R. Hill and W .L. Johnson, "Situated Plan Attribution for Intelligent Tutoring," Proceedings of the Twelfth National Conference on Artificial Intelligence, Seattle, Washington, pp. 499--505, July 31--August 4, 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....the technique from Section 3, and aims to resolve ambiguities in real time[28] The architectural implications of agent tracking described in this article are not dependent on RESC. Nonetheless, we There are some recent ITS applications that have ventured into dynamic environments, e.g. REACT[13], but they still primarily rely upon a plan driven tracking strategy, dealing with the dynamic aspects as exceptions. briefly describe RESC in the followingas an example technique for real time ambiguityresolution: RESC s situatedness is based on its ability to continuously track the other ....

R. Hill and W. L. Johnson. Situated plan attribution for intelligent tutoring. In Proceedings of the National Conference on Artificial Intelligence. Menlo Park, Calif.: AAAI press, 1994.

....L s actions. The above agent tracking process is related to previous work on model tracing in intelligent tutoring systems (ITS) for tracking student actions [ Anderson et al. 1990; Ward, 1991 ] However, that work has primarily focused on static environments. A recently developed ITS, REACT [ Hill and Johnson, 1994 ] extends model tracing to a more dynamic environment. REACT relies upon a plan driven tracking strategy, and deals with the more dynamic aspects of the domain as special cases. It specifically abstracts away from tracking students mental states. In contrast, pilots appear to track their op ....

R. Hill and W. L. Johnson. Situated plan attribution for intelligent tutoring. In Proceedings of the National Conference on Artificial Intelligence. Menlo Park, Calif.: AAAI press, 1994.

.... meld products of different areas of research to provide tailored instruction addressing the particular shortcomings of each students performance (and hence knowledge) ITS in the literature regularly affect or are affected by research in areas such as natural language processing [LP96] planning [HJ94], knowledge acquisition [BM96] animated figure presentation [SL96] and simulated agents [EW96] The asynchronous nature of ITS make them often ideal candidates for use over the WWW, since it facilitates offering instruction in the domain to anywhere, to anyone, at any time. However, a number of ....

Hill, Randall W., Jr., and W. Lewis Johnson, "Situated Plan Attribution for Intelligent Tutoring." Paper presented to the 12 th National Conference on Artificial Intelligence, Seattle,August 1994, pp. 499-505.

....the technique from Section 3, and aims to resolve ambiguities in real time[28] The architectural implications of agent tracking described in this article are not dependent on RESC. Nonetheless, we 2 There are some recent ITS applications that have ventured into dynamic environments, e.g. REACT[13], but they still primarily rely upon a plan driven tracking strategy, dealing with the dynamic aspects as exceptions. briefly describe RESC in the followingas an example technique for real time ambiguityresolution: RESC s situatedness is based on its ability to continuously track the other ....

R. Hill and W. L. Johnson. Situated plan attribution for intelligent tutoring. In Proceedings of the National Conference on Artificial Intelligence. Menlo Park, Calif.: AAAI press, 1994.

....L s actions. The above agent tracking process is related to previous work on model tracing in intelligent tutoring systems (ITS) for tracking student actions [ Anderson et al. 1990; Ward, 1991 ] However, that work has primarily focused on static environments. A recently developed ITS, REACT [ Hill and Johnson, 1994 ] extends model tracing to a more dynamic environment. REACT relies upon a plan driven tracking strategy, and deals with the more dynamic aspects of the domain as special cases. It specifically abstracts away from tracking students mental states. In contrast, pilots appear to track their op ....

R. Hill and W. L. Johnson. Situated plan attribution for intelligent tutoring. In Proceedings of the National Conference on Artificial Intelligence. Menlo Park, Calif.: AAAI press, 1994.

....of individual agents in dynamic environments. RESC is a real time, reactive version of the model tracing technique used in intelligent tutoring systems it involves executing a model of the tracked agent, and matching predictions with actual observations(Anderson et al. 1990; Ward 1991; Hill Johnson 1994). Unfortunately, recursive agent group tracking leads to a large growth in the number of models. Executing all of these models would be in general highly problematic. The problem is particularly severe for a pilot agent, given that it has to track opponents maneuvers and counter them in ....

....for real time performance are critical. Previous work on optimizations for agent tracking has mostly focused on intra model (within a single model) optimizations, e.g. heuristic pruning of irrelevant operators(Ward 1991) restricted backtrack search(Tambe Rosenbloom 1995) and abstraction (Hill Johnson 1994). In contrast, this paper proposes inter model (across multiple models) optimizations. It introduces an inter model optimization called model sharing, which involves sharing the effort of tracking multiple models. Shared models are dynamically unshared when required. In essence, a model is ....

