Dynamic cooperative learning control of output‐feedback systems with output constraints

Abstract This paper investigates the dynamic cooperative learning control for high‐order output‐feedback systems under output constraints. To avoid complex computation, we use a system transformation strategy in design. Only one neural network (NN) is employed to approximate unknown synthetic function each agent. Subsequently, NN‐based mechanism designed by introducing barrier Lyapunov (BLF). The proposed expands NN approximation domain of transformed systems, and all subsystems remains constrained. Further, NNs on identified uncertain dynamics are used construct experience‐based controllers carry out same tasks. Finally, theoretical authenticity demonstrated numerical example.