Equivariant Robotics:

The Role of Symmetry Across Perception, Estimation, and Control

Workshop at IROS 2024

Abu Dhabi, United Arab Emirates
Monday, October 14, 2024 (14:00 - 18:00)

Main Workshop: Room 15 (located inside "Conference Hall A")

and on Zoom (please join here)

Poster Session: Boards 7.1 - 7.8 (located inside "Hall 4")

(see map below)

Background. Towards the end of robotic systems capable of ubiquitous, persistent deployment in the wild, researchers across diverse subdisciplines of our field have exploited the inherent symmetries present in robotic systems and their environment to achieve drastic improvements in performance, efficiency, and robustness. For example:
  • 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.
  • A symmetry-aware approach to the filter design has yielded improved convergence properties in state estimation, providing both formal certificates and astonishing empirical accuracy in field deployments.
  • 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.
Workshop Goals and Overview. Informed by this promising and recurring trend, this workshop brings together a technically diverse cohort of experts and early-career researchers working across a wide range of problems, applications, and methodologies to share their perspectives on the multifaceted role of equivariance in autonomous systems. This cross-pollination of traditionally distinct research communities will:
  • introduce new members of the broader robotics community to symmetry-informed methods,
  • identify new opportunities to leverage these cross-cutting concepts and apply geometric expertise in new areas,
  • align with the IROS 2024 theme "Robotics for Sustainable Development" by reducing the environmental impact of autonomous systems via reduced model complexity, more efficient algorithms, and greater reliability, and
  • ultimately bring us closer to the availability of ubiquitous, intelligent robotic systems prepared to tackle society's greatest challenges and play an active role in our daily lives.
Please join us at IROS 2024 to explore these exciting developments!
Workshop Recordings
The YouTube playlist below includes recordings of all the keynote talks and the panel discussion.

Keynote Speakers
Amanda Prorok
Professor of Collective
Intelligence and Robotics
University of Cambridge
Robert Mahony
Professor of Engineering
Australian National University
Elise van der Pol
Senior Researcher
Microsoft Research Amsterdam
Robin Walters
Assistant Professor
of Computer Science
Northeastern University
Chien Erh (Cynthia) Lin
PhD Candidate
in Robotics
University of Michigan
Tzu-Yuan (Justin) Lin
PhD Candidate
in Robotics
University of Michigan
Schedule
All times on the schedule are Abu Dhabi local time (UTC+4).
For virtual attendance, please join us on Zoom.


