GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback
It addresses the challenge of making CNC programming more accessible to users without extensive experience, though it appears incremental as it builds on existing LLM and RAG techniques.
This paper tackles the problem of manual G-code writing for CNC machining by introducing GLLM, a tool that uses LLMs to generate G-code from natural language instructions, achieving high accuracy and reliability through self-corrective methods and validation mechanisms.
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.