发表机构
State Key Laboratory of Astronautic Dynamics（宇航动力学国家重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究低推力轨迹优化面临的问题，提出基于大语言模型的HELIOS智能体，能自主进行PMP符号推导等。其创新包括约束自适应推导框架等，实验表明可解决多种轨迹优化问题，验证了模型无关架构及模型规模与推导能力的正相关。
AI 中文摘要
低推力轨迹优化是深空任务设计中的核心技术。基于庞特里亚金最小值原理（PMP）的间接方法虽提供了严格的最优性保证，但实际应用面临三个瓶颈：需针对每种约束类型逐案推导横截条件；不同动力学模型需重复代码重写；射击方程对初始猜测高度敏感。本文提出了HELIOS（低推力星际优化系统启发式引擎），一个围绕大语言模型构建的轨迹优化智能体。给定自然语言描述的物理问题，该系统可自主执行PMP符号推导、SymPy验证、C++射击代码生成和数值求解，无需人工干预。关键创新包括：一个约束自适应推导框架，将任意约束统一为psi(x,p)=0形式并自动生成自由参数的平稳条件；动力学自适应四模块代码生成，支持非标准动力学而无需修改底层模板；一个涵盖PMP推导中关键易错点的通用推导规则集。在11个渐进测试场景上的实验表明，HELIOS能正确推导并解决从简单交会（8个变量）到多段停留转移（48个变量）、重力辅助轨迹（17个变量）和太阳帆最短时间转移（8个变量）等问题。最佳编译成功率达到100%（11/11）。多模型比较（8个开源大语言模型后端，总分250 - 905）验证了模型无关架构，并揭示了模型规模与推导能力之间的正相关关系。
英文摘要
Low-thrust trajectory optimization is a core technology in deep-space mission design. Indirect methods based on Pontryagin's Minimum Principle (PMP) offer rigorous optimality guarantees, yet their practical application faces three bottlenecks: (1) transversality conditions must be derived case by case for each constraint type; (2) different dynamics models require repeated code rewrites; and (3) shooting equations are highly sensitive to initial guesses. This paper presents HELIOS (Heuristic Engine for Low-thrust Interplanetary Optimization System), a trajectory optimization agent built around a large language model (LLM). Given a physical problem described in natural language, the system autonomously performs PMP symbolic derivation, SymPy verification, C++ shooting-code generation, and numerical solution without human intervention. Key innovations include: (1) a constraint-adaptive derivation framework that unifies arbitrary constraints into psi(x,p)=0 form and automatically generates stationarity conditions for free parameters (e.g., gravity-assist turning angle); (2) dynamics-adaptive four-module code generation supporting non-standard dynamics (solar sail, J2 perturbation) without modifying the underlying template; and (3) a general derivation rule set covering critical error-prone points in PMP derivation. Experiments on 11 progressive test scenarios show that HELIOS correctly derives and solves problems from simple rendezvous (8 variables) to multi-leg stay transfers (48 variables), gravity-assist trajectories (17 variables), and solar-sail minimum-time transfers (8 variables). The best compilation success rate reaches 100% (11/11). A multi-model comparison (8 open-source LLM backends, total scores 250-905) verifies the model-agnostic architecture and reveals a positive correlation between model scale and derivation capability.
