Paper:
Emergence and Effectiveness of Communication Interface in a System of Distributed Intelligent Agents
Arvin Agah* and George A. Bekey**
*Bio-Robotics Division, Mechanical Engineering Laboratory, AIST- Ministry of International Trade and Industry, 1-2 Namiki, Tsukuba 305, Japan
**Institute for Robotics and Intelligent Systems, Computer Science Department University of Southern California, Los Angeles, CA 90089, U.S.A.
The emergence and effectiveness of communication interface in a colony of autonomous agents is discussed in this paper. The robotic agents sense the world within which they are embedded, while performing specific tasks in the world. Some of the tasks require the simultaneous cooperation of two robotic agents. These agents are able to sense other agents and communicate via simple, task-related messages. Using genetic algorithms, a colony of agents is evolved, producing agents with improved performance. It is shown that the tendency of the robotics agents to communicate increases through evolution, as the colony cooperates more, in order to perform more tasks. The concepts developed through computer simulation are tested for feasibility in a team of four small mobile-manipulator robots, each controlled autonomously via an on-board micro-processor.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.