Adaptive control of a mechatronic system using constrained residual reinforcement learning

TL;DR

This paper introduces a residual reinforcement learning approach for adaptive control of mechatronic systems, combining safety guarantees with improved performance by constraining learned corrections relative to a base controller.

Contribution

It presents a novel constrained residual RL method that ensures safety and stability in industrial control systems, validated through theoretical proofs and experimental validation.

Findings

The method guarantees stability for a broad class of systems.

Constraining residual actions enhances safety during learning.

Experimental results show improved performance and safety.

Abstract

We propose a simple, practical and intuitive approach to improve the performance of a conventional controller in uncertain environments using deep reinforcement learning while maintaining safe operation. Our approach is motivated by the observation that conventional controllers in industrial motion control value robustness over adaptivity to deal with different operating conditions and are suboptimal as a consequence. Reinforcement learning on the other hand can optimize a control signal directly from input-output data and thus adapt to operational conditions, but lacks safety guarantees, impeding its use in industrial environments. To realize adaptive control using reinforcement learning in such conditions, we follow a residual learning methodology, where a reinforcement learning algorithm learns corrective adaptations to a base controller's output to increase optimality. We investigate how constraining the residual agent's actions enables to leverage the base controller's robustness to guarantee safe operation. We detail the algorithmic design and propose to constrain the residual actions relative to the base controller to increase the method's robustness. Building on Lyapunov stability theory, we prove stability for a broad class of mechatronic closed-loop systems. We validate our method experimentally on a slider-crank setup and investigate how the constraints affect the safety during learning and optimality after convergence.