Low-Code is a paradigm for domain experts to deal with their software requirements themselves, potentially without training in software engineering. In industrial automation, and in particular in robot programming, there are many layers of abstraction from atomic instructions up to compound skills. Given the recent advances in Artificial Intelligence (AI) for software engineering, we present an initial exploratory study that demonstrates the transformation of robot programs into low-code with Large Language Models (LLMs) using examples from an industry-academia collaboration. In particular, we investigate the capabilities of the LLMs GPT-40 and Mistral 7B in terms of robot program analysis and abstraction. The results show the potential of LLMs for low-code generation, but also raise questions and directions for future research.

A Low-Code Development Platform (LCDP) enables people with little or no software development training to create software applications. Unlike traditional textual programming environments, it provides tools that are more natural to the users, such as visual programming. By raising the level of abstraction beyond code, an LCDP empowers those who need software to develop it, bridging the gap between the growing demand for industrial software and the ability to deliver it. In this paper, we present an iterative, user-centered approach for developing an LCDP for welding robot control that replaces a system based on the C programming language. Findings indicate that an iterative approach, active user participation, usability evaluations, and paper prototyping all favor the successful development of an industrial LCDP.

Low-Code (Software) Development (LCD or LCSD) promises to reduce time-to-market, lower development costs, and make software development accessible to domain experts without software development training. By raising the level of abstraction beyond code through visual programming and model-driven development, a Low-Code Development Platform (LCDP) provides the tools to create software using the low-code approach. LCDPs typically support specific application types and domains such as web applications, mobile applications, data analytics platforms and dashboards. While some LCDPs exist for control systems in the manufacturing industry, this domain is not yet fully supported. In this paper, we present a multiple-case study based on five interviews to explore the role LCDPs can play in industrial automation. In particular, we investigate which use cases are considered relevant for LCDPs and what the actual requirements for such platforms are from an industrial perspective. Our results show that many different manufacturing use cases could be implemented by or already benefit from LCDPs. However, successful future LCDPs must meet certain industry-specific requirements.

Adapting the behavior of robots and their interaction with other machines on the shop floor is typically accomplished by non-programmers. Often these non-programmers use visual languages to specify the robot’s and/or machine’s control logic. While visual languages are explored as a means to enable novices to program, there is little understanding of what problems novices face when tasked with realistic adaptation programming tasks on the shop floor. In this paper, we report the results of a controlled experiment where domain experts in the injection molding industry inspected and changed realistic programs involving a robot, injection molding machine, and additional external machines. We found that participants were comparably quick to understand the program behavior with a familiar sequential function chart-based language and a Blockly-based language used for the first time. We also observed that these non-programmers had difficulty in multiple aspects independent of language due to the interweaving of physical and software-centric interaction between robot and machine. We conclude that assistance needs to go beyond optimizing available language elements to include suggesting relevant programming elements and their sequence.

The paradigm shift triggered by Industry 4.0 leads to a fast rising number of industrial machinery and collaborative robots that increases the need for flexible customization of production processes and automation workflows. End-user programming of industrial robots has become an essential capability for all areas in industry. In this paper, we investigate the applicability of block-based programming languages for large and complex robot programs. Therefore, we implemented a real-world program for industrial robots using Blockly, a block-based visual language, and assessed the results regarding portability, readability, understandability, and maintainability. Our findings are, that (1) large and complex real-world robot programs can be expressed in Blockly, (2) that the readability and understandability of such programs is equal to conventional flow-chart based programming languages, and (3) that the maintainability of Blockly programs can even be considered better than in flowchart based languages. Our results and findings serve as basis for usability studies with end-users in robot programming.