Online learning-based linear model predictive control approximation
온라인 학습 기반 선형 모델 예측 제어 근사
Changeun Park, Kyunghwan Choi*
Key Figure

  • Access the paper
    • 제어로봇시스템학회 (ICROS), 2026 accepted [📃 Full-Text]
    • Abstract

      • This paper proposes an online learning method for approximating the policy of linear MPC using a Radial Basis Function model. The proposed neural-network-based policy updates its weights online to minimize the MPC cost function. The resulting policy shows behavior similar to that obtained from a QP-solver-based MPC with a shorter computation time. The proposed method is validated through MATLAB simulations of IPMSM current control system.