Connectionists: CFP: IROS 2022 Workshop on Life-long Learning of High-level Cognitive and Reasoning Skills

[Alper Ahmetoglu]

Call for Papers:

IROS 2022 Workshop on Life-long Learning of High-level Cognitive and Reasoning Skills
--------------------------------------------------
A Full-day Hybrid Event
October 23, 2022
https://lifelongrobotics.github.io


Important dates

- Early Paper Submission Deadline (for early registration): Aug 19, 2022
- Early Acceptance Notification (for early registration): Aug 22, 2022
- Paper Submission Deadline: Aug 29, 2022
- Acceptance Notification: Sep 2, 2022
- Workshop date: Oct 23, 2022


Invited Speakers:

- Eric Eaton, University of Pennsylvania
- George Konidaris, Brown University
- Jeff Clune, OpenAI, University of British Columbia
- Jun Tani, Okinawa Institute of Science and Technology
- Minoru Asada, Osaka University
- Stefanie Tellex, Brown University
- Tamim Asfour, Karlsruhe Institute of Technology
- Yukie Nagai, University of Tokyo


Summary:

This workshop will focus on how to create open-ended or life-long learning systems that will allow for a robot to autonomously explore its environment and learn ever-growing representations for perception and actuation. This is an underexplored area in robotics and artificial intelligence research that can contribute to the development of generally capable agents. We will discuss the necessary elements (e.g., methods, environments, datasets, embodiments) for a life-long learning setting. We will encourage participants to take part in discussions with the following points:

- How to adopt the current open-ended methods for life-long robot learning
- Are the current machine learning methods sufficient for life-long learning?
- How to combine the current toolset of ML for life-long learning
- How to design end-to-end systems for life-long learning
- What are the necessary components for a life-long learning system? Which parts should we take for granted?
- How to design appropriate environments both in simulation and real-world that support life-long learning


Submissions:

We accept regular papers (up to 8 pages of unpublished work) and extended abstracts (up to 4 pages of novel work or from a recently published paper) in standard IEEE format, excluding unlimited pages for references. The review process will be single-blind. 10 minutes will be allocated for each regular paper, and 2 minutes for each extended abstract. Papers will be submitted through CMT (https://cmt3.research.microsoft.com/LLR2022).

The topics that are indicative but by no means exhaustive are as follows:

- Open-ended learning, life-long learning
- Continual learning, transfer learning, catastrophic forgetting
- Multi-task learning, meta-learning
- Modularity
- Computational approaches to the study of development and learning
- Machine learning techniques for robot learning and development
- Cognitive and perceptual development
- Concept formation and symbol grounding
- Imitation learning
- Embodied cognition
- Affordance learning
- Interactive learning
- Exploration and learning in animals and robots
- Curiosity and intrinsic motivation
- Skill and language acquisition
- Human assisted learning and scaffolding
- Human-robot interaction


Organizing Committee:

Alper Ahmetoglu (contact person), Bogazici University (Turkey), ahmetoglu.alper at gmail.com
M. Tuluhan Akbulut (contact person), Brown University, USA, tuluhan_akbulut at brown.edu
Erhan Oztop, Ozyegin University / Osaka University (Turkey/Japan)
Justus Piater, University of Innsbruck, (Austria)
Tadahiro Taniguchi, Ritsumeikan University, (Japan)
Emre Ugur, Bogazici University, (Turkey)