Machine Learning for Control [About this Issue]

ThisIEEE Control Systemsissue includes two feature articles and one focus on education. The first feature article[A1]is the transcript of the 2023 Bode Lecture by Miroslav Krstic. The author proposes a use of machine learning that leverages the control community’s heritage of rigorous, certificate-bearing control designs. He employs, in partial differential equations (PDE) control, the recent breakthroughs in deep learning approximations of the so-called neural operators. With neural operators, entire PDE control methodologies are encoded into what amounts to a function evaluation, leading to a thousandfold speedup in real-time implementation, while retaining the stability guarantees. Applications range from traffic control and epidemiology to manufacturing, energy generation, and supply chains.