MCCoder: Streamlining Motion Control with LLM-Assisted Code Generation and Rigorous Verification

TL;DR

MCCoder leverages large language models, structured workflows, and simulation to generate, verify, and improve motion control code, enhancing safety and efficiency in factory automation.

Contribution

This paper introduces MCCoder, a novel LLM-based system for motion control code generation with integrated verification and a new benchmark dataset, MCEVAL.

Findings

MCCoder achieves 33.09% performance improvement over baselines.

Significant accuracy and safety enhancements through simulation and data verification.

Outperforms existing models on complex motion tasks in MCEVAL dataset.

Abstract

Large Language Models (LLMs) have demonstrated significant potential in code generation. However, in the factory automation sector, particularly motion control, manual programming, alongside inefficient and unsafe debugging practices, remains prevalent. This stems from the complex interplay of mechanical and electrical systems and stringent safety requirements. Moreover, most current AI-assisted motion control programming efforts focus on PLCs, with little attention given to high-level languages and function libraries. To address these challenges, we introduce MCCoder, an LLM-powered system tailored for generating motion control code, integrated with a soft-motion controller. MCCoder improves code generation through a structured workflow that combines multitask decomposition, hybrid retrieval-augmented generation (RAG), and iterative self-correction, utilizing a well-established motion library. Additionally, it integrates a 3D simulator for intuitive motion validation and logs of full motion trajectories for data verification, significantly enhancing accuracy and safety. In the absence of benchmark datasets and metrics tailored for evaluating motion control code generation, we propose MCEVAL, a dataset spanning motion tasks of varying complexity. Experiments show that MCCoder outperforms baseline models using Advanced RAG, achieving an overall performance gain of 33.09% and a 131.77% improvement on complex tasks in the MCEVAL dataset.