takubo, Y., Guffanti, T., Gammelli, D., Pavone, M., and D’Amico, S., “Towards Robust Spacecraft Trajectory Optimization via Transformers,”IEEE Aerospace Conference, 2025

    work page 2025

  39. [39]

    Generalizable spacecraft trajectory generation via multimodal learning with transformers,

    Celestini, D., Afsharrad, A., Gammelli, D., Guffanti, T., Zardini, G., Lall, S., Capello, E., D’Amico, S., and Pavone, M., “Generalizable spacecraft trajectory generation via multimodal learning with transformers,”2025 American Control Conference (ACC), IEEE, 2025, pp. 3558–3565

    work page 2025

  40. [40]

    Agile Tradespace Exploration for Space Rendezvous Mission Design via Transformers,

    Takubo, Y., Gammelli, D., Pavone, M., and D’Amico, S., “Agile Tradespace Exploration for Space Rendezvous Mission Design via Transformers,”IEEE Aerospace Conference, 2026. (accepted)

    work page 2026

  41. [41]

    Pretraining for Language Conditioned Imitation with Transformers,

    Putterman, A. L., Lu, K., Mordatch, I., and Abbeel, P., “Pretraining for Language Conditioned Imitation with Transformers,” Offline Reinforcement Learning Workshop at Neural Information Processing Systems (NeurIPS), 2021

    work page 2021

  42. [42]

    SCvx-fast: A superlinearly convergent algorithm for a class of non-convex optimal control problems,

    Mao, Y., and Acikmese, B., “SCvx-fast: A superlinearly convergent algorithm for a class of non-convex optimal control problems,”arXiv preprint arXiv:2112.00108, 2021

    work page arXiv 2021

  43. [43]

    New state transition matrices for spacecraft relative motion in perturbed orbits,

    Koenig, A. W., Guffanti, T., and D’Amico, S., “New state transition matrices for spacecraft relative motion in perturbed orbits,” Journal of Guidance, Control, and Dynamics, Vol. 40, No. 7, 2017, pp. 1749–1768

    work page 2017

  44. [44]

    Adaptive End-to-End Architecture for Autonomous Spacecraft Navigation and Control During Rendezvous and Proximity Operations,

    Kruger, J. J., Guffanti, T., Park, T. H., Murray-Cooper, M., Low, S. Y., Bell, T., D’Amico, S., Roscoe, C. W., and Westphal, J., “Adaptive End-to-End Architecture for Autonomous Spacecraft Navigation and Control During Rendezvous and Proximity Operations,”AIAA SCITECH 2024 Forum, 2024, p. 0430

    work page 2024

  45. [45]

    DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

    Sanh, V., Debut, L., Chaumond, J., and Wolf, T., “DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter,” arXiv preprint arXiv:1910.01108, 2019

    work page internal anchor Pith review Pith/arXiv arXiv 1910

  46. [46]

    Robust nrho station-keeping planning with maneuver location optimization under operational uncertainties,

    Kumagai, N., and Oguri, K., “Robust nrho station-keeping planning with maneuver location optimization under operational uncertainties,”AAS/AIAA Astrodynamics Specialist Conference, 2023

    work page 2023

  47. [47]

    UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction,

    McInnes, L., Healy, J., and Melville, J., “UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction,” ,

    work page

  48. [48]

    URL https://arxiv.org/abs/1802.03426

    work page internal anchor Pith review Pith/arXiv arXiv

  49. [49]

    Pytorch: An imperative style, high-performance deep learning library,

    Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al., “Pytorch: An imperative style, high-performance deep learning library,”Advances in neural information processing systems, Vol. 32, 2019. 28

    work page 2019