Transferability in Robotics is a key step to achieving sufficient scale and robustness in order to make robots unambiguous in our everyday lives. The concept of transferability covers a wide range of topics such as i) Embodiment transfer - transferring from one robotic platform to another while considering their different embodiments, ii) Task/skill transfer - transferring methods or capabilities from one task to another, and iii) Knowledge transfer - transferring high-level concepts from one to another. These different areas also have different definitions of transferability and employ different approaches (e.g., representation learning, reinforcement learning, meta-learning, sim2real, interactive learning) for the respective task. While each of these fields has made headway in its own right, to really push forward the state of the art in transferability, a combination of contributions from the different fields is needed. The EU Horizon project euRobin aims to achieve transferability by not focusing on any specific sub-category but to share knowledge in a higher/more abstract way. The goal of this workshop is to combine the advances made in the individual fields into a more global picture by facilitating a common understanding of transferability, as well as highlighting contributions and encouraging collaborations between the different areas.
The workshop aims to explore different aspects of transferability in robotics, facilitating contributions from a wide range of related fields. It also introduces the vision of the euRobin project on how to tackle transferability to solve meaningful real-world tasks such as robotic manufacturing for a circular economy, Personal Robots for Enhanced QOL and Well-Being as well as Outdoor Robots for Sustainable Communities. Specifically, the workshop will focus on, but is not limited to, the following topics in regards to transferability in robotics:
- Transferable representations
- Transfering from simulation to real-world (and vice versa)
- Task to task transfer (meta-learning and others)
- Robot (embodiment) to robot transfer
- Concept to concept transfer
- Transferability in practice
Time Zone: GMT +01
|09:00 - 09:05||Opening|
|09:05 - 09:35||Alin Albu-Schäffer: euROBIN: The European Robotics and AI Network|
|09:35 - 10:05||Animesh Garg: Prospection: rethinking transfer in the era of large scale pretraining|
|10:05 - 10:35||Spotlight talks #1
|10:35 - 11:00||Coffee break + Posters presentation #1
|11:00 – 11:30||David Hsu: Generalization and Transfer in Deformable Object Manipulation|
|11:30 – 12:00||Aleš Ude: Enhancing training datasets for data-driven motion prediction|
|12:00 - 12:45||Group discussion|
|12:45 – 14:00||Lunch|
|14:00 – 14:30||Eric Eaton: Composable Representations for Lifelong Learning in Autonomous Systems (ONLINE)|
|14:30 – 15:00||Aleksandra Faust: Toward Generalist Agents|
|15:00 – 15:30||Spotlight talks #2
|15:30 - 16:00||Coffee break + Posters presentation #2
|16:00 – 16:30||Gayane Kazhoyan: Transferability in Task-level Robot Control for Everyday Mobile Manipulation Actionse|
|16:30 – 17:00||Noémie Jaquier: A Geometric Take on Embodiment Transfer|
|17:00 – 17:45||Panel discussion|
|17:45 – 18:00||Closing remarks|
Accepted extended abstracts (3 pages with unlimited references) presented in poster sessions and selected spotlight talks using the IEEE conference template Submissions are welcome relevent to the above mentioned topics. Contribution are encuraged, but not requierd to be original. Submission will be done over the CMT platform.
The euROBIN project offers funding for one travel grant to attend the workshop in London, covering expenses up to $3,000. The award is designated to exceptional students who are actively working on skill, task, and knowledge transfer. To foster diversity, we highly encourage applications from underrepresented groups. Interested candidates need to submit an extended abstract (see above), a two-page motivation letter, and their CV.
