LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models
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_ | 1866912504952651776 |
|---|---|
| author | Zhou, Zhongchao Lu, Yuxi Zhu, Yaonan Zhao, Yifan He, Bin He, Liang Yu, Wenwen Iwasawa, Yusuke |
| author_facet | Zhou, Zhongchao Lu, Yuxi Zhu, Yaonan Zhao, Yifan He, Bin He, Liang Yu, Wenwen Iwasawa, Yusuke |
| contents | With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have explored the use of LLMs in feedback controller design; however, these efforts are restricted to overly simplified systems, fixed-structure gain tuning, and lack real-world validation. To further investigate LLMs in automatic control, this work targets a key subfield: adaptive control. Inspired by the framework of model reference adaptive control (MRAC), we propose an LLM-guided adaptive compensator framework that avoids designing controllers from scratch. Instead, the LLMs are prompted using the discrepancies between an unknown system and a reference system to design a compensator that aligns the response of the unknown system with that of the reference, thereby achieving adaptivity. Experiments evaluate five methods: LLM-guided adaptive compensator, LLM-guided adaptive controller, indirect adaptive control, learning-based adaptive control, and MRAC, on soft and humanoid robots in both simulated and real-world environments. Results show that the LLM-guided adaptive compensator outperforms traditional adaptive controllers and significantly reduces reasoning complexity compared to the LLM-guided adaptive controller. The Lyapunov-based analysis and reasoning-path inspection demonstrate that the LLM-guided adaptive compensator enables a more structured design process by transforming mathematical derivation into a reasoning task, while exhibiting strong generalizability, adaptability, and robustness. This study opens a new direction for applying LLMs in the field of automatic control, offering greater deployability and practicality compared to vision-language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20509 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models Zhou, Zhongchao Lu, Yuxi Zhu, Yaonan Zhao, Yifan He, Bin He, Liang Yu, Wenwen Iwasawa, Yusuke Robotics Artificial Intelligence Systems and Control With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have explored the use of LLMs in feedback controller design; however, these efforts are restricted to overly simplified systems, fixed-structure gain tuning, and lack real-world validation. To further investigate LLMs in automatic control, this work targets a key subfield: adaptive control. Inspired by the framework of model reference adaptive control (MRAC), we propose an LLM-guided adaptive compensator framework that avoids designing controllers from scratch. Instead, the LLMs are prompted using the discrepancies between an unknown system and a reference system to design a compensator that aligns the response of the unknown system with that of the reference, thereby achieving adaptivity. Experiments evaluate five methods: LLM-guided adaptive compensator, LLM-guided adaptive controller, indirect adaptive control, learning-based adaptive control, and MRAC, on soft and humanoid robots in both simulated and real-world environments. Results show that the LLM-guided adaptive compensator outperforms traditional adaptive controllers and significantly reduces reasoning complexity compared to the LLM-guided adaptive controller. The Lyapunov-based analysis and reasoning-path inspection demonstrate that the LLM-guided adaptive compensator enables a more structured design process by transforming mathematical derivation into a reasoning task, while exhibiting strong generalizability, adaptability, and robustness. This study opens a new direction for applying LLMs in the field of automatic control, offering greater deployability and practicality compared to vision-language models. |
| title | LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models |
| topic | Robotics Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/2507.20509 |