Computers Can Feel Too

The introduction of emotional reactions to e-Learning environments might offer a more efficient and effective communication between the user and the machine; a more natural and realistic computer interface. Embodied Intelligent Emotional Agents (IEAs) which are highly expressive and show empathy for the users may help learners overcome academic difficulties and may contribute positively to the pedagogical procedure by making it more efficient and enjoyable. IEAs can be programmed to “show” the correct social behaviour and through them a channel of communication might open to serve for better interaction among learners. This could contribute to increase student’s self esteem, help them recover from negative emotions as well as encourage learners to overcome academic problems. In this chapter the authors review existing systems that use emotional agents and analyze their specific characteristics, their advantages and disadvantages. Finally, based on this analysis they enumerate specific requirements for efficient communication between agents and users and we use them to propose a general architecture model upon which the development of future IEAs could be based.

Agents with a Theory of Mind in Virtual Training

Virtual training provides an effective means to train complex, dynamic tasks like social interaction, negotiation and crisis management. The virtual characters with whom the trainee interacts are often played by autonomous, intelligent agents. For effective training, it is required that the agents behave in a believable way. In order to display believable social behavior, the agents must be able to take others’ perspectives into account. This can be achieved by equipping them with a theory of mind, that is, the ability to attribute mental states such as beliefs and desires to others. In this chapter the authors describe an executable model for agents with a theory of mind, based on the BDI (belief desire intention) approach. The aim of the model is to develop agents that display believable social behavior and provide explanations about their behavior.

A Comparative Study of Platforms for Multi-User Virtual Environments

Multi-User Virtual Environments (MUVEs) have been found to be engaging and provide an environment in which the elements of discovery, exploration and concept testing, fundamental to the field of science, can be experienced. Furthermore, MUVEs accommodate lifelike experiences with the benefit of the situated and distributed nature of cognition; they also provide virtual worlds to simulate the conditions that are not doable or practicable under real world circumstances making them very relevant to many other fields of study such as history, geography and foreign language learning. However, constructing MUVEs can be expensive and time consuming depending on the platform considered. Therefore, providing the most appropriate platform that requires minimal effort, cost and time will make MUVE deployment in the classroom faster and more viable. In this chapter, the authors provide a comparative study of prominent existing platforms for MUVEs that can be used to identify the right balance of functionality, flexibility, effort and cost for a given educational and technical context. A number of metrics are identified, described and used to enable the comparison. Platform assessment was done in four main metric groups: communication and interaction, characters, features and education. Communication and interaction metrics are used to assess how the communication and interaction is done within the examined platform. Character metrics are employed to measure avatar and agent affordances. Features metrics are defined to compare what the platform offers in terms of technology. Lastly, education metrics are used to identify the value of the associated platform for educational purposes.

Introducing AI and IA into a Non Computer Science Graduate Programme

As part of designing a new Master’s programme entitled Technology, Innovation and Entrepreneurship there was an apparent need to include a unit involving the use of innovative technologies for the development of innovative products and services. The authors aim was therefore to introduce students to Artificial Intelligence and Intelligent Agents using, however, different from “mainstream” practices since the programme is addressed to students from varying, not necessarily Computer Science related, backgrounds. In this work they report their approach and experience from the entire process -from designing the unit, taking into consideration some inherent restrictions such as coordination of teachers and short duration of the course, to delivering it to a diverse audience that requires different didactic methods to be employed. Their primary aim is to disseminate their ideas and report good practice to fellow educators that may face similar situations or wish to employ any of our techniques.

