Towards an Intention Abstraction Layer for Autonomous Industrial Systems

2026-07-16

AI Summary

Industrial autonomous systems often lose semantic fidelity when translating high-level human intentions into low-level control logic, making it difficult to promptly detect goal deviations. To address this issue, this work proposes an Intent Abstraction Layer (IAL) that, for the first time, models intent as a first-class runtime object. By synergizing large language models with OWL ontologies, the IAL parses natural language goals into structured, persistent, and interpretable intent representations. This approach enables pre-execution detection of intent conflicts and provides natural language explanations, shifting behavioral assurance from post-hoc analysis to proactive verification. A prototype system successfully identified and explained multi-agent conflicts between production and energy-consumption objectives, demonstrating the feasibility of intercepting intent inconsistencies before execution.

Abstract

Modern industrial environments increasingly run many autonomous subsystems at once - schedulers, energy managers, vehicle fleets - each pursuing its own goals while sharing the same physical resources. Because high-level human intentions are translated into low-level control logic and then discarded, no running component can tell whether it is still doing what was actually intended, and goal conflicts surface only after they have caused a missed target or a shutdown. We propose the Intention Abstraction Layer (IAL), a domainagnostic middleware that represents intentions as first-class, persistent, and explainable runtime objects: a large language model grounded in a formal OWL ontology parses naturallanguage goals into structured intentions, a consistency monitor detects conflicts at registration time, before execution, and a transparency module explains them in natural language. We report a first proof of concept in which two autonomous agents register conflicting production and energy intentions, and the IAL flags and explains the conflict before it reaches the execution layer. The result is a mechanism that shifts behavioral assurance for cooperating autonomous systems from post-hoc failure analysis to pre-execution, intention-level checking.

Problem

• autonomous industrial systems
• intention representation
• goal conflict
• behavioral assurance
• runtime intention

Innovation

• Intention Abstraction Layer
• autonomous industrial systems
• goal conflict detection
• explainable AI
• OWL ontology