Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Conclusions and Future Work
References
All Topics
Computer Science
Machine Learning

Learning domain knowledge for teaching procedural skills

Profile image of Lewis JohnsonLewis Johnson

2002, Proceedings of the first international joint conference on Autonomous agents and multiagent systems part 3 - AAMAS '02

https://doi.org/10.1145/545056.545134
visibility

…

description

7 pages

link

1 file

Abstract

This paper describes a method for acquiring procedural knowledge for use by pedagogical agents in interactive simulation-based learning environments. Such agents need to be able to adapt their behavior to the changing conditions of the simulated world, and respond appropriately in mixed-initiative interactions with learners. This requires a good understanding of the goals and causal dependencies in the procedures being taught. Our method, inspired by human tutorial dialog, combines direct specification, demonstration, and experimentation. The human instructor demonstrates the skill being taught, while the agent observes the effects of the procedure on the simulated world. The agent then autonomously experiments with the procedure, making modifications to it, in order to understand the role of each step in the procedure. At various points the instructor can provide clarifications, and modify the developing procedural description as needed. This method is realized in a system called Diligent, which acquires procedural knowledge for the STEVE animated pedagogical agent.

Related papers

An Intelligent Tutoring Architecture for Simulation-Based Training
Ashish Karnavat

aaai.org, 2008

Truly generic and reusable intelligent tutoring software architectures have remained elusive. As part of our effort to develop tutoring systems for simulations of ill-defined domains, a software framework has emerged with minimal dependencies on any domain-specific details, except for the data used to instantiate the framework for a particular application. Here, we describe this framework, its functionality, underlying representations, configurability, and use of natural language generation.

View PDFchevron_right
Animated Pedagogical Agent in a Learning Environment
Luciane Fraga, Leandro Dihl

Artificial Intelligence is an important area in the field of Computing applied to Education in terms of technological implementation. This paper describes IVTE, Intelligent Virtual Teaching Environment, implemented by Multi-Agents technology including pedagogical features, represented by Guilly. Guilly is a Animated Pedagogical Agent that acts based on a student model and teaching strategies.

View PDFchevron_right
Animated Pedagoggical Agent in a Learning Environment
Luciane Fraga, Leandro Dihl

SECIII-Open IFIP-GI- …, 2002

Artificial Intelligence is an important area in the field of Computing applied to Education in terms of technological implementation. This paper describes IVTE, Intelligent Virtual Teaching Environment, implemented by Multi-Agents technology including pedagogical features, represented by Guilly. Guilly is a Animated Pedagogical Agent that acts based on a student model and teaching strategies.

View PDFchevron_right
An intelligent tutoring framework for simulation-based training
Milton Rosenberg

Proceedings of the 16th …, 2008

Truly generic, reusable intelligent tutoring software frameworks remain elusive. As part of our effort to develop ITSs for simulations, a software framework with minimal dependencies on domain specifics has emerged. Herein, we describe this framework, its functionality, components, configurability, and use of natural language generation.

View PDFchevron_right
Integrating Pedagogical Agents into Virtual Environments
Allen Munro

Presence: Teleoperators and Virtual Environments, 1998

In order for a virtual environment to be effective as a training tool, it is not enough to concentrate on the fidelity of the renderings and the accuracy of the simulated behaviors. The environment should help trainees develop an understanding of the task being trained, and should provide guidance and assistance as needed. This paper describes a system for developing virtual environments in which pedagogical capabilities are incorporated into autonomous agents that interact with trainees. These pedagogical agents can monitor trainees' progress and provide guidance and assistance. The agents interact with simulations of objects in the environment, and with trainees. The paper describes the architectural features of the environment and of the agents that permit the agents to meet instructional objectives within the virtual environment. It also discusses how agent-based instruction is combined with other methods of delivering instruction.

View PDFchevron_right
Using a model of collaborative dialogue to teach procedural tasks
Charles Rich

2001

Previous research on building intelligent tutoring systems has not leveraged general models of collaborative discourse, even though tutoring is an inherently collaborative and often discourse-based activity. Similarly, previous research on collaborative discourse theory has rarely addressed tutorial issues, even though teaching and learning are crucial components of collaboration. We help bridge the gap between these two related research threads by presenting a tutorial agent, called Paco, that we built using an application-independent collaboration manager, called Collagen. Our primary contribution is to show how a variety of tutorial behaviors can be expressed as rules for generating candidate discourse acts in the framework of collaborative discourse theory.

View PDFchevron_right
Mixed initiative problem solving with animated pedagogical agents
James Lester

1997

Abstract Knowledge-based learning environments provide an ideal testbed for developing and evaluating computational models of mixed initiative interaction. In each problem-solving episode, learners incrementally develop solutions for problems posed by the environment. To maximize learning effectiveness and learning efficiency, we have been developing animated pedagogical agents that dynamically provide explanatory advice in response to changing problem-solving contexts in learning environments.

