One of the constituting characteristics of software agents is their ability to sense the environment. The reception and processing of percepts is a key element for the agent's internal reasoning process and essential for interacting with other entities in the environment. But sensing the environment is often seen as an abstract concept which is practically more or less reduced to the simple processing of some domain-specific message content. In order to be generally applicable among different multi-agent applications a common model of an environment incorporating an extensible set of entities, distribution protocols, and representation- as well as query languages needs to be established. Therefore, we propose a generic, extensible and adaptable model for resource-aware agents. It is organized into different information channels to help directing the focus of interest to specific aspects of the environment. Several discovery- and distribution protocols as well as different representation- and query languages may be used to satisfy the requirements of dynamic environments. The whole model is realized with a dedicated service agent on each platform, which local as well as remote agents can query for environmental information. This way, repeatedly and redundantly integrating these features into every agent application can be avoided and agent developers only have to deal with a simple protocol-API to access the information. Due to our highly flexible and adaptable model, we can face the heterogeneity of multi-agent applications operating in infrastructure- as well as mobile ad-hoc networks.
展开▼
