Navigation

Learning for Dynamics and Control (L4DC)

Learning for Dynamics and Control (L4DC)

May 30 & 31, 2019 at the Ray and Maria Stata Center

Massachusetts Institute of Technology, Cambridge, MA

Over the next decade, the biggest generator of data is expected to be devices which sense and control the physical world.

This explosion of real-time data that is emerging from the physical world requires a rapprochement of areas such as machine learning, control theory, and optimization. While control theory has been firmly rooted in tradition of model-based design, the availability and scale of data (both temporal and spatial) will require rethinking of the foundations of our discipline. From a machine learning perspective, one of the main challenges going forward is to go beyond pattern recognition and address problems in data driven control and optimization of dynamical processes.

Our overall goal is to create a new community of people that think rigorously across the disciplines, asks new questions, and develops the foundations of this new scientific area.

Anima Anandkumar

Bren Professor of Computer Science at Caltech

Francesco Borrelli

Professor of Mechanical Engineering at UC Berkeley

Emma Brunskill

Assistant Professor of Computer Science at Stanford University

Anca Dragan

Assistant Professor of Electrical Engineering and Computer Sciences at UC Berkeley

Maryam Fazel

Associate Professor of Electrical Engineering at the University of Washington

Sham Kakade

Associate Professor in Computer Science and Statistics at the University of Washington

Zico Kolter

Assistant Professor of Computer Science at Carnegie Mellon University

Andreas Krause

Professor of Computer Science at ETH Zurich

Sergey Levine

Assistant Professor of Electrical Engineering and Computer Sciences at UC Berkeley

Manfred Morari

Distinguished Faculty Fellow of Electrical and Systems Engineering, University of Pennsylvania

Dorsa Sadigh

Assistant Professor of Computer Science and Electrical Engineering at Stanford University

Angela Schoellig

Assistant Professor at the University of Toronto, Institute for Aerospace Studies

Stefano Soatto

Professor of Computer Science at UCLA

Russ Tedrake

Toyota Professor of EECS, Aero/Astro, and Mechanical Engineering at MIT

Claire Tomlin

Professor of Electrical Engineering and Computer Sciences and Charles A. Desoer Chair in the College of Engineering at UC Berkeley

John N. Tsitsiklis

Clarence J Lebel Professor of Electrical Engineering and Computer Science & Director of LIDS at MIT

Emo Todorov

Associate Professor of Applied Mathematics and Computer Science at the University of Washington

Rene Vidal

Herschel Seder Professor of Biomedical Engineering & Director of the Mathematical Institute for Data Science at Johns Hopkins University

Cathy Wu

Assistant Professor of CEE/ IDSS (starting July) at MIT

 

Conference Scope

The conference will focus on the foundations and applications of Learning for Dynamical and Control Systems. Topics of interest include, but are not limited to:

  • Foundations of Learning of dynamics models
  • System identification
  • Optimization for Machine Learning
  • Data-driven optimization for dynamical systems
  • Distributed learning over distributed systems
  • Reinforcement learning for physical systems
  • Safe reinforcement learning and safe adaptive control
  • Statistical learning for dynamical and control systems
  • Bridging model-based and learning-based dynamical and control systems
  • Physics-constrained learning
  • Physical learning in dynamical and control systems applications in robotics, autonomy, transportation systems, cognitive systems, cognitive systems, neuroscience, etc.

While the conference is open to any topic on the interface between machine learning, control, optimization and related areas, its primary goal is to address scientific and application challenges in real-time physical processes modeled by dynamical or control systems.