DMCA
Towards Active Perception in Situated Multi-agent Systems
| Venue: | Best of EUMAS’03, Special Issue of Journal on Applied Artificial Intelligence |
| Citations: | 28 - 18 self |
BibTeX
@ARTICLE{Weyns_towardsactive,
author = {Danny Weyns and Elke Steegmans and Tom Holvoet},
title = {Towards Active Perception in Situated Multi-agent Systems},
journal = {Best of EUMAS’03, Special Issue of Journal on Applied Artificial Intelligence},
year = {},
pages = {2004}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Modeling the environment and agent-environment relationships is not well explored in multi-agent systems, in particular not for software multi-agent systems. This paper aims to contribute with a generic model for active perception in situated multi-agent systems. Active perception enables an agent to direct its perception at the most relevant aspects in the environment, according to its current task. The model decomposes perception into three functionalities: sensing, interpreting, and filtering. The agent first senses its neighborhood through a set of selected foci, resulting in a representation. A set of perceptual laws enforces domain specific constraints on sensing. Next, the agent interprets the representation by means of descriptions, resulting in a percept. Percepts are expressions that can be understood by the internal machinery of the agent. Finally, the percept is filtered by a set of selected filters, restricting the perceived data according to specific context relevant selection criteria. Most researchers in the multi-agent community agree that the environment is an essential part of any multi-agent system (MAS), yet most of them neglect to integrate the environment as a primary abstraction in MASs. In fact most of the proposed models or tools for MASs reduce the concept of environment to a message delivering system or broker infrastructure; see e.g., Bellifemine
Keyphrases
situated multi-agent system towards active perception multi-agent system active perception generic model essential part specific constraint multi-agent community selected filter relevant aspect current task internal machinery primary abstraction agent-environment relationship specific context relevant selection criterion software multi-agent system broker infrastructure perceptual law enforces
