Stochastic Deep Model Reference Adaptive Control
This work addresses control challenges in nonlinear systems for robotics or automation, but it is incremental as it builds on prior deep model reference adaptive control methods.
The paper tackles the problem of controlling nonlinear systems with uncertainties by extending a deep model reference adaptive controller to use Bayesian deep neural networks, resulting in guaranteed tracking performance and boundedness with a real-time feedback controller.
In this paper, we present a Stochastic Deep Neural Network-based Model Reference Adaptive Control. Building on our work "Deep Model Reference Adaptive Control", we extend the controller capability by using Bayesian deep neural networks (DNN) to represent uncertainties and model non-linearities. Stochastic Deep Model Reference Adaptive Control uses a Lyapunov-based method to adapt the output-layer weights of the DNN model in real-time, while a data-driven supervised learning algorithm is used to update the inner-layers parameters. This asynchronous network update ensures boundedness and guaranteed tracking performance with a learning-based real-time feedback controller. A Bayesian approach to DNN learning helped avoid over-fitting the data and provide confidence intervals over the predictions. The controller's stochastic nature also ensured "Induced Persistency of excitation," leading to convergence of the overall system signal.