Visualizing Agent Communications Graphical Interfaces for Conversation Paradigms
Abstract
This research puts forth a graphical user interface for interacting with and modifying conversations used by software agents in a Multi Agent System (MAS) architecture (CASA). MAS Communications is a field of Artificial Intelligence focusing on improving the way agents communicate. Thus message exchanges are made meaningful by implementing concepts surrounding context. Additionally, they should be flexible in order to avoid problems due to unpredictability. Lastly, these paradigms should be simple to ease their adoption.
Using this interface one can visualize how different conversations progress and why they do so allowing for the identification of error sources in the system. The user can also modify existing conversation types, create new ones, and instantiate implementations of them for individual agents.
The conversation types are typically distinguished by what is called the performative of the communicative act. This is a concept adopted from linguistics where the performative indicates a conversation's intent/desires.
Description
Keywords
Artificial Intelligence, Computer Science, Robotics
Citation
Aurini, T. (2015). Visualizing Agent Communications Graphical Interfaces for Conversation Paradigms (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca. doi:10.11575/PRISM/28654