Language-Conditioned Safe Trajectory Generation for Spacecraft Rendezvous
Not on the map. Why?
Abstract (arXiv)
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/
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 29 of its 56 references that are in the map. First posted on arXiv 9 Dec 2025.
Builds on
29 of 56 references.
References · 29
- 2017Attention Is All You Needcited by 59,932
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
- 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
- 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
- 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
- 2020Language Conditioned Imitation Learning over Unstructured Datacited by 208
- 2019A Survey of Reinforcement Learning Informed by Natural Languagecited by 154
- 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
- 2023Transformers for Trajectory Optimization with Application to Spacecraft Rendezvouscited by 15
- 2024Transformer-based Model Predictive Control: Trajectory Optimization via Sequence Modelingcited by 15
17 more
- 2024Space-LLaVA: a Vision-Language Model Adapted to Extraterrestrial Applicationscited by 14
- 2016Successive Convexification of Non-Convex Optimal Control Problems and Its Convergence Propertiescited by 10
- 2019GuSTO: Guaranteed Sequential Trajectory Optimization via Sequential Convex Programmingcited by 9
- 2024Towards Robust Spacecraft Trajectory Optimization via Transformerscited by 9
- 2023Successive Convexification with Feasibility Guarantee via Augmented Lagrangian for Non-Convex Optimal Control Problemscited by 7
- 2019Nonlinear Uncertainty Control with Iterative Covariance Steeringcited by 6
- 2024Generalizable Spacecraft Trajectory Generation via Multimodal Learning with Transformerscited by 6
- 2025Visual Language Models as Operator Agents in the Space Domaincited by 6
- 2023Autonomous Guidance Navigation and Control of the VISORS Formation-Flying Missioncited by 5
- 2025Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Programcited by 5
- 2021Fast Homotopy for Spacecraft Rendezvous Trajectory Optimization with Discrete Logiccited by 4
- 2025Fine-Tuned Language Models as Space Systems Controllerscited by 4
- 2025Agile Tradespace Exploration for Space Rendezvous Mission Design via Transformerscited by 4
- 2024Chance-Constrained, Drift-Safe Guidance for Spacecraft Rendezvouscited by 3
- 2025Safe and Optimal N-Spacecraft Swarm Reconfiguration in Non-Keplerian Cislunar Orbitscited by 3
- 2021SCvx-fast: A Superlinearly Convergent Algorithm for A Class of Non-Convex Optimal Control Problemscited by 1
- 2025Efficient Input-Constrained Impulsive Optimal Control of Linear Systems with Application to Spacecraft Relative Motioncited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.
- 2026Semantic Constraint Synthesis for Adaptive Trajectory Optimization via Large Language Modelscited by 1
- 2026Transformer-Based Warm-Starting for Feasible and Optimal Terminal Approach to Tumbling Objects with Space Manipulatorscited by 1
- 2026OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvouscited by 0
- 2026OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous1 Oct 2026
- 2026Transformer-Based Warm-Starting for Feasible and Optimal Terminal Approach to Tumbling Objects with Space Manipulators15 Jun 2026
- 2026Semantic Constraint Synthesis for Adaptive Trajectory Optimization via Large Language Models2 Jun 2026