A Deep Reinforcement Learning-based Sliding Mode Control Design for Partially-known Nonlinear Systems

TL;DR

This paper introduces a novel control method combining data-driven deep reinforcement learning with sliding mode control to effectively manage nonlinear systems with uncertain and partially known dynamics.

Contribution

It proposes a hybrid control approach that integrates model-based sliding mode control with deep reinforcement learning to handle uncertainties in nonlinear systems.

Findings

Effective control of partially known nonlinear systems demonstrated

Deep RL enhances robustness against model uncertainties

Numerical examples validate the proposed method's viability

Abstract

Presence of model uncertainties creates challenges for model-based control design, and complexity of the control design is further exacerbated when coping with nonlinear systems. This paper presents a sliding mode control (SMC) design approach for nonlinear systems with partially known dynamics by blending data-driven and model-based approaches. First, an SMC is designed for the available (nominal) model of the nonlinear system. The closed-loop state trajectory of the available model is used to build the desired trajectory for the partially known nonlinear system states. Next, a deep policy gradient method is used to cope with unknown parts of the system dynamics and adjust the sliding mode control output to achieve a desired state trajectory. The performance (and viability) of the proposed design approach is finally examined through numerical examples.