Conferences/Workshops

Workshop on New Frontiers for Deep Learning in Robotics, RSS 2017

Robotics: Science and Systems (RSS) 2017

In this workshop a wide range of renowned experts will discuss deep learning techniques at the frontier of research that are not yet widely adopted, discussed, or well-known in the robotics community.

We carefully selected research topics such as Bayesian deep learning, generative models, or deep reinforcement learning for planning and navigation that are of high relevance and potentially groundbreaking for robotic perception, learning, and control. The workshop introduces these techniques to the robotics audience, but also exposes participants from the machine learning community to real-world problems encountered by robotics researchers that apply deep learning in their research.

Where and When?

The workshop is organised in conjunction with the Robotics: Science and Systems conference (RSS) at MIT, Boston, USA and takes place on July 15, 2017.

Invited Speakers

The following experts have agreed to join the list of speakers for our workshop (and will take part in the panel discussion):

  • Bayesian Deep Learning: Yarin Gal (University of Cambridge)
  • Learning to Navigate: Piotr Mirowski (DeepMind)
  • Generative Models for Reinforcement Learning: Pieter Abbeel (UC Berkeley/OpenAI)
  • Challenges of Embodied Deep Learning: Yann LeCun (Facebook, NYU)
  • Learning and Cognitive Robotics: Josh Tenenbaum (MIT) (tentative)
  • A Neuroscience Perspective on Deep Learning: Davix Cox (Harvard)
  • Generative Models: Aaron Courville (Université de Montréal)

Call for Papers

Download the Call for Papers (pdf) here.

Organisers and Support

The workshop is organised by Dr Niko Sünderhauf, Dr Juxi Leitner, Assoc Prof Milchael Milford, Prof Peter Corke from the Australian Centre for Robotic Vision (ACRV), and Queensland University of Technology (QUT), as well as by Assoc Prof Pieter Abbeel from UC Berkeley.

The workshop is supported by the Australian Centre for Robotic Vision.

More Information

For more information, please check the workshop website at http://tinyurl.com/robotdeeplearning.

Author - Niko Suenderhauf

Niko Suenderhauf

Niko is a postdoctoral research fellow at Queensland University of Technology, and the leader of the project Scene Understanding for Robotic Vision in the ARC Centre of Excellence for Robotic Vision. His research is concerned with enabling robots to see, understand, and recognise their environment reliably and under all conditions. Niko received his PhD in 2012 from Chemnitz University of Technology, Germany, for his research on robust localisation and mapping for robots and autonomous vehicles. Link

Category: Conferences/Workshops
Posted 24 April 2017

Australian Centre for Robotic Vision
2 George Street Brisbane, 4001
+61 7 3138 7549