RSS 2020 Workshop Proposal



Self-Supervised Robot Learning

Self-supervised learning is a promising direction that aims to learn representations from the data itself without explicit and potentially even manual supervision. One of the major benefits of self-supervised learning is the ability to scale to large amounts of unlabelled data in a lifelong learning manner and to improve performance by reducing the effect of dataset bias. Recent development in self-supervised learning has resulted in  achieving comparable or better performance than fully-supervised models. However, many of these methods are developed in domain-specific communities such as robotics, computer vision or reinforcement learning. The aim of this workshop is to bring together researchers from different communities to discuss opportunities, challenges and explore new directions.

Invited Speakers

Pieter Abbeel (UC Berkeley & Covariant.AI)

Dieter Fox (University of Washington & NVIDIA)

Abhinav Gupta (CMU & Facebook AI Research)

Roberto Calandra (Facebook AI Research)

Chelsea Finn (Stanford University)

Pierre Sermanet (Google Brain)

Andy Zeng (Google Brain)


The focus topics of our workshop include, but are not restricted to:

  • Self-supervised learning for robotics, robot vision, reinforcement learning….
  • Self-supervised domain adaptation
  • Meta-learning of self-supervised tasks
  • Large-scale self-supervised learning
  • Learning of generalizable pretext-tasks
  • Loss functions for self-supervised learning
  • Learning from auxiliary/multiple tasks
  • Multimodal and cross-modal learning

Important Dates

March 12, 2020    Call for Contributions

April 9, 2020        Submission Deadline

April 30, 2020      Author Notification

May 15, 2020       Camera Ready Submission

July 13, 2020       Workshop


Abhinav Valada (University of Freiburg)< valada(at) > (Primary contact)

Anelia Angelova (Google Research/Google Brain) < anelia(at) >

Joschka Boedecker (University of Freiburg) < jboedeck(at) >

Oier Mees  (University of Freiburg)  < meeso(at) >

Wolfram Burgard (University of Freiburg) < burgard(at) >