Salta al contenuto principale
Passa alla visualizzazione normale.

ANTONIO CHELLA

Can agents talk about what they are doing? A proposal with Jason and speech acts

  • Autori: Seidita V.; Lanza F.; Sabella A.M.P.; Chella A.
  • Anno di pubblicazione: 2022
  • Tipologia: Contributo in atti di convegno pubblicato in volume
  • OA Link: http://hdl.handle.net/10447/578752

Abstract

The dream of building robots and artificial agents that are more and more capable of thinking and acting like humans is growing by the day. Various models and architectures aim to mimic human behavior. In our current research, we propose a solution to make actions and thought cycles of agents explainable by introducing inner speech into a multi-agent system. The reasons that led us to use inner speech as a self-modeling engine raised the question of what inner speech is and how it affects cognitive systems. In this proposal, we used speech act to enable a coalition of agents to exhibit inner speech capabilities to explain their behavior, but also to guide and reinforce the creation of an inner model triggered by the decision-making process through actions applied to the surrounding world and to themselves. The BDI agent paradigm is used to keep the agents rational and with the innate ability to act in a human-like manner. The proposed solution continues the research path that began with the definition of a cognitive model and architecture for human-robot teaming interaction, and aims to integrate the believable interaction paradigm into it.