View PDFchevron_right
Teaching Animated Agents in Virtual Worlds
Lewis Johnson

2000

This paper describes the potential for instructing animated agents through collaborative dialog in a simulated environment. The abilities to share activity with a human instructor and employ both verbal and nonverbal modes of communication allow the agent to be taught in a manner natural for the instructor. A system that uses such shared activity and instruction to acquire the knowledge needed by an agent is described. This system is implemented in STEVE, an embodied agent that teaches physical tasks to human students.

View PDFchevron_right
Task-oriented tutorial dialogue: Issues and agents
Charles Rich

2000

Towards our goal of developing computer tutors that can collaborate with students on tasks in simulated environments, we have built a series of four prototype tutors. These tutors integrate two independent but related strands of research: intelligent tutoring systems and task-oriented dialogue systems. While the tutors share a core approach to teactfing procedural tasks, each was designed to explore a different set of issues. This paper outlines the issues that arise in taskoriented tutorial dialogue and the ways they have been addressed in these four tutors.

View PDFchevron_right
OLYMPUS: AN INTELLIGENT INTERACTIVE LEARNING PLATFORM FOR PROCEDURAL TASKS
Luis Matey

Providing Interactive Systems with educational capabilities is essential in order to achieve real effectiveness in simulation based trainings. However, the development cost of adding intelligence to those systems is huge. In this paper we present OLYMPUS, a generic learning platform that allows integrating Interactive Systems with an Intelligent Learning System. The platform is able to diagnose students activity while they solve procedural tasks, it assist them with feedback and helps instructors to follow students’ progress with a monitoring tool. Besides, OLYMPUS provides the instructional designers with authoring tools to help them during the knowledge acquisition process

View PDFchevron_right

References (35)

