GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback

TL;DR

GLLM is a system that uses large language models with self-correction and user feedback to automatically generate accurate G-code from natural language instructions, simplifying CNC programming.

Contribution

The paper presents GLLM, a novel framework combining domain-specific training, retrieval-augmented generation, and self-corrective mechanisms for reliable G-code generation from natural language.

Findings

High syntactic and semantic accuracy in G-code output

Effective validation mechanisms improve reliability

Democratizes CNC programming for non-experts

Abstract

This paper introduces GLLM, an innovative tool that leverages Large Language Models (LLMs) to automatically generate G-code from natural language instructions for Computer Numerical Control (CNC) machining. GLLM addresses the challenges of manual G-code writing by bridging the gap between human-readable task descriptions and machine-executable code. The system incorporates a fine-tuned StarCoder-3B model, enhanced with domain-specific training data and a Retrieval-Augmented Generation (RAG) mechanism. GLLM employs advanced prompting strategies and a novel self-corrective code generation approach to ensure both syntactic and semantic correctness of the generated G-code. The architecture includes robust validation mechanisms, including syntax checks, G-code-specific verifications, and functional correctness evaluations using Hausdorff distance. By combining these techniques, GLLM aims to democratize CNC programming, making it more accessible to users without extensive programming experience while maintaining high accuracy and reliability in G-code generation.