Leader-following privacy-preserving consensus control of nonlinear multi-agent systems: a state decomposition approach

This paper focuses on a nonlinear multi-agent system (MAS) in the presence of unknown dynamics and eavesdroppers. An output consensus control strategy is proposed based on an extended state observer, which achieves leader-following privacy-preserving consensus in a backstepping framework. Different from existing distributed average consensus approaches that require each follower to exchange and expose state information to its neighbours, our strategy avoids the requirement for communication during information interaction by decomposing each follower's state information into two sub-states. The status information is leaked, thereby achieving privacy preservation. Furthermore, for this class of MAS with unknown dynamics, we use an extended state observer to estimate the unknown dynamics and design an auxiliary system. The auxiliary variables generated by this auxiliary system combined with the back-stepping method can effectively compensate for dynamics. By combining graph theory knowledge and techniques such as Lyapunov functions, it is proven that the output-consensus tracking error of an MAS is ultimately bounded. Finally, the effectiveness of the control strategy is verified via an example.