LLM-Enhanced Symbolic Control for Safety-Critical Applications

TL;DR

This paper presents a framework that uses Large Language Models to translate natural language specifications into formal control code for safety-critical applications, ensuring correctness and robustness.

Contribution

It introduces a novel LLM-based approach for synthesizing formal controllers from natural language, integrating verification to enhance safety in control systems.

Findings

Handles linguistic variability effectively

Improves robustness over direct LLM planning

Ensures safety through automated verification

Abstract

Motivated by Smart Manufacturing and Industry 4.0, we introduce a framework for synthesizing Abstraction-Based Controller Design (ABCD) for reach-avoid problems from Natural Language (NL) specifications using Large Language Models (LLMs). A Code Agent interprets an NL description of the control problem and translates it into a formal language interpretable by state-of-the-art symbolic control software, while a Checker Agent verifies the correctness of the generated code and enhances safety by identifying specification mismatches. Evaluations show that the system handles linguistic variability and improves robustness over direct planning with LLMs. The proposed approach lowers the barrier to formal control synthesis by enabling intuitive, NL-based task definition while maintaining safety guarantees through automated validation.