Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Mohamed Benchat, Dominique Briechle, Raj Chanchad, Mitbhai Chauhan, Meet Chavda, Ruidi He, Dhruv Jajadiya, Dhruv Kapadiya, Nidhiben Kaswala, Daniel Osterholz, Andreas Rausch, Meng Zhang

TL;DR

A UML-based modeling concept for hierarchical structural architectures of ROS~2 systems and a blueprint-guided automated recovery pipeline that reconstructs such models from code and configuration artifacts by combining deterministic extraction with LLM-based agents are contributed.

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.

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

TL;DR

A UML-based modeling concept for hierarchical structural architectures of ROS~2 systems and a blueprint-guided automated recovery pipeline that reconstructs such models from code and configuration artifacts by combining deterministic extraction with LLM-based agents are contributed.

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.
Paper Structure (26 sections, 1 equation, 4 figures, 3 tables)

This paper contains 26 sections, 1 equation, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Modeling/description techniques for ROS 2 architectures
  4. Structural architecture recovery and LLM-based recovery
  5. UML-based Modeling for Hierarchical Structural Architecture of ROS 2 Systems
  6. AtomicRosNodeClassifier
  7. Mapping to Source Code and Naming
  8. Port Definition and Typing Semantics
  9. Interface Types
  10. RosNodePart
  11. Instantiation and Structural Conformance
  12. Interfaces Between RosNodeParts
  13. ComposedRosNodeClassifier
  14. Mapping to Launch Files and Naming
  15. Port Definition and Typing Semantics
  16. ...and 11 more sections

Figures (4)

  • Figure 1: Code-level and Architecture-level representation of the AtomicRosNodeClassifierFooNode, including the AtomicClassifierDiagram and the associated Message & ServiceTypeDiagram. The colored Trace lines indicate the mapping between model annotations and code-level identifiers.
  • Figure 2: Code- and architecture-level representation of the ComposedRosNodeClassifierCompose_example. The architecture-level view comprises two ComposedClassifierDiagrams; atomic classifier structures are embedded but not explicitly represented as separate diagrams. Colored Trace lines indicate the mapping between model annotations and code-level identifiers.
  • Figure 3: C4-conformed Architecture of Blueprint-Guided Automated Architecture Recovery System (retrofitted after brown2013software).
  • Figure 4: Setup of Experimental Evaluation Pipeline