Félix Ramos

Development of Computational Models of Emotions for Autonomous Agents: A Review

It has been recognized that human behavior is an observable consequence of the interactions between cognitive and affective functions. This perception has motivated the study of human emotions in disciplines such as psychology and neuroscience and led to the formulation of a number of theories and models that attempt to explain the mechanisms underlying this human process. In the field of artificial intelligence, these theoretical findings have posed a series of challenges in the development of autonomous agents (AAs) capable of exhibiting very believable and human-like behaviors. One of these challenges is the design and implementation of computational models of emotions (CMEs), which are software systems designed to provide AAs with proper mechanisms for the processing of emotional information, elicitation of synthetic emotions, and generation of emotional behaviors. In this paper, we review this type of computational model from the perspective of their development. Particularly, we investigate five design aspects that influence their development process: theoretical foundations, operating cycle, interaction between cognition and emotion, architectural design, and role in cognitive agent architectures. We provide discussions about key issues and challenges in the development of CMEs and suggest research that may lead to more robust and flexible designs for this type of computational model.

Node localization in WSN using trigonometric figures

Wireless Sensor Network for their rapid deployment can be used in habitat monitoring for detecting fire and in disaster for helping rescue teams. Node localization is key factor for some applications. We propose the Triangular Centroid Localization algorithm (TCL). It is based in simple trigonometric figures and it does not require special hardware or synchronization time. In our simulations using the received signal strength indicator; TCL improves the accuracy of Centroid Localization (CL) in 54% and Weighted Centroid Localization (WCL) in 64%; using the link quality indicator it improves to CL in 38% and WCL in 64.98%.

Cognitive computational models of emotions

Emotions are one of the important unconscious mechanisms that influence human behaviors, attentions, and decision making. The emotion process helps to determine how humans perceive their internal status and needs in order to form consciousness of an individual. Emotions have been studied from multidisciplinary perspectives and covered a wide range of empirical and psychological topics, such as understanding the emotional processes, creating cognitive and computational models of emotions, and applications in computational intelligence. This paper presents a comprehensive survey of cognitive and computational models of emotions resulted from multidisciplinary studies. We concentrate on exploring how cognitive models have served as the theoretical basis of the computational models of emotions. A comparative analysis of current approaches is elaborated with discussions of how recent advances in this area may improve the development of a coherent Cognitive Computational Model of Emotions (C2MEs), which leads to the machine simulated emotions for cognitive robots and autonomous agent systems in cognitive informatics and cognitive computing.

A platform to design and run dynamic virtual environments

This paper is devoted to introducing, in a general fashion, a platform that allows users to generate virtual scenes. Such generation involves two phases: 1) description of the attributes, arrangement and intentions of the virtual characters participants throughout a natural language, and 2) a virtual representation of a dynamic scene during which the characters interact with each other in order to fulfill the specification provided by the modeler.

Cognitive Computational Models of Emotions and Affective Behaviors

Emotions are one of the important subconscious mechanisms that influence human behaviors, attentions, and decision making. The emotion process helps to determine how humans perceive their internal status and needs in order to form consciousness of an individual. Emotions have been studied from multidisciplinary perspectives and covered a wide range of empirical and psychological topics, such as understanding the emotional processes, creating cognitive and computational models of emotions, and applications in computational intelligence. This paper presents a comprehensive survey of cognitive and computational models of emotions resulted from multidisciplinary studies. It explores how cognitive models serve as the theoretical basis of computational models of emotions. The mechanisms underlying affective behaviors are examined as important elements in the design of these computational models. A comparative analysis of current approaches is elaborated based on recent advances towards a coherent cognitive computational model of emotions, which leads to the machine simulated emotions for cognitive robots and autonomous agent systems in cognitive informatics and cognitive computing.

An action selection process to simulate the human behavior in virtual humans with real personality

In this paper, we present an action selection mechanism to simulate the human behavior in realistic and believable virtual humans according to their personality and affective state taking into account their beliefs, desires, intentions, and the level of intensity of the events they perceive from their environment.

Computational models of emotions for autonomous agents: major challenges

A great number of computational models of emotions (CMEs) have been developed to be included in, or as part of, cognitive agent architectures. These computational models have been designed to provide autonomous agents with appropriate mechanisms for the processing of emotional stimuli, the elicitation of synthetic emotions, and the generation of emotional responses. The research on CMEs has allowed for improvements in several application domains and contributed to progress in areas such as human-computer interaction and artificial intelligence. Nevertheless, despite the wide variety of CMEs proposed in the literature and their success in multiple areas, the complexity and quality of current and future human-centered applications require the development of more flexible and robust CMEs. In this sense, CMEs have yet to face a series of challenges in order to meet such types of requirements. In this paper, we explore key aspects of the development and applications of CMEs for autonomous agents, discuss four major challenges facing their development process, and present a novel approach to deal with these challenges.

GeDA-3D Agent Architecture

This paper presents an agent-architecture useful to generate suitable behaviors to virtual creatures participating in virtual environments created by a declarative description. This architecture is used in a platform to design and run dynamic virtual environments that allows users to generate virtual scenes involving two phases: 1) description of the attributes and intentions of the characters participants throughout a declarative description, and 2) graphical simulation of a dynamic scene during which the characters interact with each other in order to achieve individual and/or collective goals

Using a Declarative Language to Describe the Interactions in Virtual Scenes

A generic platform useful to design and run virtual scenes as a result of a human-like description is introduced. The present article describes the operation of one of the main components of such platform: the virtual-environment (VE) editor. The main goal of the VE editor is to allow a human description of a virtual scene and translate it, if errors-free, into a set of low-level commands. The modeler is provided a declarative language useful to: a) arrange the virtual entities using geometric constraints instead of geometrical data, b) assign personalities to virtual humans, and c) specify goals to be fulfilled by virtual humans. A scene takes place in a specific world. For every different world to model a set of rules must be defined. The VE editor allows the specification of some features related to a particular virtual world, including the following: actions and skills that can be performed, virtual entities acceptable, pre-and post- conditions for interactions, effect of natural laws (gravity, collisions), and a set of rules, which reject or allow the assignment of goals according to the state of virtual humans

Virtual sensors for dynamic virtual environments

This paper proposes a sensor-based mechanism that allows virtual creatures to perceive the environment that surrounds them. We are keen on modeling the behavior of real-life creatures via VR-techniques. Every living creature is endowed by a number of senses, by means of which, the creature is aware of the world around. We picture the environment as a multi-agent system, where every agent has, primarily, a knowledge base, a sensors and effectors to allow interaction. The effectors may launch actions (graphical changes), noises, messages or aromas. The sensors model, particularly, the sight, hearing and smell senses of a living creature. Every sensor has specific perception capabilities and gathers partial or full information about the objects around. Through the sensors, a virtual creature is aware of the environment and capable to increase the knowledge base. The local state of a creature can be amplified by allowing cooperation between agents