IEEE RAS TEP on “Deep Learning for Robot Vision”

The Summer School was co-organized by the Advanced Mining Technology Center of the Universidad de Chile, Chile and the Institute of Engineering Sciences of the Universidad de O’Higgins, Chile. It was co-funded by the IEEE Robotics and Automation Society (RAS) Summer School Program, it was technically sponsored by the IEEE RAS Technical Committee on Robot Learning, and it follows the successful IEEE RAS Summer School on “Robot Vision and Applications” organized in Chile in 2012.

This international Summer School targeted students (Master / PhD level and last years of undergraduate), researchers and professionals interested in Robotics, Robot Vision, Deep Learning and related topics. The official language of the summer school was English, and included tutorial courses, keynote lectures, a student poster competition, and live demonstrations (autonomous vehicle, robot soccer, domestic robots, etc.).

The Summer School provided a clear overview of Deep Learning methods in Robotics with a particular emphasis in robot vision, while also providing an in-depth analysis of state-of-the-art research in this area. There were introductory lectures and short advance courses in the following topics: deep learning for robot vision, deep reinforcement learning, deep learning for robot vision under time & hardware constraints, deep learning for 3D reconstruction & SLAM, deep & model-based learning, deep learning for manipulation & grasping, etc.

There were 13 keynote speakers:

Niko Sünderhauf	Australian Centre for Robotic Vision and Queensland University of Technology (QUT) in Brisbane	Keynote:  Introductory lecture on deep learning for robot vision Talk A:  Semantic SLAM Talk B: The Importance of Uncertainty for Deep Learning in Robotics
Jens Kober	Cognitive Robotics department, Delft University of Technology (TU Delft)	Keynote: (Deep) Reinforcement Learning for Robotics Talk: Learning State-Representations
Juxi Leitner	Australian Centre of Excellence for Robotic Vision	Keynote: (Deep) Learning for Robotic Grasping and Manipulation
Stefan Leutenegger	Imperial College London	Keynote: Spatial AI for mobile robots
Wei Pan	Delft University of Technology (TU Delft)	Keynote: Sparse Bayesian (Deep) Learning for Robotic
Pedro Maldonado	Universidad de Chile	Talk: Similarities and differences between artificial intelligence and the human brain
Wolfhart Totschnig	Universidad Diego Portales	Talk: Introduction to the ethics of artificial intelligence
Rodrigo Verschae	Universidad de O’Higgins	Talk: Deep Photovoltaic Prediction
Alexandre Bergel	Universidad de Chile	Talk: Building neural networks through neuroevolution
Javier Ruiz-del-Solar	Universidad de Chile	Nicolás Cruz & Javier Ruiz del Solar Talk: Bridging the simulation-to-reality-gap using generative neural networks Francisco Leiva & Javier Ruiz del Solar : Deep Reinforcement Learning for Robotic Navigation and Collision Avoidance
Maria Jose Escobar	Universidad Tecnica Federico Santa Maria	Keynote: Towards a Chilean Artificial Intelligence Strategy
Nicolás Cruz	Universidad de Chile	Nicolás Cruz & Javier Ruiz del Solar Talk: Bridging the simulation-to-reality-gap using generative neural networks
Francisco Leiva	Universidad de Chile	Francisco Leiva & Javier Ruiz del Solar Talk: Deep Reinforcement Learning for Robotic Navigation and Collision Avoidance

 

Each year, the IEEE Robotics & Automation Society offers financial support for three Technical Education Programs (RAS-TEP), formerly Summer Schools. In efforts to bring RAS closer to its membership, these programs rotate though the Americas, Europe and Asia and Pacific.

The RAS-TEP program is jointly run by the Member Activities Board (MAB) and the Technical Activities Board (TAB). The program is intended to sponsor or co-sponsor up to three summer schools per year around the world. For more information on RAS Technical Education Programs and how to propose a new program, click here.