Frontiers of optimization for robotics
Workshop at Robotics: Science and Systems
July 15th, 2024 in Delft, Netherlands
Workshop about the latest and future advances in optimization for robotics, by roboticists
Workshop about the latest and future advances in optimization for robotics, by roboticists
This workshop is organized in response to the great advances in optimization for robotics and by roboticists and the resulting need for an in-depth treatment of this topic. The workshop has three central motivations, which are outlined below.
This workshop is organized in response to the great advances in optimization for robotics and by roboticists and the resulting need for an in-depth treatment of this topic. The workshop has three central motivations, which are outlined below.
Exchange ideas across fields
Exchange ideas across fields
Optimization is ubiquitous in robotics and the tools developed in one application area can foster innovation in other areas. This workshop brings people from different fields together, creating an environment where people can learn from each other and find common ground in the optimization tools and theories developed in all fields of robotics.
Optimization is ubiquitous in robotics and the tools developed in one application area can foster innovation in other areas. This workshop brings people from different fields together, creating an environment where people can learn from each other and find common ground in the optimization tools and theories developed in all fields of robotics.
Establish future directions for optimization
Establish future directions for optimization
Optimization research is moving fast! Recent developments in the machine learning community have become competitive with classical model-based methods in robotics. At the same time, theoretical concepts from non-convex optimization and other advanced fields in mathematics have found applications in robotics in recent years. New methods seek to combine learning and model-based methods to capitalize on their combined strengths. This workshop aims to contextualize and summarize these advances and provide a platform for establishing consensus in terms of the future of optimization in robotics.
Optimization research is moving fast! Recent developments in the machine learning community have become competitive with classical model-based methods in robotics. At the same time, theoretical concepts from non-convex optimization and other advanced fields in mathematics have found applications in robotics in recent years. New methods seek to combine learning and model-based methods to capitalize on their combined strengths. This workshop aims to contextualize and summarize these advances and provide a platform for establishing consensus in terms of the future of optimization in robotics.
Foster community and distribute Open Code
Foster community and distribute Open Code
Openly distributed code can help both the robotics and optimization communities move forward, interact, and learn from each other. This workshop provides a platform to showcase open-source tools that can benefit both researchers and practitioners, promoting transparency and reusability.
Openly distributed code can help both the robotics and optimization communities move forward, interact, and learn from each other. This workshop provides a platform to showcase open-source tools that can benefit both researchers and practitioners, promoting transparency and reusability.
Invited Speakers
Invited Speakers
Luca Carlone
Luca Carlone
Massachusetts Institute of Technology
Russ Tedrake
Russ Tedrake
Massachusetts Institute of Technology
Noemie Jaquier
Noemie Jaquier
Karlsruhe Institute of Technology
David M. Rosen
David M. Rosen
Northeastern University
Paul Goulart
Paul Goulart
University of Oxford
Francesco Biral
Francesco Biral
University of Trento
Brandon Amos
Brandon Amos
FAIR, Meta
Rika Antonova
Rika Antonova
University of Cambridge
Lin Zhao
Lin Zhao
National University of Singapore
Armin Nurkanovic
Armin Nurkanovic
University of Freiburg
Marc Toussaint
Marc Toussaint
Technical University Berlin
Robin Deits
Robin Deits
Boston Dynamics