  1. REFERENCES
  2. R. Angros, Jr. Learning What to Instruct: Acquiring Knowledge from Demonstrations and Focussed Experimentation. PhD thesis, Department of Computer Science, University of Southern California, Los Angeles, CA, 2000.
  3. S. Benson. Inductive learning of reactive action models. Machine Learning: Proceedings of the 12th International Conference, pages 47-54, 1995.
  4. R. Bindiganavale, W. Schuler, J. M. Allbeck, N. I. Badler, A. K. Joshi, and M. Palmer. Dynamically altering agent behaviors using natural language instructions. In Proceedings of the Fourth International Conference on Autonomous Agents, pages 293-300, New York, 2000. ACM Press.
  5. A. Cypher, editor. Watch What I Do: Programming by Demonstration. MIT Press, Cambridge, MA, 1993.
  6. J. Delin, A. Hartley, C. Paris, D. Scott, and K. Vander Linden. Expressing procedural relationships in multilingual instructions. In Proceedings of the Seventh International Workshop on Natural Language Generation, pages 61-70, Kennebunkpurt, Maine, 1994.
  7. Y. Gil. Acquiring Domain Knowledge for Planning by Experimentation. PhD thesis, Carnegie Mellon University, 1992.
  8. T. R. Gruber. Automated knowledge acquisition for strategic knowledge. Machine Learning, 4:293-336, 1989.
  9. S. B. Huffman and J. E. Laird. Flexibly instructable agents. Journal of Artificial Intelligence Research, 3:271-324, 1995.
  10. W. L. Johnson, J. Rickel, R. Stiles, and A. Munro. Integrating pedagogical agents into virtual environments. Presence: Teleoperators and Virtual Environments, 7(6):523-546, December 1998.
  11. B. J. Krawchuk and I. H. Witten. On asking the right questions. In 5th International Machine Learning Conference, pages 15-21. Morgan Kaufmann, 1988.
  12. C. Mellish and R. Evans. Natural language generation from plans. Computational Linguistics, 15(4):233-249, 1989.
  13. T. M. Mitchell. Generalization as search. Artificial Intelligence, 18:203-226, 1982.
  14. T. M. Mitchell, S. Mahadevan, and L. I. Steinberg. LEAP: A learning apprentice for VLSI design. In Machine Learning An Artificial Intelligence Approach, volume III, pages 271-289. Morgan Kaufmann, San Mateo, CA, 1990.
  15. T. M. Mitchell, P. E. Utgoff, and R. Banerji. Learning by experimentation: Acquiring and refining problem-solving heuristics. In R. Michalski, J. Carbonell, and T. Mitchell, editors, Machine Learning An Artificial Intelligence Approach, volume I. Morgan Kaufmann, San Mateo, CA, 1983.
  16. A. Munro, M. Johnson, Q. Pizzini, D. Surmon, and D. Towne. Authoring simulation-centered tutors with RIDES. International Journal of Artificial Intelligence in Education, 8:284-316, 1997.
  17. M. Nicolescu and M. Mataric. Experience-based representation construction: learning from human and robot teachers. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2001.
  18. T. Oates and P. R. Cohen. Searching for planning operators with context-dependent and probabilistic effects. In Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAI-96), pages 863-868, Menlo Park, CA, 1996. AAAI Press/MIT Press.
  19. D. Pearson and J. Laird. Toward incremental knowledge correction for agents in complex environments. In S. Muggleton, D. Michie, and K. Furukawa, editors, Machine Intelligence, volume 15. Oxford University Press, 1995.
  20. B. W. Porter and D. F. Kibler. Experimental goal regression: A method for learning problem-solving heuristics. Machine Learning, 1:249-286, 1986.
  21. M. A. Redmond. Learning by observing and understanding expert problem solving. PhD thesis, Georgia Institute of Technology, 1992.
  22. J. Rickel and W. L. Johnson. Animated agents for procedural training in virtual reality: Perception, cognition, and motor control. Applied Artificial Intelligence, 13:343-382, 1999.
  23. J. Rickel and W. L. Johnson. Task-oriented collaboration with embodied agents in virtual worlds. In J. Cassell, J. Sullivan, S. Prevost, and E. Churchill, editors, Embodied Conversational Agents. MIT Press, Cambridge, MA, 2000.
  24. S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach. Prentice Hall, Englewood Cliffs, NJ, 1995.
  25. C. Sammut and R. B. Banerji. Learning concepts by asking questions. In R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, editors, Machine Learning: An Artificial Intelligence Approach, volume II, pages 167-191. Morgan Kaufmann, Los Altos, CA, 1986.
  26. A. M. Segre. A learning apprentice system for mechanical assembly. In IEEE Third Conference on Artificial Intelligence Applications, pages 112-117, 1987.
  27. E. Shaw, W. L. Johnson, and R. Ganeshan. Pedagogical agents on the web. In Proceedings of the Third International Conference on Autonomous Agents, pages 283-290, New York, 1999. ACM Press.
  28. W.-M. Shen. Discovery as autonomous learning from the environment. Machine Learning, 11(4):250-265, 1993.
  29. B. D. Smith and P. S. Rosenbloom. Incremental non-backtracking focusing: A polynomial bounded generalization algorithm for version spaces. In Proceedings of the Eighth National Conference on Artificial Intelligence (AAAI-90), pages 848-853, Menlo Park, 1990. AAAI Press.
  30. D. C. Smith, A. Cypher, and J. Spohrer. KIDSIM: Programming agents without a programming language. CACM, 94(7):55-67, 1994.
  31. R. Stiles, L. McCarthy, and M. Pontecorvo. Training studio interaction. In Workshop on Simulation and Interaction in Virtual Environments (SIVE-95), pages 178-183, Iowa City, IW, July 1995. ACM Press.
  32. G. Tecuci and M. R. Hieb. Teaching intelligent agents: the Disciple approach. International Journal of Human-Computer Interaction, 8(3):259-285, 1996.
  33. X. Wang. Learning Planning Operators by Observation and Practice. PhD thesis, Carnegie Mellon University, 1996.
  34. X. Wang. A multistrategy learning system for planning operator acquisition. In The Third International Workshop on Multistrategy Learning, Harpers Ferry, West Virginia, May 1996.
  35. R. M. Young. Generating Descriptions of Complex Activities. PhD thesis, University of Pittsburgh, 1997.

Related papers

An Authoring System for Intelligent Procedural-Skill Tutors
Tom Galvin

IEEE Expert / IEEE Intelligent Systems, 1998

US Naval Postgraduate School sequence of actions to achieve some desired result, and "learning by doing" in computer simulations is often the best way for students to learn and practice these skills. Technical organizations, such as the US Navy, demand that students learn a wide range of reactive and technical procedures. Learning these skills becomes especially challenging when choosing between many actions with context-dependent effects. A simulation can easily back up or redo actions, patiently test students on numerous subtly different problems, and teach skills otherwise quite expensive or dangerous to learn. However, successful "learning by doing" tutoring requires intelligence; it requires flexible knowledge representation and AI planning methods to analyze student plans, find alternatives, and explain the correct actions. When building our authoring systemcomposed of Metutor and Mebuilder-we emphasized space efficiency, simulation credibility, intelligent and automated task planning, and ease of exercise construction and modification. Our system provides teachers with an easy-to-use general-purpose tool for authoring software for intelligent tutoring, and it lets them particularize their application with narrowly focused knowledge.

