Continual Learning-based Optimal Output Tracking of Nonlinear Discrete-time Systems with Constraints: Application to Safe Cargo Transfer

This paper addresses a novel lifelong learning (LL)-based optimal output tracking control of uncertain non-linear affine discrete-time systems (DT) with state constraints. First, to deal with optimal tracking and reduce the steady state error, a novel augmented system, including tracking error and its integral value and desired trajectory, is proposed. To guarantee safety, an asymmetric barrier function (BF) is incorporated into the utility function to keep the tracking error in a safe region. Then, an adaptive neural network (NN) observer is employed to estimate the state vector and the control input matrix of the uncertain nonlinear system. Next, an NN-based actor-critic framework is utilized to estimate the optimal control input and the value function by using the estimated state vector and control coefficient matrix. To achieve LL for a multitask environment in order to avoid the catastrophic forgetting issue, the exponential weight velocity attenuation (EWVA) scheme is integrated into the critic update law. Finally, the proposed tracker is applied to a safe cargo/ crew transfer from a large cargo ship to a lighter surface effect ship (SES) in severe sea conditions.