Reactive synthesis for relay-explorer consensus with intermittent communication

Abstract

Listen

Translate article

A distributed multi-agent system architecture is explored to reach approximate consensus with intermittent communication. The multi-agent system is cast as a relay-explorer problem, where a relay agent intermittently provides navigational feedback to multiple explorer agents that do not have on-board absolute navigational sensors in a pre-defined sub-region. Within each sub-region, there is one relay agent responsible for servicing the corresponding explorer agents, and the estimated trajectory of an explorer agent can cross the boundary and enter another sub-region. We develop a reactive synthesis approach to formulate the mission specifications, while the state–space system dynamics provide real-time information for state corrections. Specifically, we pre-synthesize a set of planning strategies corresponding to candidate instantiations (i.e., pre-specified representative information scenarios) to dynamically switch among the explorers, and the planning strategies enable transfer of the servicing responsibility between relay agents. To guarantee stability of the switching strategies and the approximate consensus of the explorer agents, we develop maximum dwell-time conditions using a Lyapunov-based analysis to allow the explorer agents to drift for a pre-defined period without requiring servicing from the relay agents. Finally, we include a simulation study to demonstrate the performance of the developed method.