OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous
Abstract
Spacecraft rendezvous and proximity operations (RPO) are currently planned through an expertise-intensive process in which engineers translate high-level operational intent into safe, dynamically feasible trajectories, creating a bottleneck to scalable operations. Large language model (LLM)-based agents could offer an intuitive interface for this process, although their outputs are not inherently grounded in orbital dynamics, operational constraints, or the structure of admissible spacecraft maneuvers. To exploit their semantic reasoning while ensuring the generated plan's physical validity, this paper presents a hierarchical framework for spacecraft task-and-motion planning (TAMP) that grounds LLM reasoning in a graph of reusable behaviors and domain-specific planning modules. Within this framework, a pretrained LLM maps a natural-language command to a partial mission specification. The associated planners then resolve unspecified decisions within the admissible operational space. Finally, trajectory optimization converts the completed mission specification into a dynamically feasible trajectory. Numerical experiments demonstrate that this architecture substantially improves intent recovery over direct LLM generation, achieving 98% exact recovery of partial mission specifications across all evaluated splits when backed by frontier LLMs. Additional test-time-compute experiments show that, for a compact 9B model, verifier-guided revision increases exact recovery from 75% to 88%, while broader behavior-plan search independently improves selection among admissible trajectory realizations. Overall, these results establish a scalable and auditable foundation for language-driven agentic planning of spacecraft RPO.
Related
- PLUTO: An Agentic AI Tool for Interactive Spacecraft Rendezvous Trajectory Design
- Constrained Attitude Reorientation Maneuver of Spacecraft based on Path Planning
- Information-Based Trajectory Planning for Spacecraft-to-Spacecraft Tracking and Navigation in Cislunar Space
- Quantum-assisted rendezvous on hypercubes: a quantum Bernoulli noise approach
- Double Gravity-Assist Rendezvous Trajectory to Halley's Comet Using Deep-Space Low Thrust
BibTeX
@misc{takubo2026orbittamp,
title = {{OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous}},
author = {Yuji Takubo and Daniele Gammelli and Marco Pavone and Simone D'Amico},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.01093},
eprint = {2610.01093},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.01093},
}
RIS
TY - UNPB
TI - OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous
AU - Yuji Takubo
AU - Daniele Gammelli
AU - Marco Pavone
AU - Simone D'Amico
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.01093
UR - https://arxiv.org/abs/2610.01093
AB - Spacecraft rendezvous and proximity operations (RPO) are currently planned through an expertise-intensive process in which engineers translate high-level operational intent into safe, dynamically feasible trajectories, creating a bottleneck to scalable operations. Large language model (LLM)-based agents could offer an intuitive interface for this process, although their outputs are not inherently grounded in orbital dynamics, operational constraints, or the structure of admissible spacecraft maneuvers. To exploit their semantic reasoning while ensuring the generated plan's physical validity, this paper presents a hierarchical framework for spacecraft task-and-motion planning (TAMP) that grounds LLM reasoning in a graph of reusable behaviors and domain-specific planning modules. Within this framework, a pretrained LLM maps a natural-language command to a partial mission specification. The associated planners then resolve unspecified decisions within the admissible operational space. Finally, trajectory optimization converts the completed mission specification into a dynamically feasible trajectory. Numerical experiments demonstrate that this architecture substantially improves intent recovery over direct LLM generation, achieving 98% exact recovery of partial mission specifications across all evaluated splits when backed by frontier LLMs. Additional test-time-compute experiments show that, for a compact 9B model, verifier-guided revision increases exact recovery from 75% to 88%, while broader behavior-plan search independently improves selection among admissible trajectory realizations. Overall, these results establish a scalable and auditable foundation for language-driven agentic planning of spacecraft RPO.
ER -