CALL FOR PAPERS
Best Poster Award
An Nvidia RTX 3090 GPU will be awarded to the best poster presentation. The organizing committee will decide on the award on the basis of scientific rigor, novelty, and quality of presentation. The best poster award is made possible thanks to the generous support of Honda Research Institute, USA in an effort to promote fundamental research in the emerging areas of understanding and reproducing intrinsically-motivated behavior in robotics applications.
Workshop Goal
In this workshop, we aim to bring together researchers, students, and practitioners in robotics and other sciences to discuss how to build curious robots and agents. The workshop should appeal to both researchers developing tools to recreate aspects of intelligent agents, e.g., reinforcement learning, active learning, deep learning, symbolic reasoning, computer vision; as well as researchers in trying to understand intelligent agents, e.g., in biology, psychology, human-robot interaction. As an outcome of this workshop, we expect the participating researchers to identify and address important challenges, techniques, and benchmarks that are needed to better understand, model, synthesize and analyze curiosity-driven behavior in robots. Specifically, questionnaires will be provided to attendees in order to chart the current research activities in the field. The results of the questionnaire will be used to write a follow-up report, indicating current practices and applications as well as future challenges and opportunities. Our hope is that the resulting report could act as a manifesto for curiosity-driven learning, which can help students and researchers become familiar with the field and identify research opportunities. We also plan to award a workshop Best Poster award to encourage and recognize outstanding research and presentation efforts.
Relevant topic areas include (but are not limited to):
Developmental robotics
Efficient data collection criteria
Attention systems
Metrics for identifying stimuli-of-interest
Curiosity-driven learning
Self-supervised learning
Symbolic reasoning about novel objects
Open-ended approaches to robot programming
Curiosity for perception and attention
Formalizing the curiosity and the “hunger for knowledge”
Learning based on prediction errors
Cognitive origins of curiosity
Information-theoretic reward functions
Balancing intrinsic and extrinsic rewards
Goal and sub-goal generation processes
Reinforcement learning with intrinsic rewards
Curious behavior in social settings and human-robot interaction
Important Dates
4/5/2021 - Deadline for paper submissions
4/15/2021 - Notification
6/4/2021 - Workshop
Workshop Format
A key goal of the workshop is to identify modern techniques for open-ended and curiosity-based adaptation, learning, and planning by presenting novel technical contributions. Surveys of recent advances in the field are also welcome. In this manner, the current state-of-the-art can be assessed. Given these insights, we want to discuss important next steps and open problems in the field.
Submission
Prospective participants are invited to submit short papers of up to 4 pages + references. The paper should be submitted in the format of IEEE/ICRA formatting guidelines. We aim to publish all papers on our website and as an Arxiv collection to enable easy access to the information. Depending on the overall quality of the contributions, we might consider proposing a journal Special Issue in the near future. All papers for the Workshop must be submitted in PDF format by email to the address: curiosityworkshop.icra21@gmail.com.
Note: Submission is not anonymous