Call for IROS 2024 Workshop Papers

Brain over Brawn (BoB): Workshop on Label Efficient Learning Paradigms for Autonomy at Scale Webpage: https://bob-workshop.github.io/

Recent advances in autonomous mobile robotics have enabled their deployment in a wide range of structured environments where an abundance of manually labeled data is readily available to train existing deep learning algorithms. However, manual data annotation is financially prohibitive at large scales and also hinders the deployment of such algorithms in complex unstructured environments where labeled data is not available.

The goal of this workshop is to bring into spotlight different robotics paradigms that can be leveraged to train models with limited supervision. Specifically, this workshop shall explore various works in the fields of self-supervised learning, zero-/few-shot/in-context learning, and transfer learning among others. Furthermore, this workshop also intends to investigate the use of rich feature representations generated by emergent vision foundation models such as DINO, CLIP, SAM, etc., to reduce or remove manual data annotation in existing training protocols. This workshop will specifically aim to address the following core questions:

1. What are the real-world limitations of largely relying on labeled data?
2. What are the challenges of existing learning with limited supervision paradigms that prevent their widespread adoption in autonomous mobile robotics?
3. Which research directions in computer vision and deep learning are beneficial for robotics, and which directions need significant reformulation?
4. How can the robotics community better utilize various breakthroughs in machine learning and deep learning?

To this end, we invite both early-career as well as experienced researchers to submit high quality research works as a short paper (max. 4 pages excluding references) focusing on, but not limited to, the following topics:

1. Self-Supervised, Weakly-Supervised and Unsupervised Learning
2. Zero- and K-Shot Learning
3. Leveraging Vision Foundation Models for Data-Efficient Learning
4. Transfer Learning
5. Knowledge Distillation (Cross-Modal, Cross-Domain, Teacher-Students, etc.)
6. Domain Adaptation
7. Open World Learning

We encourage submissions of works-in-progress as well as recent works that are currently under review or have already been accepted elsewhere. Accepted papers will be made non-archival public through our workshop website, and will be presented as posters during IROS2024 in Abu Dhabi, UAE, with a selected few in the spotlight lightning session.

The three best posters during the workshop will be awarded with a physical GPU, sponsored by NVIDIA.

Please find more information about submitting a contribution to our workshop on the workshop webpage: https://bob-workshop.github.io/

Timeline:

• Submission deadline: 31 Aug 2024
• Notification: 15 Sep 2024
• Workshop date: 14 Oct 2024

Organizing committee:
Nicholas Autio Mitchell (NVIDIA)
Andrei Bursuc (Valeo)
Daniele Cattaneo (University of Freiburg)
Hazel Doughty (Leiden University)
Nikhil Gosala (University of Freiburg)
Kürsat Petek (University of Freiburg)
Katie Skinner (University of Michigan)
Andreea Tulbure (ETH Zürich)
Abhinav Valada (University of Freiburg)