As human machine teaming becomes central to paradigms like Industry 5.0, a critical need arises for machines to safely and effectively interpret complex human behaviors. A research gap currently exists between techno centric robotic frameworks, which often lack nuanced models of human behavior, and descriptive behavioral ontologies, which are not designed for real time, collaborative interpretation. This paper addresses this gap by presenting OntoPret, an ontology for the interpretation of human behavior. Grounded in cognitive science and a modular engineering methodology, OntoPret provides a formal, machine processable framework for classifying behaviors, including task deviations and deceptive actions. We demonstrate its adaptability across two distinct use cases manufacturing and gameplay and establish the semantic foundations necessary for advanced reasoning about human intentions.

翻译：随着人机协作成为工业5.0等范式的核心，机器需要安全有效地解释复杂的人类行为，这一需求变得至关重要。目前，技术中心的机器人框架（通常缺乏细致的人类行为模型）与描述性行为本体论（并非为实时协作解释而设计）之间存在研究空白。本文通过提出OntoPret（一种用于解释人类行为的本体论）来填补这一空白。OntoPret基于认知科学和模块化工程方法，提供了一个形式化的、机器可处理的框架，用于对行为进行分类，包括任务偏差和欺骗性行为。我们通过两个不同的应用场景（制造和游戏）展示了其适应性，并建立了对高级人类意图推理所必需的语义基础。