Invited Session Series on Learning-based Control
Data science and machine learning have demonstrated tremendous success in the last decades in applications such as image recognition, recommender systems, or question answering. Compared to these applications, which can largely be subsumed as static problems, learning-based control systems take a special role within the world of statistical and machine learning. The coupling of a learning algorithm with a control loop requires a combined treatment as a dynamic process and raises fundamental questions about stability, robustness, and safety, which are generally less critical in most traditional application areas of machine learning. In order to leverage the potential of data-based and learning methods for control, we therefore believe that principled approaches integrating machine learning and control theory are needed, which extend beyond the methods and tools of the individual disciplines.
Based on the increasing interest in this domain, we have started a new Invited Session Series on Learning-based Control taking place yearly at the IEEE Conference on Decision and Control (CDC). The first session in December 2016 was a great success and we are looking forward to your contributions and the next session at CDC'17. Please do not hesitate to contact us if you have any question.
It is our pleasure to invite experts in the area to contribute a paper to the Invited Session on Learning-based Control at CDC 2017. The session is planned to include six distinguished papers, which will undergo the same review process as regular CDC papers and, if accepted, will be published in the conference proceedings.
More information:Invited Session Call CDC 2017 (PDF, 94 KB)
Angela Schoellig is an Assistant Professor at the University of Toronto Institute for Aerospace Studies (UTIAS), where she heads the Dynamic Systems Lab. She is also an Associate Director of the Center for Aerial Robotics Research and Education (CARRE) at the University of Toronto. With her team, she conducts research at the interface of robotics, controls and machine learning. Her goal is to enhance the performance and autonomy of robots by enabling them to learn from past experiments and from each other.
Sebastian is a Senior Research Scientist and Group Leader at the Max Planck Institute for Intelligent Systems in Tübingen, Germany. Sebastian leads the Intelligent Control Systems group within the Autonomous Motion Department. His research interests are in the area of control systems theory and design with emphasis on autonomous, networked, and learning systems.
Melanie is an Assistant Professor at the Department of Mechanical and Process Engineering at ETH Zurich, where she is leading the Intelligent Control Systems group at the Institute for Dynamic Systems and Control. Her research interests are centered around real-time and distributed control and optimization, as well as safe learning-based control, with applications to human-in-the-loop control.
The Invited Session was very well received among CDC participants. We thank all authors for contributing to this success.
- Distributed Iterative Learning Control for a Team of Quadrotors
Hock, Andreas (Univ. of Toronto)
Schoellig, Angela P (Univ. of Toronto)
- Continuous-Time DC Kernel — a Stable Generalized First Order Spline Kernel
Chen, Tianshi (Linköping Univ. Sweden)
Pillonetto, Gianluigi (Univ. of Padova)
Chiuso, Alessandro (Univ. Di Padova)
Ljung, Lennart (Linkoping Univ)
- Learning Quadrotor Dynamics Using Neural Network for Flight Control
Bansal, Somil (UC Berkeley)
Akametalu, Anayo K. (UC Berkeley)
Tomlin, Claire J. (UC Berkeley)
Laine, Forrest J. (UC Berkeley)
- Safe Learning of Regions of Attraction for Uncertain, Nonlinear Systems with Gaussian Processes
Berkenkamp, Felix (ETH Zurich)
Moriconi, Riccardo (ETH Zurich)
Schoellig, Angela P (Univ. of Toronto)
Krause, Andreas (ETH Zurich)
- Learning State Representation for Deep Actor-Critic Control
Munk, Jelle (Delft Univ. of Tech)
Kober, Jens (Delft Univ. of Tech)
Babuska, R. (Delft Univ. of Tech)
- Relaxation of the EM Algorithm Via Quantum Annealing for Gaussian Mixture Models
Miyahara, Hideyuki (The Univ. of Tokyo)
Tsumura, Koji (The Univ. of Tokyo)
Sughiyama, Yuki (The Univ. of Tokyo)