HELIOS: An LLM-Driven Autonomous Indirect Trajectory Optimization Agent
This work addresses key limitations of indirect methods in low-thrust trajectory optimization—namely, the manual derivation of transversality conditions, code reimplementation upon dynamical model changes, and the sensitivity of shooting methods to initial guesses. The authors propose an autonomous optimization agent powered by large language models that accepts natural-language mission descriptions and automatically performs symbolic derivations based on Pontryagin’s Minimum Principle (PMP), validates them via SymPy, and generates high-performance C++ solvers. Central innovations include a constraint-adaptive derivation framework that uniformly handles arbitrary terminal constraints and auto-generates smoothness conditions for free parameters, a dynamics-adaptive four-module architecture accommodating non-standard dynamics, and a comprehensive rule set covering common PMP derivation pitfalls. The approach successfully solves 11 progressively complex scenarios—including rendezvous, multi-phase hovering, gravity assists, and minimum-time solar sail transfers—with 8–48 variables, demonstrating model-agnosticism and scalability.