Select "Travel Grant" in the submission system
- Submission Deadline: 17/04/2023
Google Brain, United States
Talk title: Toward Generalist Agents
Bio: Aleksandra Faust is a Senior Staff Research Scientist, Autonomous Agents research lead, and Reinforcement Learning research team co-founder at Google Brain. Her research is centered around safe and scalable autonomous systems for social good, including reinforcement learning, planning, and control for robotics, autonomous driving, and digital assistants. Previously, Aleksandra founded and led Task and Motion Planning research in Robotics at Google, machine learning for self-driving car planning and controls in Waymo, and was a senior researcher in Sandia National Laboratories. She earned a Ph.D. in Computer Science at the University of New Mexico with distinction, and a Master's in Computer Science from the University of Illinois at Urbana-Champaign. Aleksandra won the IEEE RAS Early Career Award for Industry, the Tom L. Popejoy Award for the best doctoral dissertation at the University of New Mexico in the period of 2011-2014, and was named Distinguished Alumna by the University of New Mexico School of Engineering. Her work has been featured in the New York Times, PC Magazine, ZdNet, VentureBeat, and was awarded Best Paper in Service Robotics at ICRA 2018, Best Paper in Reinforcement Learning for Real Life (RL4RL) at ICML 2019, Best Paper of IEEE Computer Architecture Letters in 2020, and IEEE Micro Top Picks 2023 Honorable Mention.
Jožef Stefan Institute, Slovenia
Talk title: Enhancing training datasets for data-driven motion prediction
Bio: Aleš Ude received the Diploma degree in applied mathematics from the University of Ljubljana, Slovenia, and the Dr. eng. sciences degree from the University of Karlsruhe, Germany, in 1990 and 1995, respectively. Currently he is the head of the Dept. of Automatics, Biocybernetics, and Robotics, Jožef Stefan Institute, Ljubljana. His research interests include robot learning, imitation learning, reconfigurable robotic systems, cognitive robotics, and humanoid robotics. He has been a coordinator and/or principal investigator of numerous national and international projects in these areas.
Technical University of Munich, Germany
Talk title: euROBIN: The European Robotics and AI Network
Bio: Alin Albu-Schäffer received his M.S. in electrical engineering from the Technical University of Timisoara, Romania in 1993 and his Ph.D. in automatic control from the Technical University of Munich in 2002. Since 2012 he is the head of the Institute of Robotics and Mechatronics at the German Aerospace Center (DLR). Moreover, he is a professor at the Technical University of Munich, holding the Chair for "Sensor Based Robotic Systems and Intelligent Assistance Systems" at the Computer Science Department. His personal research interests include robot design, modeling and control, nonlinear control, flexible joint and variable compliance robots, impedance and force control, physical human-robot interaction, bio-inspired robot design and control. He received several awards, including the IEEE King-Sun Fu Best Paper Award of the Transactions on Robotics in 2012 and 2014; several ICRA and IROS Best Paper Awards as well as the DLR Science Award. He was strongly involved in the development of the DLR light-weight robot and its commercialization through technology transfer to KUKA. He is the coordinator of euROBIN, the European network of excellence on intelligent robotics.
University of Toronto, Canada
Talk title: Prospection: rethinking transfer in the era of large scale pretraining
Bio: Animesh Garg is an Assistant Professor of Computer Science at University of Toronto and a Faculty Member at the Vector Institute. He directs the UofT People, AI and Robotics (PAIR) group. Animesh is affiliated with Mechanical and Industrial Engineering (courtesy) and UofT Robotics Institute. He is also a Sr. Research Scientist at Nvidia.
National University of Singapore, Singapore
Talk title: Generalization and Transfer in Deformable Object Manipulation
Bio: David Hsu is a professor of computer science and the Director of Smart Systems Institute at the National University of Singapore (NUS). He is an IEEE Fellow. He received BSc in Computer Science & Mathematics from the University of British Columbia and PhD in computer science from Stanford University. At NUS, he co-founded NUS Advanced Robotics Center in 2013 and founded the AI Laboratory in 2019. His research spans robotics, AI, and computational structural biology. In recent years, he has been working on robot planning and learning under uncertainty for human-centered robots. His work won several international awards, including, most recently, Test of Time Award at Robotics: Science & Systems (RSS), 2021. He has chaired or co-chaired several major international robotics conferences, including CoRL 2021, ICRA 2016, RSS 2015, and WAFR 2004 and 2010.
