Utilizing LLMs for Industrial Process Automation: A Case Study on Modifying RAPID Programs
Salim Fares, Steffen Herbold
TL;DR
The paper investigates whether a generic, off-the-shelf LLM can assist industrial RAPID programming for ABB robotic arms without domain-specific fine-tuning, using on-premise inference and carefully crafted few-shot prompts. AKE Technologies provides real-world data, and a rule-based verifier assesses output correctness across three modification tasks with varying complexity. Results show near-perfect accuracy for simple argument changes, high accuracy for adding offsets with multiple attempts, and lower accuracy for reversing routines, especially under language prompts that are not English. The study demonstrates the viability of AI-assisted, well-bounded RAPID code modifications in SME contexts while highlighting the need for robust validation and cautious integration into development workflows.
Abstract
How to best use Large Language Models (LLMs) for software engineering is covered in many publications in recent years. However, most of this work focuses on widely-used general purpose programming languages. The utility of LLMs for software within the industrial process automation domain, with highly-specialized languages that are typically only used in proprietary contexts, is still underexplored. Within this paper, we study enterprises can achieve on their own without investing large amounts of effort into the training of models specific to the domain-specific languages that are used. We show that few-shot prompting approaches are sufficient to solve simple problems in a language that is otherwise not well-supported by an LLM and that is possible on-premise, thereby ensuring the protection of sensitive company data.