Learning from a plan-based interface

2006

Abstract: Recent standardization in learning technology has resulted in a model of activity-based learning designs called IMS LD that provides a common framework for expressing any kind of activity-based learning program. This emphasis on designing learning programs based on assembling activities and resources in turn allows the application of Artificial Intelligence (AI) techniques to help in the process of design.

International Joint Conference on Artificial Intelligence, 2011

This paper presents a plan recognition algorithm for inferring student behavior using virtual science laboratories. The algorithm extends existing plan recognition technology and was integrated with an existing educational application for chemistry. Automatic recognition of students' activities in virtual laboratories can provide important information to teachers as well as serve as the basis for intelligent tutoring. Student use of virtual laboratories presents several challenges: Students may repeat activities indefinitely, interleave between activities, and engage in exploratory behavior using trial-anderror. The plan recognition algorithm uses a recursive grammar that heuristically generates plans on the fly, taking into account chemical reactions and effects to determine students' intended high-level actions. The algorithm was evaluated empirically on data obtained from college students using virtual laboratory software for teaching chemistry. Results show that the algorithm was able to (1) infer the plans used by students to construct their models; (2) recognize such key processes as titration and dilution when they occurred in students' work; (3) identify partial solutions; (4) isolate sequences of actions that were part of a single error.

CISM International Centre for Mechanical Sciences, 1999

Human-computer collaboration provides a practical and useful application for plan recognition techniques. We describe a plan recognition algorithm which is tractable by virtue of exploiting properties of the collaborative setting, namely: the focus of attention, the use of partially elaborated hierarchical plans, and the possibility of asking for clarification. We demonstrate how the addition of our plan recognition algorithm to an implemented collaborative system reduces the amount of communication required from the user.

Journal of Experimental and Theoretical Artificial Intelligence, 1995

1987

This paper adresses the problem of building user mod& within the framework of Computer Assisted Instruction (ICAI), and more particularly for systems teaching elementary arithmetic or algebra. By "model building" we mean the

Anais do Simpósio …, 2007

Many computer tools have been developed to be used in learning activities. However, the effective use of these resources depends on the teachers' decisions, therefore, it is necessary to assist teachers in the planning of learning activities. This paper presents PACO -a framework for Planning learning Activities supported by COmputers. The essence of PACO is that the design of activities and the choice of computer tools should be addressed by Pedagogical aspects and characteristics of the target-students. Workshop em Informática na Educação (sbie) 2007 529 XVIII Simpósio Brasileiro de Informática na Educação -SBIE -Mackenzie -2007

Proceedings of the Fifteenth …, 1999

We present a new abductive, probabilistic theory of plan recognition. This model differs from previous theories in being centered around a model of plan execution: most previous methods have been based on plans as formal objects or on rules describing the recognition process. We show that our new model accounts for phenomena omitted from most previous plan recognition theories: notably the cumulative effect of a sequence of observations of partially-ordered, interleaved plans and the effect of context on plan adoption. The model also supports inferences about the evolution of plan execution in situations where another agent intervenes in plan execution. This facility provides support for using plan recognition to build systems that will intelligently assist a user.

We will present the adaptive model of the ExploraGraph© Interface and explain how the interface can serve as a mean of communication between learners and an intelligent support system. The goal of the ExploraGraph© research project was to build an environment where both user models, task model and pedagogical model could meet in a productive way. The idea was to offer each user an interface where intentions could be externalized. In it, concepts, activities and course objectives are organized in order to foster understanding, but also to project the user's model, as in "overlay" systems but in a more expressive way. The system makes the meta-dimensions of the process naturally explicit and functional, bringing the user to learn their use and thus proceed to a higher and reflexive process level. Finally our hypothesis was that if users manipulated the interface at the level of goals and concepts, it would be easier to follow and guide them 1 . The ExploraGraph© system was developed as an adaptive support environment. In the ExploraGraph© Editor, graphs of elements are dynamically and intelligently arranged depending on semantic relations between them. They proved to be very useful in helping course designers conceptualize and produce organized and understandable learning interfaces. For learners, the ExploraGraph© Navigator -and its highly organized, informative and responsive GUI -offers a tool consistent with ergonomic criteria of flexibility, organization, gradual visibility and internal coherence. An additional navigation tool empowers each user to specify intentions and access shortcuts to actions. When the user manipulates the interface at the level of intentions, the system is informed and can then support the user with contingent delegated actions, feedback or support using MS Agent avatars and multimodal demonstrations. This support model is stored in the database along with the course, as a rule-based system. Replication is used to synchronize the content of the course, the learner models and the group model.

Intelligent Virtual Agents, 2003

In this paper, we describe how we have integrated Steve, an intelligent tutor based on Soar, and HeSPI, a human simulation tool for planning and simulating maintenance tasks in nuclear power plants. The objectives of this integration were to test Steve's flexibility to be used in different applications and environments and to extend HeSPI to use it as a virtual environment for training. We discuss the problems encountered and the solutions we have designed to solve them.

2014

The Last Planner® System (LPS) allows teams and individuals to learn and improve their use of language to plan and coordinate production every day on their construction project. This paper will investigates how LPS, when consistently applied, reinforces W. Edwards Deming’s Plan-Do-Study-Act. LPS also promotes and requires effective use of key elements of reliable promising and “grammar of action” as put forth by Fernando Flores. These two theories will be explained along with others throughout this paper as a framework and management system for project teams operating in a production setting. The second half of the paper discusses how technology has been leveraged to achieve high-functioning LPS performance. A cloud-based Last Planner software application exists that helps project teams create learning through the ability to establish reliable promises. By applying Deming's PDSA method for continuous improvement, this collaborative software creates real-time feedback and learnin...