This paper proposes an Intention Abstraction Layer (IAL) for autonomous industrial systems that treats high-level intentions as persistent, explainable runtime objects. An LLM grounded in a formal OWL ontology converts natural-language goals into structured intentions. A consistency monitor checks conflicts when intentions are registered, before execution, while a transparency module explains detected conflicts in natural language. In a proof of concept, two autonomous agents register conflicting production and energy intentions, and the IAL identifies and explains the conflict before it reaches the execution layer. The work targets coordination across schedulers, energy managers, and vehicle fleets.
No heat snapshots are available in the last 24 hours.