Rapid Vibration Suppression and Trajectory Tracking of a Serial Manipulator with Multi-Flexible Links

TL;DR

This paper introduces a backstepping output-feedback control framework combined with DeepONet neural operators for rapid vibration suppression and precise trajectory tracking in multi-flexible-link serial manipulators, enhancing performance and scalability.

Contribution

The novel integration of DeepONet neural operators with backstepping control enables real-time, scalable vibration suppression and trajectory tracking in flexible robotic manipulators.

Findings

Faster vibration suppression compared to traditional methods.

Successful experimental validation on a two-link flexible manipulator.

Effective end-effector trajectory convergence under the proposed control scheme.

Abstract

Flexible robotic manipulators (FRMs) offer advantages in lightweight design and large workspace, but their structural flexibility induces vibrations, accelerates fatigue, degrades tracking performance, and limits operational speed. These challenges are further amplified in multi-link serial manipulators, where increased overall length leads to greater structural flexibility. This article presents a backstepping output-feedback framework for fast vibration suppression and tip tracking of an n-degree-of-freedom serial flexible manipulator robot (nDSFMR), with a DeepONet-based approximation for practical deployment. Each link-joint is modeled as a Timoshenko beam coupled with an ODE and transformed into a canonical hyperbolic PDE with boundary dynamics. A backstepping-based boundary controller at the joint is developed to equivalently inject distributed damping along the beam, enabling rapid vibration suppression and trajectory tracking, only using available boundary measurements. To enable real-time implementation and scalability, a DeepONet neural operator is introduced to approximate the backstepping kernels, significantly reducing computational cost and facilitating fast controller updates under varying operating conditions. Experiments on a two-link flexible manipulator demonstrate faster vibration suppression and convergence of the end-effector to the desired trajectory, compared with a linear quadratic regulator (LQR) with feedforward control.