Learning for Dynamics, and Control (L4DC)
Abstract
Over the past few years, machine learning has had a tremendous impact in numerous areas, such as computer vision and language transl,ation. Over the next decade, the biggest generator of data is expected to be devices that sense and control the physical world. T,his explosion of real-time data emerging from the physical world requires a rapprochement of areas such as machine learning, model-b,ased dynamical systems, and control and decision theory. While control theory has been firmly rooted in the tradition of model-based, design, the availability and scale of data (both temporal and spatial) will require a rethinking of the foundations for our discipl,ine. From a machine learning perspective, one of the main challenges going forward is to go beyond pattern recognition and address p,roblems in data driven control and decision making as well as learning-based optimization of dynamical processes. We propose a two-d,ay conference on the interface between learning, dynamics, and control on June 23-24 at Stanford University. Since the inaugural con,ference at MIT in 2019, L4DC has successfully created a new community of people that think rigorously across the disciplines, ask no,vel fundamental questions, and develop the foundations of this new scientific area. The conference has already attracted much attent,ion from numerous scientific communities this year, with over 175 paper submissions. We believe that this event will be an influenti,al medium to discuss state-of-the-art interdisciplinary research problems.Intellectual Merit: The intellectual merit of this propos,al is the continuum of a scientific forum that brings together pioneers and state-of-the-art research in the areas of control system,s, optimization, machine learning, and related disciplines that define the state-of-the-art in Learning for Dynamical and Control Sy,stems. Broader Impact: This interdisciplinary conference has a tremendous impact not only scientifically by bridging two distant ar,eas but also from acommunity perspective that nurtures a growing number of junior researchers working on this emerging interface. Th,is conference across control, optimization, and learning will provide a natural and nurturing home for the professional development,of students, postdocs, and junior faculty.We expect over 300 attendees from various backgrounds and with different experience levels,. We will cultivate new research ideas and discussions with keynote talks and oral and poster presentation sessions. We also invite,representatives from government and industry organizations to bridge the gaps between state-of-the-art research and real-world probl,ems. Approved for Public Release.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- May 16, 2022
- Source ID
- N000142212409
Entities
People
- Mykel Kochenderfer
Organizations
- Office of Naval Research
- Stanford University
- United States Navy