Safe Imitation Learning of Nonlinear Model Predictive Control for Flexible Robots

TL;DR

This paper introduces a safe imitation learning framework that approximates nonlinear model predictive control for flexible robots, significantly reducing computation time while maintaining safety and performance.

Contribution

It presents a novel framework combining imitation learning and a predictive safety filter to enable real-time, safe control of flexible robots with reduced computational demands.

Findings

Over eightfold reduction in computation time compared to NMPC.

Guarantees safety constraints during control.

Outperforms state-of-the-art reinforcement learning methods.

Abstract

Flexible robots may overcome some of the industry's major challenges, such as enabling intrinsically safe human-robot collaboration and achieving a higher payload-to-mass ratio. However, controlling flexible robots is complicated due to their complex dynamics, which include oscillatory behavior and a high-dimensional state space. Nonlinear model predictive control (NMPC) offers an effective means to control such robots, but its significant computational demand often limits its application in real-time scenarios. To enable fast control of flexible robots, we propose a framework for a safe approximation of NMPC using imitation learning and a predictive safety filter. Our framework significantly reduces computation time while incurring a slight loss in performance. Compared to NMPC, our framework shows more than an eightfold improvement in computation time when controlling a three-dimensional flexible robot arm in simulation, all while guaranteeing safety constraints. Notably, our approach outperforms state-of-the-art reinforcement learning methods. The development of fast and safe approximate NMPC holds the potential to accelerate the adoption of flexible robots in industry. The project code is available at: tinyurl.com/anmpc4fr