Humanoid robots were introduced into the education sector as tools, tutors and companions for students to make learning more effective. This research does reliability and validity test for a proposed questionnaire which looks at various perceptions issues such as how students perceive gender and the role that humanoid robots have. Such a valid and reliable questionnaire could help the research team get the whole picture of students' preference, attitude, and level of interaction with humanoid robots for educational purpose. The research could help to determine what and how these issues will affect the acceptance and integration of humanoid robots into the education system.

This paper presents the conceptual design of a virtual 3D quiz game based on a multi-agent system (MAS) architecture aptly named QuizMASter. The QuizMASter supports formative assessment by providing adaptive testing and feedback using intelligent pedagogical agents within an immersive game-based virtual learning environment. This enables instructors to use assessment as a motivational tool within an entertaining context where students do not feel the usual pressures related to taking tests.

Employing the state-of-the-art artificial intelligence (AI) technology in current e-learning systems can bring personalized, adaptive, and intelligent services to both students and educators. Although we have seen more and more successful applications of AI in e-learning, most of them have not yet been expanded to or adopted in widely used e-learning systems, especially open-source learning management systems (LMS) such as Moodle, Sakai and so on. This observation takes us to the analysis and discussion of the current work in both LMS and applied AI. The findings include that current intelligent LMS systems are still in their early stage, while AI applications need to handle some problems or to be modified before applying them into the LMS systems, and AI technology also needs to be brought to open source communities.

This paper presents an infrastructure for developing problem-based pervasive learning environments. Building such environments necessitates having many autonomous components dealing with various tasks and heterogeneous distributed resources. Our proposed infrastructure is based on a multi-agent system architecture to integrate various components of the environments. The infrastructure includes a location- and context-awareness service, a question and answer service, an adaptive mechanism; problem based ubiquitous learning models, social networking issues, and the evaluation of multimedia inputs. Furthermore, student modeling issues among components are considered. The design of the infrastructure as well as its components is discussed. This paves the way towards the development of pervasive learning applications.

This paper presents an approach to designing and developing knowledge bases in e-Learning systems. We explore the use of Protégé 2000 as a knowledge editor for course material, with the addition of Web Service interfaces on top of it to facilitate retrieval of the content. Protégé 2000 provides an extensible infrastructure and allows the easy construction of domain ontologies, customized data entry forms, and provides an API that can easily be extended by Web Services for the purpose of dynamic course material creation. The use of ontology and Web Services makes the knowledge bases for e-Learning sharable, reusable, and interoperable with other technologies, such as .Net, which have standard Web Service implementations.

In multiple agent computing environments, the communication issue for negotiation, task allocation, etc. is vital for agents to do their tasks. It has been shown that agent systems with many intercommunicating agents can be very difficult to develop without appropriate tools to monitor and mediate communications. Moreover, without agent communication management, the performance of agent systems with large participants may suffer from communication livelocks, deadlock and inconsistency. The objective of this paper is to explore how to improve the multiagent system development process by incorporating a high-level monitoring and control facility into agent communication and distribution environments. A Petri net-based modeling approach is adopted in constructing task-oriented conversation schemata. Conversation managers are deployed into agent daemons throughout the network to provide an environment at network nodes to which agents may be dispatched. An example in an agent-based shop floor is briefly introduced.

This paper presents an agent-based approach to developing intelligent virtual reality-based training systems. The architecture of an intelligent virtual reality-based training system is modeled as five collaborative agents: training task-planning agent, simulation agent, performance evaluation agent, on-line instruction agent, and intelligent interface agent. The behavioral and knowledge models of each agent type and the mechanism of inter-agent interaction and coordination are described. A Petri net-based specification approach that gives the work formalism for effective modeling and implementation is elaborated. Finally, a computerized numeric control (CNC) milling operation virtual training prototype system is introduced to show the effectiveness of this approach.

In the virtual assembly system, components are displayed and manipulated in a 3D environment using virtual reality interface technology. To reflect the real world constraint that more than one object cannot occupy the same space, a real time manipulation of component models in virtual assembly space requires a real time collision detection. In this paper, an efficient collision detection methodology using a collision class classification approach is presented.