MAgICS

The authors present a preliminary version of the MAgICS (Multi-Agent Introduction to Computer Science) framework, which is a new approach for revitalizing introductory undergraduate or high school computer science curricula through the deep integration of agent-based modeling (ABM) and multi-agent systems (MAS) perspectives. The authors discuss the merits of using multi-agent systems as a lens for conceptual understanding across disciplines, compare multi-agent approaches to traditional serial ones, and explore how this approach can bring together disparate topics in computer science through the common focus on emergent systems to promote a broader view of the field as a whole. To exemplify this approach, they have developed a suite of curricular models for topics spanning from searching and sorting to machine learning and networks and security. By introducing these topics with a focus on parallel, distributed, and stochastic methods, they can make traditionally upper-level topics both motivating and accessible to introductory-level students. The authors review findings from a short implementation of several elements of MAgICS in an introductory computer science classroom with regard to student motivation and evidence of learning of distributed design strategies.

Survey of Educational Multi-User Virtual Environments and Agents

The potential value of Multi-User Virtual Environments (MUVEs) is increasing amongst educationalists. A key issue with MUVE for education is the need to provide system intelligence and believable characters so that the learning goals may be monitored and achieved. Agent-technology offers solutions towards achieving these needs. In this chapter, the authors explore numerous existing educational MUVE and the use of agents for pedagogy in general, as they pave the way forward for delivering intelligent educational MUVE.

Adapting Rewards to Encourage Creativity

Creativity drives innovation and improves the quality of products, problem solving skills, information technology solutions and entrepreneurship. Curriculum standards for CS education typically lack the emphasis and coverage to promote or encourage creative approaches to Software Engineering, focusing on technological solutions rather than innovative design. As a result, creativity is not directly rewarded. This chapter discusses the development of a multi-agent system to apportion rewards for creative contributions to collaborative and group problem solving among students in a software projects course. Encouraging creativity in a classroom team environment, especially for software development, needs a collaboration framework that combines idea management with a motivating reward system. Their multi-agent reward system works directly with the idea capture and visualization portion of SEREBRO, a Web application that combines social networking with software product development tools to foster creativity. The authors discuss the multi-agent reward system and an initial evaluation of its use in a computer science course.

An Intelligent Agents and Multi-Agent Systems Course Involving NetLogo

In the context of an Agent and Multi-Agent Systems course, exposing students to problems and issues related to agent-based programming allows them to understand at a deeper level the otherwise theoretical aspects involved in the design of a multi-agent system (MAS). Indeed, educators have reported a variety of environments and techniques they use in order to increase active learning. The authors argue that NetLogo presents an excellent platform for the task, since it provides, among other interesting features, a small learning curve and an easy to setup visualization environment. This chapter records their experience in teaching a MAS course, using NetLogo as the vehicle for practical coursework. In addition, two extra NetLogo libraries that were provided to students are described, one for BDI-like agents (Belief-Desire-Intention, i.e. goal-oriented agents) and one for ACL-like (Agent Communication Language) communication, which were specifically developed for allowing students to implement more complex agent societies than the original NetLogo platform allowed.

Crafting a Personalised Agent-Oriented Mobile E-Learning Platform for Adaptive Third Level Education

This chapter presents the architecture of an agent-based m-Learning platform, “Personalised Ubiquitous Learning Platform” (PULP), which incorporates adaptive personalisation and collaborative learning for the development of enhanced e-learning. The main objective of this platform is to provide University College Dublin with a single supported intelligent mobile learning environment that will promote adaptive and collaborative learning, human computer interaction on mobile clients anywhere, anytime and also to provide useful recommendation about available educational resources. The system aims to enhance the students’ learning experience in third level educational environment.

Scenario Authoring by Domain Trainers

Authoring is a bottleneck in the widespread uptake of technology for training and education as the time and skill needed for domain experts such as trainers and teachers to develop learning modules is prohibitive. In this project the authors are particularly concerned with providing experiential knowledge transfer, where the trainer is able to create scenarios similar to those they have experienced and allow their trainees to consider appropriate responses to such situations. For this the authors need an environment which is immersive for both parties, in which knowledge is acquired, transferred and gained in the context of the scenario. The scenario itself becomes part of the knowledge to be experienced. To this end they have created a simple approach involving synthetic agents within a Virtual Environment who can be changed along with their dialog and behaviour to create and modify scenarios as deemed appropriate by the domain expert in order to improve the learning experiences of the trainee.