Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces the AI Control Scientist (AICS), an innovative LLM-driven agent designed to automate control system design by translating user requirements into optimized controllers. By employing a Task Modeling Agent, a Controller Design Agent, and a Parameter Tuning Agent, AICS significantly enhances the efficiency and scalability of control design processes, traditionally reliant on expert knowledge and manual tuning. Experimental results indicate that AICS not only generates multiple effective control systems but also surpasses existing automated methods in both design success rates and optimization efficiency.
AICS transforms control system design from a manual, expert-driven process to an efficient, automated agent-driven approach that outperforms traditional methods.
Control system design is critical for modern industry, such as chemical process temperature regulation and aero-engine control. However,traditional control design workflows rely heavily on expert knowledge and extensive manual parameter tuning, resulting in limited efficiency and scalability. To this end, this paper proposes AI Control Scientist (AICS), the first large language model (LLM)-driven agent capable of automatically generating optimized controller from language design requirements. Specifically, a Task Modeling Agent interprets user requirements to engineering constraints; a Controller Design Agent generate candidate controller structures and executable code; and a Parameter Tuning Agent refine controller parameters under closed-loop performance criteria. Experiments demonstrate that the proposed agentic system can automatically generate multiple representative control systems, outperforms existing automated baselines in both design success rate and optimization efficiency. This work has the potential to transform control system design from human-driven to agent-driven, paving the way for model predictive control and other advanced control systems design.