Toma de Decisiones Afectivas para Agentes Robóticos Sociales.

• Autores: Si Liu
• Directores de la Tesis: David Ríos Insua (dir. tes.)
• Lectura: En la Universidad Autónoma de Madrid ( España ) en 2020
• Idioma: español
• Tribunal Calificador de la Tesis: Alfonso Mateos Caballero (presid.) , José Vila (secret.) , Manuel González Bedia (voc.)
• Texto completo no disponible (Saber más ...)
• Resumen

  • With the proliferation of information and communication technologies, agents that perform intelligent tasks interacting with humans in a seamless manner are becoming a reality. Especially with recent developments in Artificial Intelligence, social robots at home and the workplace are no longer being treated as lifeless and emotionless, leading to proposals which aim at incorporating affective elements within agents. Advances in areas such as affective decision-making and affective computing drive this interest as affective elements have been shown to have impact on how individuals and groups make decisions.

    Our motivation in this thesis is to use affection as a basic element within a decision-making process to facilitate robotic agents providing more seemingly human responses. We first use earlier research in cognitive science and psychology to provide a model for an autonomous agent that makes decisions partly influenced by affective factors when interacting with humans and other agents. The factors included are emotions, mood, personality traits and activation sets in relation with impulsive behavior. We describe several simulations with this model to study and compare its performance when facing various types of users. Through them, we essentially showcase that our model allows for a powerful agent design mechanism regulating its behavior and provides greater decision making adaptivity when compared to emotionless agents and simpler emotional models.

    When it comes to the constitution of communities of robotic agents that interact among them and with one or more users, such agents might evolve from a cooperative to a competitive attitude, and vice versa, in contexts in which interactions among agents repeat over time. We then provide a framework to model transitions between competition and cooperation in such scenario. Competition is dealt with through the paradigm of adversarial risk analysis, which provides a disagreement solution; implicitly, we minimize the distance to such solution. Cooperation is handled through a concept of maximal separation from the disagreement solution. Mixtures of both problems are used to refer to in-between behavior.

    These transitions among agents’ relationship are not only depending on environmental factors and other contextual circumstances, but also on affective factors. We also consider how emotions and mood impact the degree of competitiveness and cooperativeness in groups. We provide a parametric model to regulate its evolution and introduce a negotiation scheme to facilitate group formation, depending on such affective elements. We simulate a virtual platform for the proposed model and conduct experiments showing that our proposal is effective: agents which cooperate affectively with others through negotiation tend to attain higher utilities and outperform non-cooperative and/or emotionless agents.

    Finally, we present a specification for the design of the models underlying affective decision making capabilities in a low cost robot with potential applications in education. We detail the belief and preference models and how these are impacted by affective elements and provide a global algorithm underlying the operation of the robot.