Exploiting the Superposition Property of Wireless Communication for Max-Consensus Problems in Multi-Agent Systems

Abstract

This paper presents a consensus protocol that achieves max-consensus in multi-agent systems over wireless channels. Interference, a feature of the wireless channel, is exploited: each agent receives a superposition of broadcast data, rather than individual values. With this information, the system endowed with the proposed consensus protocol reaches max-consensus in a finite number of steps. A comparison with traditional approaches shows that the proposed consensus protocol achieves a faster convergence.

arXiv commentSubmitted for IFAC Workshop on Distributed Estimation and Control in Networked Systems