Using planning techniques in intelligent tutoring systems

doi:10.1016/S0020-7373(86)80041-4

International Journal of Man-Machine Studies

Volume 24, Issue 1, January 1986, Pages 77-98

https://doi.org/10.1016/S0020-7373(86)80041-4 Get rights and content

Abstract

This paper proposes an architecture for building better Computer-Assisted Instruction (CAI) programs by applying and extending Artificial Intelligence (AI) techniques which were developed for planning and controlling the actions of robots. A detailed example shows how programs built according to this architecture are able to plan global teaching strategies using local information. Since the student's behavior can never be accurately predicted, the pre-planned teaching strategies may be foiled by sudden surprises and obstacles. In such cases, the planning component of the program is dynamically reinvoked to revise the unsuccessful strategy, often by recognizing student misconceptions and planning a means to correct them. This plan-based teaching strategy scheme makes use of global course knowledge in a flexible way that avoids the rigidity of earlier CAI systems. It also allows larger courses to be built than has been possible in most AI-based “intelligent tutoring systems” (ITSs), which seldom address the problem of global teaching strategies.

References (24)

R.E. Fikes et al.
STRIPS: a new approach to the application of theorem proving to problem solving
Artificial Intelligence
(1971)
J.R. Hartley et al.
Towards more intelligent teaching systems
International Journal of Man-Machine Studies
(1973)
G.I. McCalla et al.
Plan creation, plan execution and knowledge acquisition in a dynamic microworld
International Journal of Man-Machine Studies
(1982)
J.A. Self
Student models in computer-aided instruction
International Journal of Man-Machine Studies
(1974)
J.S. Brown et al.
SOPHIE: a sophisticated instructional environment for teaching electronic troubleshooting
J.S. Brown et al.
Aspects of a theory for automated student modelling
R.R. Burton et al.
An investigation of computer coaching for informal learning activities
J.R. Carbonell
AI in CAI: an artificial intelligence approach to computer-assisted instruction
IEEE Transactions on Man-Machine Systems
(1970)
J.A. Chambers et al.
Computer assisted instruction: current trends and critical issues
Communications of the ACM
(1980)
W.J. Clancey
Tutoring rules for guiding a case method dialogue

M.J. Colbourn

Computer-guided diagnosis of learning disabilities: a prototype

R.E. Fires et al.

Learning and executing generalized robot plans

Artificial Intelligence

(1972)

Cited by (82)

