Call for Papers
5th Annual Conference on Robot Learning (CoRL2021)
November 8-11, 2021 | London, UK, and virtual
The Conference on Robot Learning (CoRL) is an annual international conference aiming to bring together the robotics and machine learning research communities. It focuses on the increasingly important role of learning in robotics and its interaction with other areas of robotics. While relatively young, CoRL grew rapidly and in 2020, attracted hundreds of the best researchers working in the intersection of robotics and machine learning.
The 5th Annual Conference on Robot Learning (CoRL 2021) will be held in London, UK, November 8-11, 2021, in a hybrid format. It will feature single-track presentations, keynotes, and tutorials. We look forward to your best work at CoRL in London and online.
CoRL 2021 invites contributions at the intersection of robotics and machine learning. CoRL is a selective, single-track international conference for robot learning research, spanning a broad range of topics in both theory and applications. Examples include:
Imitation learning and inverse reinforcement learning
Model-free learning for decision-making
Bio-inspired learning and control
Probabilistic learning and representation of uncertainty in robotics
Machine learning for system identification and control
State estimation, localization and mapping
Multimodal perception, sensor fusion, and computer vision
Learning for human-robot interaction and natural language instruction processing
Applications of robot learning in robot manipulation, navigation, driving, flight, and other areas of robotics
This year, we are soliciting two types of submissions: contributed papers, and blue-sky positional papers. All submissions will be evaluated according to their technical novelty, quality, potential impact, and clarity at the intersection at robotics and machine learning.
Submissions in the contributed paper category will need to demonstrate the relevance of proposed models, algorithms, data sets, and benchmarks to robotics. The authors are encouraged to report real-robot experiments or provide evidence of transfer to real robots for simulation experiments. The authors are also encouraged to submit code as supplementary materials.
The blue-sky papers should propose visionary ideas, paradigm shifts, thought provoking ideas, or novel point of view to either methods or problem domains at the intersection of robotics and machine learning.
All accepted submissions will be published in the JMLR Workshop & Conference Proceedings series. The accepted blue sky contributions will be presented at a blue-sky oral session, while the contributed papers will be presented either as posters, spotlights or long talks in the plenary session.
This year, to encourage high quality reviews and interaction between the authors and reviewers, CoRL will be using OpenReview. The anonymized submissions, reviews and rebuttals will be public throughout the submission process. The authors will have an opportunity to update the submissions during the rebuttal period. The accepted papers will be de-anonymized and remain public, while the rejected submissions will be made private.
Considerations for CoRL2021 and the Pandemic
The CoRL 2021 organising committee and board acknowledge the challenges in producing high-quality experimental results during the social distance policies implemented in different parts of the world. Like last year, at CoRL2020, authors affected by these policies are encouraged to submit a one-page supplemental material explaining the rationale why the evaluation methodology is sufficient, how it is deficient compared to the real-world experiments, and how their method will be experimentally validated with real data.
June 1, 2021 | Paper submission open
June 18 | Paper submission deadline; 23:59 Pacific Daylight Time (UTC-7)
June 25 | Supplemental materials due; 23:59 Pacific Daylight Time (UTC-7)
August 16 | Reviews available
August 23 | Rebuttals and revisions due
September 17 | Paper acceptance notification
November 1 | Camera ready papers due
November 8 - 11 | CoRL 2021
Submissions will be evaluated based on the significance and novelty of the results, either theoretical or empirical. Results will be judged on the degree to which they have been objectively established and/or their potential for scientific and technological impact, as well as their relevance to robotic learning. Authors will have an opportunity to submit a response to reviewers during the rebuttal period. Reviews and rebuttals of accepted papers will be made publicly available.
We take a broad view of robot learning. Papers with both experimental and theoretical results relevant to robot learning are welcome. Our intent is to make CoRL a selective top-tier conference on robotic learning.