Hill, R., and Johnson, W. L. 1994. Situated plan attribution for intelligent tutoring. In Proceedings of the National Conference on Artificial Intelligence. Menlo Park, Calif.: AAAI press.

....interact with each other, either collaboratively or non collaboratively, to achieve their goals. Many of these multi agent domains require the interaction to be dynamic and real time. For instance, in education, intelligent tutoring systems interact with students to provide real time feedback[12, 37]. In entertainment, projects such as interactive fiction[3] virtual immersive environments[21] and virtual theatre[11] all involve real time and dynamic multi agent interaction (collaborative and competitive) Similarly, in training, a recent thrust on dynamic, real time simulations e.g. ....

....and right turns They are together executing a pincer. Indeed, it is only an accurate interpretation of the joint pincer that enables D to effectively counteract it. Recognizing this jointness also enables D to track a subteam s (L and M) behaviors when it is not visible. 1 Previous approaches[1, 26, 37, 12, 35], that focus on tracking individual agents, fail to track such joint team activities. In particular, these approaches are based on model tracing, which involves executing an agent s runnable model, and matching the model s predictions with actual observations. However, an individual s model does ....

R. Hill and W. L. Johnson. Situated plan attribution for intelligent tutoring. In Proceedings of the National Conference on Artificial Intelligence. Menlo Park, Calif.: AAAI press, 1994.

No context found.

R. Hill and W .L. Johnson, "Situated Plan Attribution for Intelligent Tutoring," Proceedings of the Twelfth National Conference on Artificial Intelligence, Seattle, Washington, pp. 499--505, July 31--August 4, 1994.

No context found.

Hill, R. & Johnson, W.L. Situated plan attribution for intelligent tutoring. In Proc. of the Nat. Conf. on AI. Menlo Park, CA: AAAI Press, 1994.

....team training of tank platoons. To evaluate that, we are currently studying the applicability of the method to other domains, including Robocup soccer simulations [6] 16 7 Related Work This work is closely related to intelligent tutoring systems that employ some form of student modeling (e.g. [1, 12, 17, 3]) Student modeling typically assumes some task that needs to be performed and some overall plan(s) of action or method(s) are known to achieve that task. In turn, the plan is used to interpret student actions so as to determine, for example, when a student is making a mistake or is at an impasse. ....

....what goals need to be achieved and what tasks are to be performed. This view gains support from the fact that it is consistent with how the Army lays out its exercise plan as well as how it evaluates the student teams. There are student modeling techniques that lie between these extremes (e.g. [3, 12]) For instance, Situated Plan Attribution [3] is a system for tutoring satellite link operators. Because of the interactive, dynamic nature of the operator s task, Situated Plan Attribution attempts to loosen how actions and their goals are fit into an overall plan. Nevertheless the intent to do ....

[Article contains additional citation context not shown here]

Hill, R. & Johnson, W.L. Situated plan attribution for intelligent tutoring. In Proceedings of the National Conference on Artificial Intelligence. Menlo Park, CA: AAAI Press, 1994.

....is in the process of being adapted to handle air to ground operations; it is expected that these changes will little or no impact on Debrief. Plans are underway to apply Debrief to an entirely different domain, namely automated control of radar tracking stations in the NASA Deep Space Network [8, 7]. 3 An Example The following example scenario illustrates how Debrief is employed. Suppose that the TacAir Soar agent is assigned a Barrier Combat Air Patrol (BARCAP) mission, i.e. to search the skies for enemy aircraft and intercept them so that they cannot threaten a high value unit such as an ....

R.W. Hill and W.L. Johnson. Situated plan attribution for intelligent tutoring. In Proceedings of the National Conference on Artificial Intelligence, Seattle, Washington, 1994. to appear.

....et al. 1990) to interpret student actions tend to intervene whenever the student wanders off of a correct solution path; this intervention policy is potentially 1 Portions of this paper are based on the AAAI 94 paper entitled Situated Plan Attribution for Intelligent Tutoring Systems. (Hill Johnson, 1994) disruptive and does not appear to be based on an analysis of whether it is appropriate to intervene. This paper describes an approach to plan recognitio n called situated plan attribution that takes these factors into account. Situated plan attribution analyzes both the student s actions and ....

Hill, R.W. & Johnson, W.L. (1994). Situated plan attribution for intelligent tutoring systems.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC