Modeling and Recovering Hierarchical Structural Architectures of ROS 2 Systems from Code and Launch Configurations using LLM-based Agents

TL;DR

This paper introduces a UML-based modeling approach and an automated pipeline using LLMs to recover and analyze hierarchical architectures of ROS 2 systems from code and launch configurations, enhancing system understanding and maintenance.

Contribution

It presents a novel UML-based modeling concept and an LLM-guided recovery pipeline for extracting hierarchical architectures from ROS 2 code and configurations, addressing limitations of existing methods.

Findings

High precision in architecture recovery across abstraction levels

Subsystem-level recall decreases with repository complexity

Deterministic validation improves reliability of the models

Abstract

Model-Driven Engineering (MDE) relies on explicit architecture models to document and evolve systems across abstraction levels. For ROS~2, subsystem structure is often encoded implicitly in distributed configuration artifacts -- most notably launch files -- making hierarchical structural decomposition hard to capture and maintain. Existing ROS~2 modeling approaches cover node-level entities and wiring, but do not make hierarchical structural (de-)composition a first-class architectural view independent of launch artifacts. We contribute (1) a UML-based modeling concept for hierarchical structural architectures of ROS~2 systems and (2) a blueprint-guided automated recovery pipeline that reconstructs such models from code and configuration artifacts by combining deterministic extraction with LLM-based agents. The ROS~2 architectural blueprint (nodes, topics, interfaces, launch-induced wiring) is encoded as structural contracts to constrain synthesis and enable deterministic validation, improving reliability. We evaluate the approach on three ROS~2 repositories, including an industrial-scale code subset. Results show high precision across abstraction levels, while subsystem-level recall drops with repository complexity due to implicit launch semantics, making high-level recovery the remaining challenge.