Mission impossible? Automatically assembling agents from high-level task descriptions

Jayaputera, Glenn; Loke, Seng W.; Zaslavsky, Arkady

doi:10.1109/iat.2003.1241063

Cited by 4 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper extends the discussion that we have presented earlier in [5], and the rest of this paper is organized as follow. Section 2 elaborates on the concept of the mission.…”

Section: Introductionmentioning

confidence: 86%

“…The notion of composing a number of agents from a high-level task descriptions was first introduced in [6,5]. The need for "on-demand agent generator" was the result of our observation and study of existing multiagent systems, where we believe that they are not easily adapted to different problem domain from the one they were originally developed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Run-time mission evolution in mobile multiagent systems

Jayaputera¹,

Zaslavsky²,

Loke³

Proceedings. IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 2004. (IAT 2004).

Self Cite

View full text Add to dashboard Cite

In this paper, we present our approach to developing a multiagent system based on the proposed complex concept of the mission. The mission is a high-level abstraction that combines the overall goal of a system, the means, and the process of achieving that goal, from which agents can be automatically generated. We propose a mechanism to generate agents on-demand and at run-time rather than at the design stage. Functionalities are given to the agents at run-time also. Programmatically, a mission is a live object where it maintains not only the various revisions of the plan but also the state and data for each revision. By doing so, our system is able to suspend and resume the mission. Furthermore, we envisage that the mission execution history is useful for the planner so that it can learn from it and hence produce a better plan in the future. We discuss the concept of the mission object, our programmatic model as well as our prototype system, which we call eHermes.

show abstract

“…This paper extends the discussion that we have presented earlier in [5], and the rest of this paper is organized as follow. Section 2 elaborates on the concept of the mission.…”

Section: Introductionmentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

Run-time mission evolution in mobile multiagent systems

Jayaputera¹,

Zaslavsky²,

Loke³

Proceedings. IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 2004. (IAT 2004).

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since the TDG is a DAG, then changing its structure will simply be adding and/or removing nodes and links. The discussion about how to change the TDG at runtime can be found in [6].…”

Section: Figure 1: the Sequence Of The Tdg Executionmentioning

confidence: 99%

“…The notion of assembling agents on-demand was first introduced in [6]. The main idea is to create agents only when they are needed.…”

Section: Ehermes: the Multiagent System Shellmentioning

confidence: 99%

“…This modified part is the delta (or the difference) between the old and the new plans. Once received, the MCA will change the internal TDG structure of the mission object as presented in [6]. Furthermore, the MCA will send various commands to the working agents either to ignore some previously assigned tasks (since now they are not par of the new plan) or abort some tasks.…”

Section: Ehermes: the Multiagent System Shellmentioning

confidence: 99%

See 1 more Smart Citation

An Assembly and Execution Shell for MultiAgent Systems

Jayaputera

Zaslavsky

Loke

et al.

Proceedings of the 38th Annual Hawaii International Conference on System Sciences

Self Cite

View full text Add to dashboard Cite

This paper presents a novel approach to design and develop an assembly and execution shell for multiagent applications based on the concept of a mission. A mission is a live evolving object that contains data, current variables, goals and evolution history of the mission itself. By maintaining the states and data inside the mission, it is possible to suspend the multiagent system's mission execution temporarily and resume when permitted. Our design allows run-time and dynamic agent generation depending on the complexity of the mission itself.We discuss the design and internal structure of the mission, the strategy and efficiency of the system in executing the tasks in the mission, and present our prototype system called eHermes.

show abstract