Physical simulation is an important tool for robotic manipulation. While simulation has been well-established for robotics education and integrated robot software testing for a long time, only recently the robotics community has made significant progress in transferring manipulation capabilities learned in simulation to reality, a concept termed Sim2Real transfer.
Sim2Real draws its appeal from the fact that it is much faster, cheaper, safer and more informative to perform experiments in simulation than in the real world. Recent advances in Sim2Real have shown how to make advances in solving difficult robotic problems, such as autonomous driving, grasping or in-hand manipulation using Sim2Real techniques. However, Sim2Real still faces significant challenges, and it remains an open question whether Sim2Real techniques will ever reach the sample efficiency and accuracy of techniques based on real-world experimentation, and whether they will scale to realistic problem domains.
In this workshop we invite well-known researchers to debate the state of the art and the impact of Sim2Real on robotics. The workshop will primarily consist of debates focussed on controversial key topics with a few spotlight presentations.
The goal of this workshop is to debate the state of the art and the impact of Sim2Real for robotics. Here, Sim2Real refers to a concept of transferring robot skills acquired in simulation to the real robotic system. Sim2Real draws its appeal from the fact that it is cheaper, safer and more informative to perform experiments in simulation than in the real world. Yet, Sim2Real faces significant challenges.
The proposed workshop is the second edition of a workshop held at R:SS 2019. The R:SS 2019 had the goal of surveying the state of the art in Sim2Real for robotics, with a focus on robotic manipulation, and featured invited talks from top researchers in the field of Sim2Real. In this year’s edition, we aim to review the actual progress in Sim2Real more critically by changing the workshop format: inspired by the ICRA 2019 robotic debates workshop, for this workshop we will invite top-researchers to participate in debates focussed on controversial key topics with a few spotlight presentations.
Invited Debaters [Top]
- Dieter Fox (University of Washington and Nvidia Research)
- Chris Atkeson (Robotics Institute, Carnegie Mellon University)
- John Leonard (MIT)
- Ken Goldberg (UC Berkeley and UCSF)
- Abhinav Gupta (Robotics Institute, Carnegie Mellon University)
- Jan Peters (Technische Universität Darmstadt, MPI for Intelligent Systems)
- Karen Liu (Georgia Tech)
- Anca Dragan (UC Berkeley)
- Peter Welinder (OpenAI)
- Shuran Song (Columbia University)
- Martha White (University of Alberta)
In contrast to the R:SS 2019 edition, we changed the format from invited talks to debates. Each debate will focus on a key - rather controversial - statement regarding Sim2Real, and will be discussed by two proponents and two opponents of that statement. Each debate consists of short introductory pitches by the two sides, providing an opportunity to presenters to also highlight their work, followed by a moderated discussion. An example list of statements includes:
“Sim2Real will never work for complex robotic tasks”;
“Sim2Real is able to successfully leverage inaccurate simulations - accurate physics-based simulation and photo-realistic rendering is not required”;
“Sim2Sim performance is sufficient to indicate progress in Sim2Real”;
“Sim2Real is nothing more than system identification / model-based RL”.
We will coordinate with panelists regarding the phrasing and the selection of the statements as well as the assignment of panelists upon the acceptance of the workshop
Call for Contributions [Top]
Please stand by. This information will be published if the workshop gets accepted. We will be accepting 2 page extended abstracts.
Important dates [Top]
- Workshop Acceptance Notification: March 6, 2020
- Potential Workshop Dates: July 12/13, 2020
Taking inspiration from the ICRA 2019 Debates on the Future of Robotics Research, the workshop will consist of three debates. Every debates focuses on a single key question and is structured as follows: Poster teasers related to debate topic (3-5 minutes each depending on number) Pitch by proponents (2 researchers), 15 minutes Pitch by opponents (2 researchers), 15 minutes Debate, 45 minutes
We will be soliciting poster submissions for the workshop. We will review the contributions by putting together a program committee with experts in the field. We will have two poster sessions during the coffee breaks along with teaser presentations.
We will conclude the workshop with a panel discussion focusing on the question on how Sim2Real and real-world experimentation can be combined in the best way to achieve the best of both worlds.
|Sebastian Höfer is an applied scientist at Amazon Robotics AI headed by Siddhartha Srinivasa. Before joining Amazon, he received his Ph.D. with Oliver Brock at Technische Universität Berlin.|
|Kostas Bekris is an Associate Professor at the Computer Science department of Rutgers University and an Amazon Scholar at the Amazon Robotics AI team headed by Siddhartha Srinivasa. He received his PhD with Lydia Kavraki at Rice University.|
|Ankur Handa is a senior research scientist at NVIDIA robotics lab run by Dieter Fox. Prior to that he was a research scientist at OpenAI. He received his Ph.D. with Dr. Andrew Davison and spent two years at University of Cambridge in Prof. Roberto Cipolla’s lab as a post-doctoral researcher.|
|Juan Camilo Gamboa is a PhD Candidate at the School of Computer Science at McGill University. His research focuses on model-based RL for control and navigation of underwater vehicles.|
|Florian Golemo is a postdoctoral fellow at Mila and ElementAI, working with Liam Paull, Aaron Courville, and Chris Pal on Sim2Real and 3D perception problems. He received his PhD from INRIA Bordeaux under supervision of Pierre-Yves Oudeyer.|
|Melissa Mozifian is a PhD Candidate at the School of Computer Science at McGill University. Her research focuses on deep reinforcement learning and transfer for control of robot manipulation tasks.|