Distributed control of multi-consensus

Abstract

We consider the problem of steering a multi-agent system to multi-consensus, namely a regime where groups of agents agree on a given value which may be different from group to group. We first address the problem by using distributed proportional controllers that implement additional links in the network modeling the communication protocol among agents and introduce a procedure for the optimal selection of them. Both the cases of single integrators and of second-order dynamics are taken into account and the stability for the multi-consensus state is studied, ultimately providing conditions for the gain of the controllers. We then extend the approach to controllers that either add or remove links in the original structure, by preserving eventually the weak connectedness of the resulting graph.