Data-Driven Feedback Linearizing Controller for Robotic Manipulators with Uncertain Dynamics

In this article, we introduce a data-driven feedback linearizing controller for robotic manipulators with uncertain dynamics based on the augmented framework of time delay estimation (TDE) and a residue acceleration observer. While the time-delayed estimation approach in the inner-loop uses immediate past measurements of control effort and state to get an online estimate of the unknown manipulator dynamics, the residue acceleration observer in the outer-loop helps to nullify the estimation error on the fly, thus establishing a linear and decoupled dynamics. Once the linear dynamics is established, a PD controller helps to track the desired output trajectories. Simulation results for a two-link manipulator using the proposed controller, along with a delay-dependent convergence analysis, are shown to validate the proposition.