Towards a Definition of Awareness for Embodied AI

TL;DR

I argue that the following aspects are necessary for an aware embodied AI: having access to relevant information, also via memory recall; directing the system’s attention appropriately, filtering out distractions; and being able to integrate information into a coherent model. An aware system should respond based on that model, adapting its internal state or actions in the environment while maintaining coherence in its decisions during the task execution and over time. Finally, its decisions should be explainable and supported by verifiable outputs. Change my mind.

Abstract

This paper explores the concept of awareness in the context of embodied artificial intelligence (AI), aiming to provide a practical definition and understanding of this multifaceted term. Acknowledging the diverse interpretations of awareness in various disciplines, the paper focuses specifically on the application of awareness in embodied AI systems. We introduce six foundational elements as essential building blocks for an aware embodied AI. These elements include access to information, information integration, attention, coherence, explainability, and action. The interconnected and interdependent nature of these building blocks is emphasised, forming a minimal base for constructing AI systems with heightened awareness. The paper aims to spark a dialogue within the research community, inviting diverse perspectives to contribute to the evolving discipline of awareness in embodied AI. The proposed insights provide a starting point for further empirical studies and validations in real-world AI applications.

@inproceedings{10.5220/0012594800003636,
author={Giulio Antonio Abbo and Serena Marchesi and Kinga Ciupinska and Agnieszka Wykowska and Tony Belpaeme},
title={Towards a Definition of Awareness for Embodied AI},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: AWAI},
year={2024},
pages={1399-1404},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012594800003636},
isbn={978-989-758-680-4},
issn={2184-433X},
abstract={This paper explores the concept of awareness in the context of embodied artificial intelligence (AI), aiming to provide a practical definition and understanding of this multifaceted term. Acknowledging the diverse interpretations of awareness in various disciplines, the paper focuses specifically on the application of awareness in embodied AI systems. We introduce six foundational elements as essential building blocks for an aware embodied AI. These elements include access to information, information integration, attention, coherence, explainability, and action. The interconnected and interdependent nature of these building blocks is emphasised, forming a minimal base for constructing AI systems with heightened awareness. The paper aims to spark a dialogue within the research community, inviting diverse perspectives to contribute to the evolving discipline of awareness in embodied AI. The proposed insights provide a starting point for further empirical studies and validations in real-world AI applications.}
}