LLM-Enabled Low-Altitude UAV Natural Language Navigation via Signal Temporal Logic Specification Translation and Repair

arXiv cs.RO / 3/31/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper presents a framework that converts natural-language navigation instructions for low-altitude UAVs into Signal Temporal Logic (STL) specifications and then synthesizes safe trajectories using mixed-integer linear programming (MILP).
It introduces a reasoning-enhanced LLM trained with chain-of-thought (CoT) supervision and group-relative policy optimization (GRPO) to improve syntactic validity and semantic consistency when translating free-form text into executable STL formulas.
To handle infeasible or overly strict requirements, it adds a specification repair mechanism that uses MILP-based diagnosis plus LLM-guided semantic reasoning to relax constraints while maintaining safety guarantees.
The authors report that extensive simulations and real-world flight experiments show improved robustness for NL-to-STL translation and enable interpretable, adaptable, safety-critical UAV navigation in complex environments.

Abstract

Natural language (NL) navigation for low-altitude unmanned aerial vehicles (UAVs) offers an intelligent and convenient solution for low-altitude aerial services by enabling an intuitive interface for non-expert operators. However, deploying this capability in urban environments necessitates the precise grounding of underspecified instructions into safety-critical, dynamically feasible motion plans subject to spatiotemporal constraints. To address this challenge, we propose a unified framework that translates NL instructions into Signal Temporal Logic (STL) specifications and subsequently synthesizes trajectories via mixed-integer linear programming (MILP). Specifically, to generate executable STL formulas from free-form NL, we develop a reasoning-enhanced large language model (LLM) leveraging chain-of-thought (CoT) supervision and group-relative policy optimization (GRPO), which ensures high syntactic validity and semantic consistency. Furthermore, to resolve infeasibilities induced by stringent logical or spatial requirements, we introduce a specification repair mechanism. This module combines MILP-based diagnosis with LLM-guided semantic reasoning to selectively relax task constraints while strictly enforcing safety guarantees. Extensive simulations and real-world flight experiments demonstrate that the proposed closed-loop framework significantly improves NL-to-STL translation robustness, enabling safe, interpretable, and adaptable UAV navigation in complex scenarios.