A Cognitive Tutoring Agent with Automatic Reasoning Capabilities

2004

1993

We have defined an object-oriented software architecture for Intelligent Tutoring Systems (ITSs) 2 to facilitate the rapid development, testing, and fielding of ITSs. This software architecture partitions the functionality of the ITS into a collection of software components with well-defined interfaces and execution concept. The architecture was designed to isolate advanced technology components, partition domain dependencies, take advantage of the increased availability of commercial software packages, and reduce the risks involved in acquiring ITSs. A key component of the architecture, the Executive, is a publish and subscribe message handling component that coordinates all communication between ITS components. We implemented critical components of the architecture as a simple hypermedia training system, the Macintosh Maintenance Training System (MMTS). The domain for the prototype training system is the maintenance of Apple Macintosh Ilex computers. This project has shown that the use of a modular software architecture for the development of ITSs, and complex integrated artificial intelligence applications in general, has several important benefits. Its use allows for rapid development, ' incremental integration and testing of components, and a more maintainable, extensible, and reusable end-product. Even more evident was the benefit of an Executive component that facilitated the integration of commercial software packages with custom developed software in a well-defined manner.

2003

In this paper we present some characteristics of a new computational model to represent knowledge within intelligent tutoring systems. This model is inspired (1) by research in artificial intelligence on modelling, structuring and organising knowledge and (2) by theories of cognitive psychology which explain the human cognitive activity in terms of memory subsystems and their processes. Here, we describe one originality of our novel approach : the parsimonious use of cognitive structures suggested by psychology to encode the knowledge to be taught. Primitive units of semantic and procedural knowledge, chosen with a small level of granularity, are used to build complex knowledge entities which are dynamically combined in order to represent the learner cognitive activity. Traces of this activity are used as episodic knowledge which is specific to each learner. Episodic knowledge analysis allows to retrieve semantic and procedural knowledge and to establish their acquisition level in function of their context of usage.

4th ESA Workshop on Artificial Intelligence and Knowledge Based Systems for Space, 17-19 May, 1993, ESA/ESTEC, Noordwijk., 1993

This paper reports the preliminary results of the work carried out within a project of development open intelligent training system for astronaut training. The project objective is to cope with both subsystem and procedural training of astronauts who have to operate a scientific payload. The technical base for the project inherited from a previous spirit project (ITSIEp2615) in terms of methodology and general generic software development tools is summarised the demonstration domain, the training method scenarios, and the pedagogical goals and strategies identified for the target training system are then described.

1999

Since the beginning of research in artificial intelligence several attempts have been made to construct intelligent tutorial systems (ITS). Such an ITS consists in general of a representation of the knowledge in a special domain, a diagnostic procedure to determine the knowledge of a student working with the system, teaching material, and a procedure for adaptive teaching. This chapter demonstrates how an extension of the theory of knowledge spaces can be used for the design of a domain-independent ITS. The main components of this ITS are a representation of the skills necessary in the knowledge domain and their dependencies as a surmise system, a set of questions related through a skill assignment to the skill states used for knowledge diagnosis, and a rule that relates skill states to teaching operations. The ITS is adaptive with respect to the consideration of the prior knowledge a student possess and with respect to the learning speed of a student. The strict formalized description of the systems components and their interactions during the teaching process guarantees that an ITS with the described properties can be implemented easily.

Springer eBooks, 2004

The combination Computer Based Training systems with Artificial Intelligence and Cognitive Science has led to the development of Intelligent Tutoring Systems nearly 30 years ago. A common agreement has been reached about the constituents of an Intelligent Tutoring System (ITS). Nonetheless, the interpretation of the role of each component in the ITS is still heterogeneous. Together with the absence of formal methods in ITS, this leads to the situation, that the components of ITSs are strongly domain dependent and not reusable. The situation is analyzed for case-based ITS, i.e. ITS based on a narrative story line. A formal model of the tutoring process is introduced into the ITS architecture. The model is based on the idea to support the training of two cognitive processes, i.e. the process of diagnostic reasoning, and the process of general knowledge application. The integration of the tutoring process model as the central component in the ITS has led to a homogenization of the architecture. Based on the new architecture, the ITS Docs 'n Drugs has been realized.

1986

PUB DATE Sep 86 NOTE 58p.; For a related report, see IR 013 515. PUB TYPE Information Analyses (070) --Viewpoints (120) EDRS PRICE MF01/PC03 Plus Postage.

2006

The present article proposes a methodology for the construction of intelligent tutoring systems that can be applied to any case that implies the design of a system intended for training advanced engineering students in the operation and maintenance of mechanisms. The article offers premises for the design of the modules of knowledge domain, student and tutor, and describes control strategies implemented as metarules .

2000

This chapter describes three modeling techniques that have recently started to attract the attention of researchers and developers in the domain of intelligent tutoring systems (ITSs). These techniques are: hierarchical modeling, interoperable and reusable software components, and ontologies. All three of them have been used in developing a model of ITSs called GET-BITS (GEneric Tools for Building ITSs). The GET-BITS model has been used throughout the chapter in order to illustrate the techniques. The major goal of the chapter is to show how these three techniques can be used to make the internal organization of ITSs more natural, more flexible, and more robust, to enhance their design, and to improve their performance. Important modules of any intelligent tutoring system, like domain knowledge, pedagogical knowledge, student model, and explanation strategies, are discussed extensively in the context of the three modeling techniques and the GET-BITS model. Experience with using GET-BITS as the basis for building practical applications shows how the processes of computer-based tutoring and learning based on the GET-BITS model are much closer to human-based instruction. From the design perspective, major advantages of using hierarchical modeling, software components, and ontologies in developing practical ITSs include enhanced modularity, easy extensions, and important steps towards knowledge sharing and reuse.

1996

Despite the progress made in the field of intelligent tutoring systems (ITS), it is still a major challenge to build systems that can teach about complex, ill-structured domains. A chief reason is that detailed, dynamic modeling of students' knowledge is intractable in such areas, and complete, correct models of expert knowledge are inherently difficult to build. These difficulties have led some to argue that the goal of intelligent tutoring should be abandoned and that more benefit could be provided by systems without tutoring. We believe that there are many areas in which tutorial intervention is essential, particularly for the communication of expertise.