Alexandre Didier
Alexandre Didier

Doctoral Student

ETH Zurich

About Me

Hi, I'm Alexandre Didier, a doctoral student under the supervision of Prof. Dr. Melanie Zeilinger at IDSC, D-MAVT, ETH Zurich. My main research interests lie in the development of predictive safety filters. These filters use model predictive control techniques to enhance any learning-based controller (e.g. reinforcement learning policies) or human operators with safety guarantees. I'm also interested in establishing relationships between online optimization and classical control theory and recently I have looked into how system theory can be used in the context of foundation models.

Interests
  • Artificial Intelligence
  • Control Theory
  • Model Predictive Control
  • Machine Learning
  • Optimization
Education

  • PhD Control Theory | Applied Mathematics | Robotics

    ETH Zurich

  • MSc Robotics, Systems and Control

    ETH Zurich

  • BSc Mechanical Engineering

    ETH Zurich

  • High School

    Athénée de Luxembourg

Featured Publications
Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
Approximate predictive control barrier functions using neural networks: A computationally cheap and permissive safety filter
Recent Publications
Jelena Trisovic, Alexandre Didier, Simon Muntwiler, Melanie N Zeilinger (2024). Moving horizon estimation for simultaneous localization and mapping with robust estimation error bounds. arXiv preprint arXiv:2411.13310.

Cite Preprint

Alexandre Didier, Melanie N. Zeilinger (2024). Approximate predictive control barrier function for discrete-time systems. arXiv preprint arXiv:2411.11610.

Cite Preprint

Jerome Sieber, Alexandre Didier, Melanie N. Zeilinger (2024). Computationally Efficient System Level Tube-MPC for Uncertain Systems. arXiv preprint arXiv:2406.12573.

Cite Preprint

Jerome Sieber, Carmen Amo Alonso, Alexandre Didier, Melanie N. Zeilinger, Antonio Orvieto (2024). Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks. arXiv preprint arXiv:2405.15731.

Cite Preprint

Alexandre Didier, Andrea Zanelli, Kim P. Wabersich, Melanie N. Zeilinger (2024). Predictive stability filters for nonlinear dynamical systems affected by disturbances. arXiv preprint arXiv:2401.11183.

Cite Code Preprint

See all publications