Event-triggered output-feedback adaptive tracking control of autonomous underwater vehicles using reinforcement learning

Abstract

This paper investigates the event-triggered tracking control of fully actuated autonomous underwater vehicles (AUVs) in the vertical plane. Specifically, this paper studies the ETC in the sensor-to-controller channel, where the X-Z coordinates and the pitch angle are transmitted in an event-triggered manner. The greater communication saving is ensured. Additionally, the recently-raised problem of “jumps of virtual control laws” is solved by establishing an event-triggered adaptive neural observer. This observer can offer the benefit of state recovery, which conforms to the nautical practice. As the observer is co-located with the controller, a succinct triggering condition is devised to avoid the “Zeno” behavior and co-located with the sensors. To achieve the optimization of the long-term tracking performance, the reinforcement learning (RL) technique is performed by using the critic-actor method with the radial basis function (RBF) neural networks (NNs). The critic NN approximates the performance index and is transferred as the reinforcement signal to the actor NN, which accounts for the uncertainties. The closed-loop stability is analyzed based on the observer-based tracking errors, and all of them are proved to be semi-globally uniformly ultimately bounded (SGUUB). Finally, a numerical experiment substantiates the effectiveness of the proposed scheme.