Distributed Containment Maneuvering of Multiple Marine Vessels via Neurodynamics-Based Output Feedback

In this paper, a neurodynamics-based output feedback scheme is proposed for distributed containment maneuvering of marine vessels guided by multiple parameterized paths without using velocity measurements. Each vessel is subject to internal model uncertainties and external disturbances induced by wind, waves, and ocean currents. In order to recover unmeasured velocity information as well as to identify unknown vessel dynamics, an echo state network (ESN) based observer using recorded input-output data is proposed for each vessel. Based on the observed velocity information of neighboring vessels, distributed containment maneuvering laws are developed at the kinematic level. Next, in order to shape the transient motion profile for vessel kinetics to follow, finite-time nonlinear tracking differentiators are employed to generate smooth reference signals as well as to extract the time derivatives of kinematic control laws. Finally, ESN-based dynamic control laws are constructed at the kinetic level. The stability of the closed-loop system is analyzed via input-to-state stability and cascade theory. Simulation results are provided to illustrate the efficacy of the proposed neurodynamics-based output feedback approach.