Towards an Intention Abstraction Layer for Autonomous Industrial Systems
Artan Markaj, Raphael H\"ofer, Felix Gehlhoff
Why It Matters
What makes this one worth your time
This work addresses a critical gap in ensuring that autonomous systems align with human intentions, potentially reducing operational failures in complex industrial environments.
A middleware that enhances intention clarity and conflict resolution in autonomous systems.
Summary
The paper proposes the Intention Abstraction Layer (IAL), a middleware that transforms high-level human intentions into structured, explainable runtime objects, enabling pre-execution conflict detection among autonomous industrial systems.
Key contributions
- Introduction of the Intention Abstraction Layer (IAL) as a middleware solution.
- Development of a mechanism for parsing natural language goals into structured intentions.
- Implementation of a consistency monitor that detects conflicts before execution.
Notable insights
- The use of a large language model grounded in a formal OWL ontology for parsing natural language goals is a novel approach to intention representation.
- The integration of a consistency monitor for pre-execution conflict detection is a significant advancement in behavioral assurance.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2607.14553v1 Announce Type: new 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.