University of Pennsylvania, United States
Talk title: Composable Representations for Lifelong Learning in Autonomous Systems
Bio: Eric Eaton is a research associate professor in the Department of Computer and Information Science at the University of Pennsylvania, and a member of the GRASP (General Robotics, Automation, Sensing, & Perception) lab. He also has a secondary appointment in biomedical and health informatics at Children’s Hospital of Philadelphia. Prior to joining Penn, he was a visiting assistant professor at Bryn Mawr College, a senior research scientist at Lockheed Martin Advanced Technology Laboratories, and part-time faculty at Swarthmore College. His primary research interests lie in the field of machine learning and interactive AI, with applications to service robotics and personalized medicine. In particular, his research focuses on developing versatile AI systems that can learn multiple tasks over a lifetime of experience in complex environments, transfer learned knowledge to rapidly acquire new abilities, and collaborate effectively with humans and other agents through interaction.
University of Bremen, Germany
Talk title: Transferability in Task-level Robot Control for Everyday Mobile Manipulation Actions
Bio: Gayane is a research associate at the Institute for Artificial Intelligence at the University of Bremen, lead by Michael Beetz. Her research focus is on task-level robot control and plan executives. She has more than 10 years of experience in mobile manipulation with physical robots such as the PR2, Tiago, HSR, Turtlebot, LWR, UR and a multitude of simulated robots. The main application areas are everyday actions in a household, mobile pick and place in retail and assembly. Prior to joining Michael Beetz's group in November 2013, she worked for one year as a researcher at Kastanienbaum GmbH, now Franka Emika, led by Sami Haddadin, in tight collaboration with the Robotics and Mechatronics Center of DLR. Gayane has a M.Sc. degree in Informatics with a major in AI and Robotics from the Technical University of Munich and a B.Eng. degree in Informatics with a major in Information Security from the State Engineering University of Armenia.
Karlsruhe Institute of Technology (KIT), Germany
Talk title: A Geometric Take on Embodiment Transfer
Bio: Noémie Jaquier is a postdoctoral researcher at the High Performance Humanoid Technologies Lab (H²T) at the Karlsruhe Institute of Technology (KIT), Germany. From
2016 to 2020, she was a PhD student affiliated to the Ecole Polytechnique Fédérale de Lausanne (EPFL) in Switzerland and working at the Idiap Research Institute. She did a six-months PhD sabbatical in the Bosch Center for Artificial Intelligence (BCAI) in Germany in 2019.
Her research brings a novel Riemannian perspective to robot learning, optimization, and control by leveraging Riemannian geometry as inductive bias and as a theory to provide sound theoretical guarantees. She investigates data-efficient methods that build on geometric spaces and exploit the geometric information naturally arising in robotic data. Her work focuses on skills learning via human demonstrations and adaptation techniques with geometry as a cornerstone.
Noémie Jaquier received the best presentation award at the 2019 Conference on Robot
Learning and her PhD thesis was nominated for the EPFL Asea Brown Boveri Ldt. Award.
- Michael C. Welle, KTH Royal Institute of Technology (KTH), Stockholm, Sweden
- Andrej Gams, Jozef Stefan Institute (JSI), Ljubljana, Slovenia
- Ahalya Prabhakar, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- Rainer Kartmann, Karlsruhe Institute of Technology (KIT), 7 Karlsruhe, Germany
- Daniel Leidner, German Aerospace Center (DLR), Weßling, Germany
- Danica Kragic, KTH Royal Institute of Technology (KTH), Stockholm, Sweden
If you have any questions please contact Michael Welle at the email: mwelle AT kth DOT se
Participants are required to abide by the IEEE RAS Code of Conduct