Automated instructional design for CSCL: A hierarchical task network planning approach
2014, Expert Systems with Applications
Citation Excerpt :
These results show that our approach enables the generation of UoL for CSCL more quickly than the manual method of ID. Since the first approach for integration of automated planning in ITSs many researches employ different techniques to obtain plans tailored to each student (Peachey and McCalla, 1986). For example, the Generic Tutoring Environment (GTE) developed by Van Marcke (1998) allows to declaratively define the pedagogical model as a set of tasks and methods, and them use it for the planning process.
In Computer Supported Collaborative Learning (CSCL), one of the most important tasks for instructional designers is to define scenarios that foster group learning. Such scenarios, defined as Units of Learning (UoLs), comprise different components and are organized according to pedagogical approaches to orchestrate group learning processes. Examples of UoL components are learning objects, student roles, student characteristics (e.g., background, preferences, learning styles, etc.), instructional/learning goals, and activities, among others. Thus, the instructional design (ID) of a proper UoL for CSCL is a complex task that requires practice and experience. This is particularly true when designing, developing, adapting, and customizing UoLs, taking into consideration different instructional/learning goals and individual preferences of students. This paper therefore proposes using a Hierarchical Task Network (HTN) planning approach to automate and optimize the tasks of designers. To accomplish that, we define an initial CSCL scenario as “an ID task” and “a set of information related to students and the domain to be taught.” Then we propose a model that formally describes ID for CSCL as HTN planning, where the initial CSCL scenario is adapted and refined according to student needs. In this model, the ID strategies are defined as hierarchical tasks and methods into a planning domain definition, and the initial CSCL scenario is defined as a planning problem definition. To validate our approach, we develop a CSCL courseware generator that (i) helps designers to set up an initial CSCL scenario; (ii) automatically generates a personalized UoL based on a given initial scenario; and (iii) supports the adaptation of UoLs.
Pedagogically founded courseware generation based on HTN-planning
2009, Expert Systems with Applications
Citation Excerpt :
In this section, we will discuss the related work, focused on well-known approaches that use (or claim to use) educational knowledge to inform the sequencing and selection of learning objects. The idea to encode pedagogical knowledge encoded in planning operators to determine sequences of instructional acts was introduced by Peachy and McCalla (1986). This general idea was refined in the Generic Tutoring Environment (GTE) (Van Marcke, 1992) and the Dynamic Courseware Generator (DCG) (Vassileva & Deters, 1998).
Course generation enables the automatic assembly of course (ware) adapted to the learner’s competencies and learning goals. It offers a middle-way between traditional pre-authored “one-size fits all” courseware and manual resource look-up. Such an assembly requires pedagogical knowledge, represented, for instance, as expert system rules or planning operators. In this article, we describe the course generation framework Paigos that enables the formalization and application of complex and realistic pedagogical knowledge. Compared to previous course generation approaches, it generates structured courses that are adapted to a variety of learning goals and to the learners’ competencies. We describe basic operators and methods for course generation, which are used to formalize seven different types of courses. Furthermore, we present the results of technical evaluations that investigated the performance of the proposed framework. Among others, the results show that Paigos takes less than a second to generate complex courses with an average learning time of about twelve hours. The results also show that large amounts of educational resources are required for an adaptive pedagogically founded course generation.
Planning and scheduling in an e-learning environment. A constraint-programming-based approach
2008, Engineering Applications of Artificial Intelligence
Citation Excerpt :
The application of AI planning techniques has reported important advances in the generation of automated courses within e-learning. One of the first attempts in this direction was the work in Peachy and McCalla (1986), in which the learning material is structured in learning concepts and prerequisite knowledge is defined, which states the causal relationship between different concepts. This instructional method was one of the first approaches to combine instructional knowledge and artificial intelligence planning techniques to generate sequences of learning materials.
AI planning techniques offer very appealing possibilities for their application to e-learning environments. After all, dealing with course designs, learning routes and tasks keeps a strong resemblance with a planning process and its main components aimed at finding which tasks must be done and when. This paper focuses on planning learning routes under a very expressive constraint programming approach for planning. After presenting the general planning formulation based on constraint programming, we adapt it to an e-learning setting. This requires to model learners profiles, learning concepts, how tasks attain concepts at different competence levels, synchronisation constraints for working-group tasks, capacity resource constraints, multi-criteria optimisation, breaking symmetry problems and designing particular heuristics. Finally, we also present a simple example (modelled by means of an authoring tool that we are currently implementing) which shows the applicability of this model, the use of different optimisation metrics, heuristics and how the resulting learning routes can be easily generated.
An ontology-based planning system for e-course generation
2008, Expert Systems with Applications
Citation Excerpt :
Automatic course generation has been an active research field for more than two decades. One of the first attempts in creating an automatic system, using planning techniques for the synthesis of educational resources is the work by Peachy and Mc-Calla (1986). The learning material is structured in concepts and prerequisite knowledge is defined, which states the causal relationships between different concepts.
Researchers in the area of educational software have always shown great interest in the automatic synthesis of learning curricula. During the recent years, with the extensive use of metadata and the emergence of the Semantic Web, this vision is gradually turning into a reality. A number of systems for curricula synthesis have been proposed. These systems are based on strong relations defined in the metadata of learning objects, which allow them to be combined with other learning objects, in order to form a complete educational program. This article presents PASER, a system for automatically synthesizing curricula using AI Planning and Semantic Web technologies. The use of classical planning techniques allows the system to dynamically construct learning paths even from disjoint learning objects, meeting the learner’s profile, preferences, needs and abilities.
AI for technological innovations and practices in engineering education
2023, AIP Conference Proceedings
The history of artificial intelligence in education-the first quarter century
2023, Handbook of Artificial Intelligence in Education

View all citing articles on Scopus

View full text

Using planning techniques in intelligent tutoring systems

Abstract

Artificial Intelligence

International Journal of Man-Machine Studies

International Journal of Man-Machine Studies

International Journal of Man-Machine Studies

SOPHIE: a sophisticated instructional environment for teaching electronic troubleshooting

Aspects of a theory for automated student modelling

An investigation of computer coaching for informal learning activities

AI in CAI: an artificial intelligence approach to computer-assisted instruction

IEEE Transactions on Man-Machine Systems

Computer assisted instruction: current trends and critical issues

Communications of the ACM

Tutoring rules for guiding a case method dialogue

Computer-guided diagnosis of learning disabilities: a prototype

Learning and executing generalized robot plans

Artificial Intelligence