Self-Adaptive Robust Motion Planning for High DoF Robot Manipulator using Deep MPC

TL;DR

This paper presents a novel self-adaptive control scheme using deep MPC with a gradient sign-based update law to improve motion planning for high-DoF robot manipulators, demonstrating real-time learning and robust performance.

Contribution

It introduces a deep MPC-based self-adaptive control approach with a gradient sign update law to address gradient issues and enhance real-time learning in high-DoF robots.

Findings

Effective real-time learning of nonlinear plant dynamics.

Robust motion planning performance in high-DoF robot simulations.

Mitigation of vanishing and exploding gradient problems.

Abstract

In contemporary control theory, self-adaptive methodologies are highly esteemed for their inherent flexibility and robustness in managing modeling uncertainties. Particularly, robust adaptive control stands out owing to its potent capability of leveraging robust optimization algorithms to approximate cost functions and relax the stringent constraints often associated with conventional self-adaptive control paradigms. Deep learning methods, characterized by their extensive layered architecture, offer significantly enhanced approximation prowess. Notwithstanding, the implementation of deep learning is replete with challenges, particularly the phenomena of vanishing and exploding gradients encountered during the training process. This paper introduces a self-adaptive control scheme integrating a deep MPC, governed by an innovative weight update law designed to mitigate the vanishing and exploding gradient predicament by employing the gradient sign exclusively. The proffered controller is a self-adaptive dynamic inversion mechanism, integrating an augmented state observer within an auxiliary estimation circuit to enhance the training phase. This approach enables the deep MPC to learn the entire plant model in real-time and the efficacy of the controller is demonstrated through simulations involving a high-DoF robot manipulator, wherein the controller adeptly learns the nonlinear plant dynamics expeditiously and exhibits commendable performance in the motion planning task.