Connectionists: [CfP]: ICRA 2021 Workshop on Learning to Learn for Robotics

Timothy Hospedales t.hospedales at ed.ac.uk
Thu Mar 18 15:10:31 EDT 2021


We invite submissions of papers to the ICRA 2021 workshop on Learning to Learn for Robotics. 

****** Key Info: ******

Workshop Website: https://sites.google.com/view/learn-to-learn-robotics

The goal of the workshop is to bring together scientists from different backgrounds to further the understanding and development of learning to learn algorithms for robotics. In particular we are interested in creating a platform to enable the exchange between the fields of cognitive science, machine learning and robot learning.

We welcome contributions on all aspects of Learning To Learn, and specifically encourage contributions with respect to: 

	• What can we learn from humans utilising their bodies in the process of learning-to-learn;
	• How to make use of the embodied structure of a robot to improve or self-supervise the process of meta-learning; do we need new algorithms for embodied meta-learning?
	• Do people learn-to-learn different concepts separately or do we learn continuously throughout our lifespans; how do we make sense of the surrounding environment in this process?
	• How can we ensure learning-to-learn is safe for an embodied robot and its environment? 
	• We also solicit submissions on negative results on meta learning that help us understand the current limitations and boundaries of learning to learn

****** Key Dates: ******
Submission deadline: May 15th 2021
Workshop day: TBA


****** Workshop Abstract******

Recent years have seen a lot of interest in the development and use of learning-to-learn for a wide range of applications. Yet, existing solutions rarely take into account the structured nature of a learner’s body which constrains their applicability to learning in physical environments, an aspect which is core in robotics. 
In this workshop, we’d like to discuss how humans use their own embodied structure to learn effectively and efficiently, and what we can do to enable robotic learn-to-learn in a similar fashion. Our goal is to bring together researchers from a variety of backgrounds with the hope to discuss and reason about what learning-to-learn and embodiment means from a cognitive neuroscience perspective, and how this knowledge might translate into improving robot learning.
We believe that it is an important moment for the robot learning community to reflect upon these questions in order to advance the field and increase its variety in approaching learning to learn. We hope that by fostering discussions between cognitive science, machine learning and robot learning researchers, we can enable all sides to draw inspiration to further the understanding and development of learning-to-learn algorithms and applications.


Invited Speakers:
Pierre-yves Oudeyer (Inria)
Chelsea Finn (Stanford)
Pulkit Agrawal (MIT)
Mattej Hoffmann (CTU Prague)
Simon Osindero (DeepMind)
Dana Kulic (Monash University)


We look forward to receiving your submissions!

The organizing committee

Sarah Bechtle (Max-Planck-Institute for Intelligent Systems, Tübingen)
Todor Davchev (University of Edinburgh)
Yevgen Chebotar (Google Brain)
Timothy Hospedales (University of Edinburgh and Samsung AI Research)
Franziska Meier (Facebook AI Research)

email: learningtolearn.icra2021 at gmail.com
-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.




More information about the Connectionists mailing list