Equivariant Robotics: The Role of Symmetry Across Perception, Estimation, and Control (IROS 2024 Workshop)

Workshop at IROS 2024, Abu Dhabi, United Arab Emirates

Monday, October 14, 2024 (afternoon)

WORKSHOP WEBSITE: https://equirob2024.github.io/

Abstract

Towards the end of robotic systems capable of ubiquitous, persistent deployment in the wild, a growing trend has emerged across the many subdisciplines of our field. Namely, researchers in diverse areas have exploited the inherent symmetries present in robotic systems and their environment to achieve drastic improvements in performance, efficiency, and robustness. Equivariant architectures for data-driven perception have demonstrated impressive generalization and sample efficiency, all the while reducing model complexity and guaranteeing by design that extraneous transformations will not degrade their predictions. Meanwhile, a symmetry-aware approach to state estimation has yielded improved convergence properties, providing both formal certificates and astonishing empirical accuracy. Moreover, as the complexity of both individual agents and multiagent teams has grown, the exploitation of symmetry in control has tamed unwieldy high-dimensional models, sated the appetite of data-hungry methods like reinforcement learning, and aided in the decentralized coordination of large robot swarms. This workshop brings together prominent experts and early-career researchers, working across a wide range of problems, applications, and methodologies in robotics, to share their perspectives on the multifaceted role of equivariance in autonomous systems. Ultimately, this cross-pollination of traditionally distinct research communities will identify new avenues of investigation to leverage these cross-cutting concepts, in pursuit of intelligent robotic systems prepared to tackle society’s greatest challenges and play an active role in our daily lives.

Submission Guidelines

• We welcome the contribution of short papers / extended abstracts of 2-4 pages in 2-column IEEE conference format (including all figures and appendices but excluding references), to give a chance to authors of already published or ongoing works to present their work at the workshop.
• The workshop is non-archival (i.e. contribution should not prohibit submission to other venues), and preliminary or late-breaking results are welcome. Already-published works should mention where the work has previously been published. Contributions will be reviewed (single blind) for basic quality and relevance to the workshop.
• Accepted abstracts will be available on the workshop website and presented in poster format during the workshop.

Important Dates (Anywhere on Earth)

• Paper Submission Deadline: September 16, 2024
• Review Deadline: September 23, 2024
• Acceptance Notification Date: August 30, 2024
• Workshop: October 14, 2024 

Organizing Committees

• Dr. Vijay Kumar, University of Pennsylvania
• Dr. Kostas Daniilidis, University of Pennsylvania
• Dr. Christine Allen-Blanchette, Princeton University
• Dr. Pieter van Goor, University of Twente
• Dr. Rui (Ray) Wang, Massachusetts Institute of Technology
• Jake Welde, University of Pennsylvania
• Evangelos Chatzipantazis, University of Pennsylvania
• Yinshuang Xu, University of Pennsylvania

Contact

For more information and submission details, please visit our workshop website. For questions about workshop contributions, please contact jwelde@seas.upenn.edu or rayruw@mit.edu.