Biography
Luca Furieri is an Associate Professor of Engineering Science at the University of Oxford and a Tutorial Fellow in Engineering at St Hugh’s College. Before joining Oxford, he was an SNSF Ambizione Fellow and principal investigator at EPFL. He received his PhD from ETH Zurich. His work has received the IEEE Transactions on Control of Network Systems Best Paper Award and the O. Hugo Schuck Best Paper Award.
Luca’s research lies at the interface of control theory, optimisation, and machine learning. His group develops mathematical methods for autonomous systems that learn from data while operating in feedback with the physical world, with a focus on dynamical systems composed of many interacting decision-makers. His research is motivated by applications in robotics, multi-robot and logistics systems, and energy systems.
Most Recent Publications
On the Guarantees of Minimizing Regret in Receding Horizon
On the Guarantees of Minimizing Regret in Receding Horizon
Erratum to “Learning to Boost the Performance of Stable Nonlinear Systems”
Erratum to “Learning to Boost the Performance of Stable Nonlinear Systems”
Regret optimal control for uncertain stochastic systems
Regret optimal control for uncertain stochastic systems
Learning to Optimize With Convergence Guarantees Using Nonlinear System Theory
Learning to Optimize With Convergence Guarantees Using Nonlinear System Theory
Learning to Boost the Performance of Stable Nonlinear Systems
Learning to Boost the Performance of Stable Nonlinear Systems
Current Research Projects
Reinforcement Learning with Guarantees: Developing a neural system-level synthesis perspective to learn over safe and stable closed-loop behaviors.
Distributed Control of Networked Systems: Designing modular control policies for networks of systems, from linear to nonlinear settings.
Learning-based Optimization: Enhancing the performance of legacy solvers through neural network components without compromising worst-case convergence guarantees.
Research Interests
Networked Control with Safety and Stability Guarantees
Large-scale networked systems, such as autonomous vehicle fleets and power grids, require many interacting agents to coordinate sensing, actuation, and communication in real time. Luca's group designs learning-based control frameworks that scale to these complex environments while preserving fundamental safety and stability guarantees, without introducing unnecessary conservatism.
System Theory for Algorithm Design
Many engineering problems involve solving optimization tasks rapidly and reliably. System and control theory offer a principled toolkit to design optimization algorithms with formal guarantees on convergence, speed, and robustness. Luca's group develops enhanced optimization and machine learning algorithms by leveraging nonlinear system theory and integrating neural network components.
Research Group
Most Recent Publications
On the Guarantees of Minimizing Regret in Receding Horizon
On the Guarantees of Minimizing Regret in Receding Horizon
Erratum to “Learning to Boost the Performance of Stable Nonlinear Systems”
Erratum to “Learning to Boost the Performance of Stable Nonlinear Systems”
Regret optimal control for uncertain stochastic systems
Regret optimal control for uncertain stochastic systems
Learning to Optimize With Convergence Guarantees Using Nonlinear System Theory
Learning to Optimize With Convergence Guarantees Using Nonlinear System Theory
Learning to Boost the Performance of Stable Nonlinear Systems
Learning to Boost the Performance of Stable Nonlinear Systems