View PDFchevron_right
Agents that Learn to Instruct
Lewis Johnson

1997

This paper describes a software agent that learns procedural knowledge from a human instructor well enough to teach human students. In order to teach, the agent needs more than the ability to perform a procedure. It must also be able to monitor human students performing the procedure and be able to articulate the reasons why actions are necessary. Our research concentrates on helping an instructor instruct the agent in a natural manner, on reducing the burden on the instructor, and on focusing learning on the procedure being taught. Initially the agent has little domain knowledge. The instructor demonstrates a procedure by directly manipulating a simulated environment. However, one demonstration is not sufficient for understanding the causal relationships between a demonstration's actions. Unfortunately, the more demonstrations a procedure requires, the greater the instructor's burden. However, fewer demonstrations can be required if the agent autonomously experiments. Our experiments attempt to understand the causal dependencies between a demonstration's actions by perturbing the order of the demonstration's actions.

View PDFchevron_right
An Intelligent Tutoring System for Procedural Training with Natural Language Interaction
Jaime Ramírez

2019

In this paper we present a proposal of an Intelligent Tutoring Systems equipped with dialogue in natural language to facilitate student interaction with the learning environment, provide hints and answer students’ questions. This system is designed to be integrated with a 2D/3D virtual environment for procedural training, where it can maintain a dialogue with students adapted to the context. Our notion of context comprises: the specific features of the student; his/her progress in the development of the task; and the virtual environment where it is performed. The dialogue will be controlled by a dialogue manager, built on Watson Assistant, which has been chosen for its versatility. Additionally, we present an application example that describes the operation of the modules that constitute the proposed approach. Then, we provide some indications on how it will be evaluated with students shortly.

View PDFchevron_right
Mixed-Initiative Interaction between Pedagogical Agents and Students in Virtual Environments
Lewis Johnson

1997

Virtual reality can broaden the types of interaction between students and computer tutors. As in conventional simulation-based training, the computer can watch students practice tasks, responding to questions and offering advice. However, immersive virtual environments also allow the computer tutor to physically inhabit the virtual world with the student. Such a "pedagogical agent" can physically collaborate with the student on tasks and employ the sorts of nonverbal communication used by human tutors. This paper describes Steve, a pedagogical agent for virtual environments that helps students learn procedural tasks. Steve inhabits the virtual world with students, and he collaborates with them on tasks by gracefully shifting between demonstrating the task and providing assistance while the student performs the task. The paper also describes the subtle ways in which such a pedagogical agent can interact with students through nonverbal communication to achieve more human-like collaboration.

View PDFchevron_right
A system for interactive learning in dialogue with a tutor
Danijel Markovic

2011

In this paper we present representations and mechanisms that facilitate continuous learning of visual concepts in dialogue with a tutor and show the implemented robot system. We present how beliefs about the world are created by processing visual and linguistic information and show how they are used for planning system behaviour with the aim at satisfying its internal drive -to extend its knowledge. The system facilitates different kinds of learning initiated by the human tutor or by the system itself. We demonstrate these principles in the case of learning about object colours and basic shapes.

View PDFchevron_right

Related topics

  • Machine Learning
  • Procedural Knowledge

    • Cited by

    Generating Tutoring Feedback in an Intelligent Training System on a Robotic Simulator
    Khaled Belghith

    Lecture Notes in Computer Science, 2006

    Manipulating the Space Station Remote Manipulator (SSRMS), known as "Canadarm II", on the International Space Station (ISS) is a very challenging task. The astronaut does not have a direct view of the scene of operation and must rely on cameras mounted on the manipulator and at strategic places of the environment where it operates. In this paper, we present Roman Tutor, an intelligent robotic simulator we are developing to address this kind of problem. We also show how a new approach for robot path planning called FADPRM could be used to provide amazingly useful tutoring feedback for training on such a manipulator and under this big constraint of restricted sight.

    View PDFchevron_right
    Unveiling the implicit knowledge, one scenario at a time
    V. Gouranton

    The Visual Computer

    When defining virtual reality applications with complex procedures, such as medical operations or mechanical assembly or maintenance procedures, the complexity and the variability of the procedures make the definition of the scenario difficult and time-consuming. Indeed, the variability complicates the definition of the scenario by the experts, and its combinatorics demand a comprehension effort for the developer, which is often out of reach. Additionally, the experts have a hard time explaining the procedures with a sufficient level of details, as they usually forget to mention some actions that are, in fact, important for the application. To ease the creation of scenario, we propose a complete methodology, based on (1) an iterative process composed of: (2) the recording of actions in virtual reality to create sequences of actions and (3) the use of mathematical tools that can generate a complete scenario from a few of those sequences, with (4) graphical visualization of the scenarios and complexity indicators. This process helps the expert to determine the sequences that must be recorded to obtain a scenario with the required variability.

    View PDFchevron_right
    580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved