Russell Beale and Andrew Wood. Agent-based interaction. In Proceedings of HCI'94, August 1994. to appear.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....network bandwidth) that are available to the di erent MathWeb agents. A net of MathWeb agents would o er the means for new research projects, such as distributed proof planning. Last but not least, agent oriented programming has shown to be a perfect paradigm for human computer interaction (HCI) BW94] Since agent communication languages like KQML are based on models of human communication a human user can simply be modeled as another agent in the multi agent system. This ultimate goal is very ambitious and beyond the scope of a single PhD thesis. In the following, we therefore restrict the ....

Russell Beale and Andrew Wood. Agent-based interaction. In Proceedings of HCI'94, August 1994. to appear.

.... autonomy is then defined to apply to only one of these concepts and a generalized model of agent autonomy that facilitates measurement and dynamic adjustment is developed. Autonomy is often interpreted as freedom from human intervention, oversight, or control [3; 5; 8; 9; 18] Beale and Wood [3] explain this property in the following way: autonomous agents are agents that are able to work on behalf of their user without the need for any interaction or input from the user. They act without your presence, tirelessly performing tasks. This type of definition corresponds well to the ....

Beale, R. and Wood, A. Agent-based Interaction. In Proceedings of People and Computers IX: Proceedings of HCI'94 (Glasgow, UK, 1994), 239-245.

....and describes the operation of the multi agent system through a particular scenario along with simulation performance. Finally, Section 9 presents some conclusions. 3 2. Autonomy The general concept of autonomy is often interpreted as freedom from human intervention, oversight, or control [8, 10, 18, 19, 30, 45]. This type of definition corresponds well to the concept of autonomy in domains that involve single agent to human user interaction. However, in multi agent systems, a human user may be far removed from the operations of any particular agent. Some researchers have defined autonomy in a more ....

....is, autonomous agents act with the purpose of achieving their goals. This is fortunate because it allows external agents (or human users) to influence autonomous agents to perform useful functions. In addition, many researchers consider pro activeness to be a defining property of autonomous agents [8, 18, 21, 30]. This property requires aspects of periodic action, spontaneous execution, and initiative, in that the agent must be able to take preemptive or independent actions that will eventually. achieve its goal [21] Autonomous agents must consider their goals, make decisions about how to achieve ....

[Article contains additional citation context not shown here]

R. Beale and A. Wood, "Agent-based Interaction," in Proc. People and Computers IX: Proceedings of HCI'94, Glasgow, UK, 1994, pp. 239-245.

....allocated to an agent. Then the agent plans to accomplish the task autonomously (or it may cooperate with the other agents) and carries out the plan. Our thesis is irrelevant to such a study. The reason why we must avoid the discussions held in the context of software engineering such as Refs. [9, 10, 22, 26, 33, 47] is that programming metaphor itself is the subject of the discussion there. We must analyze mobile language systems not in the level of metaphor, but in the level of its presupposed language mechanism. Then, what about concurrent process calculi We think that it is one of the appropriate ....

Russell Beale and Andrew Wood. Agent-Based Interaction. In People and Computers IX: Proceedings of HCI'94, pages 239--245, 1994.

....An effort has been made in (Jennings, Wooldridge 1994) to study the hallmarks of agent hood. The hallmarks have been put down namely as autonomy, social ability, responsiveness and proactiveness. The agents available are numerous and differ substantially in their functionality and performance. In (Beale et al. 1994), an effort to classify the various types of available agents has been made. The various types of agents have been classified as user agents, agent guides, autonomous agents, symbiotic and cooperative agents, anthropomorphic agents, agents for multi agent systems, and agents for agent oriented ....

Beale, R. and Wood, A. (1994) Agent Based Interaction.In People and Computers IX: Proceedings of HCI'94, Glasgow, UK, August 1994 239-245.

....of intelligent agents, based on the field of Artificial Intelligence, to be the computer generated characters in such a game. The term agent has been widely and inconsistently used in recent times. At the most simple level, an agent is something that perceives and acts [1, p. 7] Beale and Wood [2] provide one classification of various notions of agents: user agents, agent guides, autonomous agents, symbiotic and co operative agents, and anthropomorphic agents. This last grouping, anthropomorphic agents or agents that imitate humans, are the type of intelligent software agents required for ....

. Russell Beale and Andrew Wood: "Agent-based interaction," People and Computers IX: Proceedings of Human-Computer Interaction, pp. 239--245, Glasgow, UK, 1994.

....Fischer, 1993 This chapter reviews a lot of the work on software agents, from early implementations and basic techniques, to state of the art technology and opinions on how research and development should proceed. Much of the early part of this review has been adapted from an earlier report [Wood 94] There has been a lot of speculative work about agents. Often visualised as software robots , agents will work for you and with you in the virtual world. They will be used for many things from simple mediation of your interaction with a particular application by providing a more intuitive ....

