Ricardo Imbert

Intelligent virtual environments for training: an agent-based approach

In this paper we propose an architecture for the development of Intelligent Virtual Environments for Training, which is based on a collection of cooperative software agents. The first level of the architecture is an extension of the classical Intelligent Tutoring System architecture that adds to the expert, student, tutoring and communication modules a new module which is called World Module. Several software agents compose each module. Moreover, the proposed architecture includes agents able to simulate the behavior of human students and tutors, as well as agents able to plan the procedures to be taught (given an initial state and a desired final state) prior to the tutoring process.

When emotion does not mean loss of control

The traditional consideration that intelligent behaviors can only be produced from pure reasoning fails when trying to explain most of human behaviors, in which the emotional component has a decisive weight. However, although many different efforts have been made to consider emotions in the rational process, emotion is still perceived by many research areas as a non-desirable quality for a computational system. This is not the case of the field of believable agents, where emotions are well respected, although they are sometimes associated to a certain loss of control.This paper presents the mechanisms proposed by a generic cognitive architecture for agents with emotionally influenced behaviors, called COGNITIVA, to maintain behaviors control without giving up the richness provided by emotions. This architecture, together with a progressive specification process for its application, have been used successfully to model 3D intelligent virtual agents.

An emotional architecture for virtual characters

This paper presents the mechanisms proposed by a generic cognitive architecture for virtual characters with emotional influenced behaviors, called cognitiva, to maintain behavior control at will without giving up the richness provided by emotions. This architecture, together with a progressive specification process for its application, have been used successfully to model 3D intelligent virtual actors for virtual storytelling.

An Approach to Determine Software Requirement Construction Sequences Based on Use Cases

The majority of software development projects utilize the use cases technique to define software requirements, which are necessary to determine not only the scope of the software itself, but also the sequence in which this software will be constructed. Currently, there are several proposals to define the construction sequence of software requirements, but most of these proposals lack of ease of use from the developerpsilas perspective. This paper presents an approach to determine software construction sequences based on use cases precedence diagrams, which offers some advantages from the developerpsilas point of view. In order to demonstrate the technique, we also present a controlled experiment performed by people who had at least two years of experience in software projects. The results of this experiment show that our proposed technique, unlike other ad hoc techniques used, enables a more precise definition of the construction sequence.

A SOFTWARE ARCHITECTURE FOR INTELLIGENT VIRTUAL ENVIRONMENTS APPLIED TO EDUCATION

This paper describes the software architecture that has been designed as a model for the application of Intelligent Virtual Environments to training activities. CORBA has been used as the middleware to integrate a graphical and interactive environment developed in OpenGL and Visual C++, with a cooperative multi-agent system developed on top of the JADE platform.

A Multiagent Extension for Virtual Reality Based Intelligent Tutoring Systems

Applying virtual reality (VR) in combination with intelligent tutoring systems (ITSs) is a promising approach to computer based learning and training. However, the classical structure of ITSs has not been conceived to deal with the new sources of information and interaction provided by VR environments. The resulting structures combining both technologies often renounce to the traditional modular separation of ITSs in pursuit of increasing efficiency, but making very difficult the reusing of their components. In this paper it is described the extension of the classical ITS structure proposed in the MAEVIF model to build reusable and adaptable VR based ITSs.

Searching Pancho's Soul: An Intelligent Virtual Agent for Human Teams

Intelligent virtual agents have characteristics that allow increasing the computers ability to engage and motivate students along their learning or training process. We are considered incorporate the particular behaviors of team roles defined by Belbin into the simulated agent Ltcalled PanchoGt that will join the human group with the intention of improving the team performance. It this paper we identify relations between the team roles defined by Belbin and the personality traits based into OCEAN model, as well as relations between each one of class of tasks proposed by McGrath and the first. Finally, we describe the cognitive architecture for emotional agents that will use for Panchos architecture.

Pedagogical Virtual Agents to Support Training of Human Groups

From the last decade, intelligent virtual environments (IVEs) have become a quite popular tool for applying computer science to education. The intelligence of the systems generated using IVEs usually falls on the denominated pedagogical virtual agent. Pedagogical virtual agents have characteristics that allow to increase the computers ability to engage and motivate students along their learning process. In this paper, a human groups (teams) training strategy is presented, supporting one of its stages by the use of a pedagogical virtual agent playing the role of team leader

A cognitive social agent architecture for cooperation in social simulations

We present a cognitive agent architecture to allow its agents to exhibit social behaviors influenced both by rational and cognitive motivators. Currently, our focus is on cooperation and our objective is the observation or emergence of non-scripted behavior in social cooperative environments. We present the results of applying our architecture in the design of virtual agents in which they spontaneously cooperate to achieve their individual and social goals.

Effort Estimation in Incremental Software Development Projects Using Function Points

Nowadays, software development methodologies, such as Rational Unified Process or agile methodologies, recommend developing software by increments instead of following a waterfall lifecycle model. Although Function Points is one of the most known techniques to estimate effort and cost in software projects, there is little work that indicates how to adapt it in non-waterfall lifecycles, such as incremental ones.