LLM-Enhanced Symbolic Control for Safety-Critical Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913865759981568 |
|---|---|
| author | Bayat, Amir Abate, Alessandro Ozay, Necmiye Jungers, Raphael M. |
| author_facet | Bayat, Amir Abate, Alessandro Ozay, Necmiye Jungers, Raphael M. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_11077 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-Enhanced Symbolic Control for Safety-Critical Applications Bayat, Amir Abate, Alessandro Ozay, Necmiye Jungers, Raphael M. Systems and Control 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. |
| title | LLM-Enhanced Symbolic Control for Safety-Critical Applications |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2505.11077 |