Collective stabilisation of multi-agent dynamical systems with single agent control

This paper studies the stability and performance of a multi-agent system composed of identical linear time-invariant dynamic agents, when only a single agent in the system is controlled by an exogenous single-input-single-output controller. It is shown that a wide class of multi-agent systems can be collectively stabilised by controlling any single agent. The tracking performance of such a closed-loop system, however, has a fundamental limitation. It is also shown that generically not only the output of controlled agent but either the sum or average of all agent outputs can be used for an exogenous controller. An example is presented to illustrate theoretical results developed in this study.