PLUTO: An Agentic AI Tool for Interactive Spacecraft Rendezvous Trajectory Design
Abstract
Modern space missions require trajectory design methods capable of efficiently adapting to diverse mission objectives and operational constraints. Despite the maturity of non-convex trajectory optimization techniques, their broader adoption remains limited by the substantial domain expertise required to tailor problem formulations across varying mission scenarios. Recent advances in large language model (LLM) reasoning and agentic AI coding capabilities offer a promising pathway to improving the accessibility of advanced trajectory optimization techniques. This paper introduces PLUTO (Plain Language Understanding for Trajectory Optimization), an interactive trajectory design framework that integrates agentic AI coding tools within a sequential convex programming (SCP) architecture. The proposed system maps high-level semantic inputs to well-defined mathematical constraints while preserving a structured representation suitable for SCP. These constraints are processed through an auto-convexification pipeline and incorporated directly into executable optimal control formulations, thereby systematically connecting user intent and trajectory generation. Visual constraint verification and scenario parameterization further support an intuitive environment for trajectory design across a wide range of application scenarios. Within an evaluation of 50 natural-language rendezvous mission prompts spanning 10 constraint types, PLUTO generated a trajectory for every prompt, and 94% of the resulting trajectories satisfied both the quantitative and qualitative requirements of the mission intent. Ultimately, this work explores the potential of agentic AI to bridge the gap between advanced optimization algorithms and engineer-focused trajectory design workflows.
Related
- OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous
- Double Gravity-Assist Rendezvous Trajectory to Halley's Comet Using Deep-Space Low Thrust
- Information-Based Trajectory Planning for Spacecraft-to-Spacecraft Tracking and Navigation in Cislunar Space
- Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning
- Design and Implementation of Interactive Videos in Undergraduate Transnational Education
BibTeX
@misc{brosius2026pluto,
title = {{PLUTO: An Agentic AI Tool for Interactive Spacecraft Rendezvous Trajectory Design}},
author = {Eleanor Brosius and Yuji Takubo and Daniele Gammelli and Simone D'Amico and Marco Pavone},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.07573},
eprint = {2610.07573},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.07573},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - PLUTO: An Agentic AI Tool for Interactive Spacecraft Rendezvous Trajectory Design
AU - Eleanor Brosius
AU - Yuji Takubo
AU - Daniele Gammelli
AU - Simone D'Amico
AU - Marco Pavone
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.07573
UR - https://arxiv.org/abs/2610.07573
AB - Modern space missions require trajectory design methods capable of efficiently adapting to diverse mission objectives and operational constraints. Despite the maturity of non-convex trajectory optimization techniques, their broader adoption remains limited by the substantial domain expertise required to tailor problem formulations across varying mission scenarios. Recent advances in large language model (LLM) reasoning and agentic AI coding capabilities offer a promising pathway to improving the accessibility of advanced trajectory optimization techniques. This paper introduces PLUTO (Plain Language Understanding for Trajectory Optimization), an interactive trajectory design framework that integrates agentic AI coding tools within a sequential convex programming (SCP) architecture. The proposed system maps high-level semantic inputs to well-defined mathematical constraints while preserving a structured representation suitable for SCP. These constraints are processed through an auto-convexification pipeline and incorporated directly into executable optimal control formulations, thereby systematically connecting user intent and trajectory generation. Visual constraint verification and scenario parameterization further support an intuitive environment for trajectory design across a wide range of application scenarios. Within an evaluation of 50 natural-language rendezvous mission prompts spanning 10 constraint types, PLUTO generated a trajectory for every prompt, and 94% of the resulting trajectories satisfied both the quantitative and qualitative requirements of the mission intent. Ultimately, this work explores the potential of agentic AI to bridge the gap between advanced optimization algorithms and engineer-focused trajectory design workflows.
ER -