....for the agents and responded enthusiastically to the concept . Guiding Agents It has also been suggested that by reversing this technique we could provide software agents with a good way of demonstrating the techniques that they use Diagram 4. 4 to provide help or explanations to human agents [Wood 94, Beale 94] Agents that undertake these sorts of tasks I will term guiding agents. Here the agent acts like a tutor or mentor, providing advice and training (diagram 4.4) Microsoft and Wordperfect both have what they call Wizards and Coaches respectively that act as tutors when using the system ....

[Article contains additional citation context not shown here]

<F1.136e+04> Andrew Wood. Agent-Based Interaction. PhD Progress Report PR-94-4, University of Birmingham, School of Computer Science, May 1994.<F1.081e+04>

....have a much better mechanism for understanding the operation of a light switch based on its physical construction. But he argues that viewing more complex agents in this way can be beneficial. One aspect of an software agent definition that is brought out in the paper by Russell Beale and myself [Beale 94] that none of the other definitions seem to cover is that of communication. An agent needs ways of interacting with its environment and other agents, including sensors and effectors to observe and manipulate its world, plus ways of talking (although not necessarily in natural language) with ....

....agents and responded enthusiastically to the concept . Guiding Agents It has also been suggested that by reversing this technique we could provide software agents with a good way of demonstrating the techniques that they use Diagram 4. 4 to provide help or explanations to human agents [Wood 94, Beale 94] Agents that undertake these sorts of tasks I will term guiding agents. Here the agent acts like a tutor or mentor, providing advice and training (diagram 4.4) Microsoft and Wordperfect both have what they call Wizards and Coaches respectively that act as tutors when using the system [Microsoft ....

[Article contains additional citation context not shown here]

<F1.136e+04> Russell Beale and Andrew Wood. Agent-Based Interaction. In<F1.158e+04> People and Computers IX: Proceedings of<F1.136e+04> HCI`94, pages 239-245. British Computer Society HCI Group, Cambridge University Press, August 1994.<F1.081e+04>

....with the application) ffl interaction (the working in the application) ffl task fulfillment (how to reach a certain goal or task) ffl user support and guidance. Since each of these domains complexity grows with the complexity of the system, they should all be supervised by a single agent [2]. In this paper we focus on the last domain: the adaptive user support and guidance in complex graphical user interfaces. 3 Virtual Environments We are going to address such questions as ffl How far should VE development go One restriction of a VE system is, that it makes no sense to only ....

Russell Beale and Andrew Wood. Agent-based interaction. In People and Computers IX: Proceedings of HCI'94, pages 239--245. British Computer Society HCI Group, Cambridge University Press, August 1994.

....and actions. This is the classical problem of symbol grounding [Harnad, 1990] It has found explicit treatment especially in human robot interaction [Klingspor et al. 1996] and distributed AI 3 One might even say that an agent worthy task should require an agent to adapt itself to it. [Beale and Wood, 1994]. Kaiser et al. 1996b] but it is inherent in any learning task that requires the agent to relate its own behaviour to a user defined concept, just as usefulness or interestingness. To solve this task, supervised inductive techniques are mostly being used, ranging from ILP [Klingspor et al. ....

Beale, R. and Wood, A. (1994). Agent-based interaction. In Proceedings of the HCI 94, Glasgow, UK.

.... system [Fischer, 1993a] Data Mining Data mining, discovering useful trends or information from large quantities of data, has a place for agents (data miners ) They can autonomously, or semi autonomously explore the data with the user, bringing interesting relationships to the users attention [Beale, 1994, Kl sgen, 1992] Agent Oriented There appears to be various definitions of agent oriented programming Programming (AOP) but it is basically an extension of object oriented programming. In the most basic definition an agent is not much more than an autonomous object, allowing easy creation of ....

....Histories: Help Form the Research Agenda , as well as being a delegate at the conference proper. I recently gave a short talk on some of the issues of Agent Based Interaction to the Cognitive Science M.Sc. students. I have also co authored a paper entitled Agent Based Interaction with Russell Beale [Beale, 1994] which is due to appear at the BCS HCI 94 Conference in Glasgow. I am hoping to attend this as a student volunteer. Agents 17 9. Conclusions Timetable Conclusion My research so far has identified several potentially interesting thesis topics: 6 the evaluation of a task s suitability for an ....

<F1.136e+04> R. Beale & A. Wood, 'Agent-Based Interaction', to appear in:<F1.158e+04> Proceedings of<F1.136e+04> HCI'94, August 1994<F1.093e+04>

No context found.

Beale, Russell, and Andrew Wood. "Agent-Based Interaction." In People and Computers IX: Proceedings of HCI `94 . Cambridge University Press. August 1994: 239-245.

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