发表机构
Stanford University; Italian Institute of Artificial Intelligence (AI4I); NVIDIA Research（斯坦福大学; 意大利人工智能研究所; 英伟达研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出OrbitTAMP分层框架，将LLM推理根植于行为图与领域规划模块，实现航天器交会任务的语言驱动规划，显著提升意图恢复精度。
AI 中文摘要
航天器交会与近距离操作（RPO）目前是通过一个高度依赖专业知识的流程进行规划的，在该流程中，工程师将高层级的操作意图转化为安全、动态可行的轨迹，这构成了可扩展操作的瓶颈。基于大语言模型（LLM）的智能体可为这一流程提供直观的界面，尽管其输出本质上并未根植于轨道动力学、操作约束或可容许的航天器机动结构。为了利用其语义推理能力，同时确保所生成规划的物理有效性，本文提出了一种用于航天器任务与运动规划（TAMP）的分层框架，该框架将LLM推理根植于一个由可复用行为和领域特定规划模块组成的图结构中。在该框架内，一个预训练的LLM将自然语言指令映射为部分任务规范。相关的规划器随后在可容许的操作空间内解析未指定的决策。最后，轨迹优化将完整的任务规范转化为动态可行的轨迹。数值实验表明，与直接LLM生成相比，该架构显著提高了意图恢复能力，在由前沿LLM支持时，在所有评估分割上实现了对部分任务规范的98%精确恢复。额外的测试时计算实验表明，对于紧凑的9B模型，验证器引导的修订将精确恢复率从75%提高到88%，而更广泛的行为规划搜索独立地改善了可容许轨迹实现中的选择。总体而言，这些结果为语言驱动的航天器RPO智能体规划奠定了可扩展且可审计的基础。
英文摘要
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.
Comments20 pages, 8 figures
