Skills Composition Framework for Reconfigurable Cyber-Physical Production Modules
Aleksandr Sidorenko, Achim Wagner, Martin Ruskowski
TL;DR
The paper tackles the challenge of reconfigurable cyber-physical production systems by proposing a skill composition framework based on Behavior Trees (BTs) to enable rapid, modular, and safe reconfiguration of reconfigurable CPP modules. It formalizes skills as precondition/invariant/postcondition triples with a parametric interface, and embeds these within BTs to create a scalable, distributed control architecture using a snowflake topology and protocol-based coordination. The approach combines backchaining for automatic skill composition, memory-enabled sequences, and distributed execution to maintain consistency and robustness across modular components, demonstrated through an IEC 61499/4DIAC implementation. The work contributes a coherent, modular, and AI-friendly operational layer that integrates with high-level descriptive models and capability frameworks, paving the way for self-reconfigurable CPPMs in industrial environments.
Abstract
While the benefits of reconfigurable manufacturing systems (RMS) are well-known, there are still challenges to their development, including, among others, a modular software architecture that enables rapid reconfiguration without much reprogramming effort. Skill-based engineering improves software modularity and increases the reconfiguration potential of RMS. Nevertheless, a skills' composition framework with a focus on frequent and rapid software changes is still missing. The Behavior trees (BTs) framework is a novel approach, which enables intuitive design of modular hierarchical control structures. BTs have been mostly explored from the AI and robotics perspectives, and little work has been done in investigating their potential for composing skills in the manufacturing domain. This paper proposes a framework for skills' composition and execution in skill-based reconfigurable cyber-physical production modules (RCPPMs). It is based on distributed BTs and provides good integration between low-level devices' specific code and AI-based task-oriented frameworks. We have implemented the provided models for the IEC 61499-based distributed automation controllers to show the instantiation of the proposed framework with the specific industrial technology and enable its evaluation by the automation community.