Wireless Robotic Communication for Collaborative Multi-Agent Systems

Abstract

Collaborative robots as a multi-agent system to complete a common mission without public reference but operate individual decision and learning mechanism represent a wide range of applications in artificial intelligence. With an illustrative example, reinforcement learning with localization and planning capabilities is developed to represent each robot's operation. It is shown that wireless robotic communication can significantly enhance overall performance of collaborative MAS in the distributed operating manner. After identify useful information (i.e. reward map and private reference) to exchange, according to properties of content, p-persistent real-time ALOHA is suggested to serve as the multiple access protocol of the ad-hoc style networking toward ultra-reliability and ultra-low latency, resulting in satisfactory overall performance close to ideal communication. Wireless robotic communication therefore reveals new technological opportunities for robotics, multi-agent systems, artificial intelligence, and communications.