Varying the user interaction within multi-agent systems

Payne, Terry R.; Sycara, Katia; Lewis, Michael

doi:10.1145/336595.337555

Cited by 22 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They introduced so-called liaison agents which support human interaction with other non-human agents by arbitrating between them. Payne et al analyzed human-agent interaction and stated that agents can have different models of user interaction [24]. In their work they describe a case study of a Multi-Agent System containing different agents with similar functional capabilities, but different types of user interaction modalities.…”

Section: Related Workmentioning

confidence: 99%

The formation of virtual organizations by means of electronic institutions in a 3D e-Tourism environment

Gärtner

Seidel

Froschauer

et al. 2010

Information Sciences

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

The formation of virtual organizations by means of electronic institutions in a 3D e-Tourism environment

Gärtner

Seidel

Froschauer

et al. 2010

Information Sciences

View full text Add to dashboard Cite

“…They introduced so-called liaison agents which support human interaction with other non-human agents by arbitrating between them. Payne et al (2000) analyzed human-agent interaction and stated that agents can have different models of user interaction. In their work they describe a case study of a Multi-Agent System containing different agents, with some having functionally similar capabilities, but with different types of user interaction modalities.…”

Section: Multi-agent Systems and 3d Virtual Worldsmentioning

confidence: 99%

Itchy Feet

Seidel¹,

Gärtner²,

Pöttler

et al. 2010

Tourism Informatics

View full text Add to dashboard Cite

In this chapter the authors describe an e-tourism environment that places emphasis on a community driven approach to foster a lively society of travelers. It enables them to exchange travel experiences, recommend tourism destinations or just catch some interesting gossip. Moreover, business transactions such as booking a trip or getting assistance from professional travel agents are a constituent part of this environment. All these interactions happen in an integrated, game-like, 3D virtual world where each tourist is impersonated as an avatar. The authors draw a retrospective on the specification, design and implementation of this e-tourism environment and present the status quo. The authors describe how they applied electronic institutions, a framework developed and employed in the area of multi-agent systems, to the tourism domain. Furthermore, they present their approach to connect a 3D virtual world with electronic institutions. Our goal is to provide a test bed for assessing the acceptance of virtual environments, as a medium to overcome the non-tangible nature of tourism products.

show abstract

“…Simulated helicopters then fly a coordinated mission to evacuate the civilians, relying on various information agents to dynamically obtain information about enemy threats, (re)plan routes to avoid threats and obstacles, etc. The distributed team is composed of diverse agents from four different research groups: A Quickset multimodal command input agent [1], a route planner [15], the Ariadne information agent [12] and eight synthetic helicopter pilots [19].…”

Section: An Example Distributed Teammentioning

confidence: 99%

Monitoring deployed agent teams

Kaminka

Pynadath

Tambe

2001

Proceedings of the Fifth International Conference on Autonomous Agents

View full text Add to dashboard Cite

Recent years are seeing an increasing need for on-line monitoring of deployed distributed teams of cooperating agents, e.g., for visualization, or performance tracking. However, in deployed systems, we often cannot rely on the agents to communicate their state to the monitoring system: (a) we rarely can change the behavior of already-deployed agents to communicate the required information (e.g., in legacy or proprietary systems); (b) different monitoring goals require different information to be communicated (e.g., agents' beliefs vs. plans); and (c) communications may be expensive, unreliable, or insecure. This paper presents a non-intrusive approach based on plan-recognition, in which the monitored agents' state is inferred from observations of their routine actions. In particular, we focus on inference of the team state based on its observed routine communications, exchanged as part of coordinated task execution. The paper includes the following key novel contributions: (i) a linear time probabilistic plan-recognition algorithm, well-suited for processing communications as observations; (ii) an approach to exploiting general knowledge of teamwork to predict agent responses during normal execution, to reduce monitoring uncertainty; and (iii) a monitoring algorithm that trades expressivity for scalability, representing only certain useful monitoring hypotheses, but allowing for any number of agents and their different activities, to be represented in a single coherent entity. Our empirical evaluation illustrates that monitoring based on observed routine communications enables significant monitoring accuracy, while not being intrusive. The results also demonstrate a key lesson: A combination of complementary low-quality techniques is cheaper, and better, than a single, highly-optimized monitoring approach.

show abstract

Varying the user interaction within multi-agent systems

Cited by 22 publications

References 21 publications

The formation of virtual organizations by means of electronic institutions in a 3D e-Tourism environment

The formation of virtual organizations by means of electronic institutions in a 3D e-Tourism environment

Itchy Feet

Monitoring deployed agent teams

Contact Info

Product

Resources

About