Iterative Tuning of Nonlinear Model Predictive Control for Robotic Manufacturing Tasks

TL;DR

This paper introduces an iterative learning framework for automatically tuning NMPC weights in robotic manufacturing, significantly reducing tuning time while maintaining high tracking accuracy.

Contribution

It proposes a novel empirical sensitivity-based weight update method for NMPC, enabling fast online adaptation without requiring gradient computations.

Findings

Converges to near-optimal tracking within 4 repetitions

Achieves RMSE within 0.3% of offline Bayesian Optimization

Reduces tuning evaluations from 100 to 4

Abstract

Manufacturing processes are often perturbed by drifts in the environment and wear in the system, requiring control re-tuning even in the presence of repetitive operations. This paper presents an iterative learning framework for automatic tuning of Nonlinear Model Predictive Control (NMPC) weighting matrices based on task-level performance feedback. Inspired by norm-optimal Iterative Learning Control (ILC), the proposed method adaptively adjusts NMPC weights Q and R across task repetitions to minimize key performance indicators (KPIs) related to tracking accuracy, control effort, and saturation. Unlike gradient-based approaches that require differentiating through the NMPC solver, we construct an empirical sensitivity matrix, enabling structured weight updates without analytic derivatives. The framework is validated through simulation on a UR10e robot performing carbon fiber winding on a tetrahedral core. Results demonstrate that the proposed approach converges to near-optimal tracking performance (RMSE within 0.3% of offline Bayesian Optimization (BO)) in just 4 online repetitions, compared to 100 offline evaluations required by BO algorithm. The method offers a practical solution for adaptive NMPC tuning in repetitive robotic tasks, combining the precision of carefully optimized controllers with the flexibility of online adaptation.