The main workshop is located in Room 15, inside "Conference Hall A". The poster session is located inside "Hall 4" (the main workshop room). The map shows the most direct route in between (go upstairs, because exhibition hall is closed off).
Click the title of each talk below to access the recording!
Opening Remarks 14:00 - 14:10
Keynote: Chien Erh Lin and Tzu-Yuan Lin (in-person), on behalf of Maani Ghaffari 14:10 - 14:40
"Computational Symmetry and Learning for Robotics"
Forthcoming mobile robots require efficient generalizable algorithms to operate in challenging and unknown environments without human intervention while collaborating with humans. Today, despite the rapid progress in robotics and autonomy, no robot can deliver human-level performance in everyday tasks and missions such as search and rescue, exploration, and environmental monitoring and conservation. In this talk, I will put forward a vision for enabling efficiency and generalization requirements of real-world robotics via computational symmetry and learning. I will walk you through structures that arise from combining symmetry, geometry, and learning in various foundational problems in robotics and showcase their performance in experiments ranging from perception to control. In the end, I will share my thoughts on promising future directions and opportunities based on lessons learned on the field and campus.
Keynote: Robert Mahony (in-person) 14:40 - 15:10
"Galilean Space-Time in Robotics"
Rigid-body or pose symmetry lies at the foundation of the spatial geometry that underlies most of classical robotics. Recent work has shown that there is an "extended pose" symmetry that has been demonstrated to provide significant benefits in inertial navigation problems. In this talk I show that the extended pose symmetry is itself a specialisation of the natural symmetry associated with Galilean space-time and show how this formalisation leads to a powerful modelling framework for dynamic robotic systems.
Keynote: Robin Walters (virtual) 15:10 - 15:40
"Pushing the Limits of Equivariant Neural Networks"
Incorporating symmetry constraints into neural networks has resulted in models called equivariant neural networks (ENNs) which are more sample efficient and generalize better. This has proved to be a crucial benefit in domains such as robotic manipulation where on-robot reinforcement learning can be very time consuming and expert demonstrations are expensive. I will discuss several applications of ENNs such as vehicle trajectory prediction, fluid dynamics modeling, robotic manipulation, world modeling, and differentiable planning. However, there are also limits to the effectiveness of current ENNs. In many applications the observation type makes the symmetry in the domain hard to exploit. I will discuss solutions to this problem such as relaxed equivariance and models which take advantage of latent symmetry.
Poster Session + Coffee 15:40 - 16:20
This session will take place in Hall 4 at poster boards 7.1 - 7.8.
Keynote: Elise van der Pol (virtual) 16:20 - 16:50
"Symmetry & Structure in RL - State of the art, challenges, and future directions"
In this talk, I will give an overview of the state of the field of symmetries and structure in reinforcement learning. I'll discuss the why and how of symmetric RL, standing challenges in the field, what work has been done to address those challenges and identify key directions for future work.
Keynote: Amanda Prorok (virtual) 16:50 - 17:20
"Leveraging Symmetry for Learning Robot Interaction Models"
Machine learning has revolutionized the way in which we address large-scale orchestration of robot systems by enabling us to automatically synthesize robot policies from high-level objectives. Yet, multi-robot and multi-agent learning paradigms often suffer from computational intractability and sample inefficiency. In this presentation, I describe how we can leverage symmetries present during the robots' operational regimes to alleviate the computational burden during learning. I present a case-study of close-proximity flight with multiple quadrotors, and show how our models are able to capture these complex physical interactions in real-world applications.
Panel Discussion 17:20 - 17:50
Our keynote speakers will join us once more to discuss key takeaways and open questions.
Award Session + Closing Remarks 17:50 - 18:00
Call for Papers
We invite contributions exploring the role of symmetry across diverse problems in robotics and autonomy, including (but not limited to):
  • Geometric mechanics and symmetry in locomotion planning and control
  • Conservation laws and motion planning for nonholonomic vehicles
  • Formal certificates or experimental verification of equivariant filters
  • Approximately equivariant architectures for working with broken symmetry
  • Feedback linearization and differential flatness in the presence of symmetry
  • Model order reduction via symmetry
  • Equivariant neural representations
  • Symmetry as a prior in physics-informed machine learning
  • Discrete symmetries in biological and robotic systems
  • Equivariant deep learning
  • Symmetries in geometric perception (3D reconstruction, registration, 3D object detection)
  • Symmetries with proprioceptive sensors (IMU integration etc.)
  • Symmetry-informed optimizers
  • Sample complexity and robustness benefits in equivariant machine learning
  • Symmetries in multiagent systems (flocking, tracking, coordination)
  • Graph neural networks for decentralized multiagent autonomy

Author 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.
  • Extended abstracts should be submitted via EasyChair: https://easychair.org/conferences/?conf=symrob2024

Important Dates

All deadlines are AoE (Anywhere on Earth).
  • Paper Submission: August 16, 2024   September 16, 2024
  • Acceptance Notification: August 30, 2024   September 23, 2024
  • Camera-Ready Submission: October 11, 2024
  • Workshop: October 14, 2024

Best Poster Award

To encourage contributions, we will present a Best Poster Award (to be judged by invited speakers and perhaps other senior researchers), with a monetary prize funded by the IEEE RAS TC on "Computer & Robot Vision".
Accepted Papers
Accepted extended abstracts are found below! Authors will present their work during the poster session. A digital poster is also found below for those authors who were unable to attend in person.
Organizers
Jake Welde
University of Pennsylvania
Pieter van Goor
University of Twente
Yinshuang Xu
University of Pennsylvania
Rui (Ray) Wang
GE Healthcare
Evangelos Chatzipantazis
University of Pennsylvania
Christine Allen-Blanchette
Princeton University
Kostas Daniilidis
University of Pennsylvania
Vijay Kumar
University of Pennsylvania
For any questions or concerns, please feel free to reach out to jwelde@seas.upenn.edu or any of the organizers.
Acknowledgements
The organizers gratefully acknowledge the financial support provided for the workshop by the IEEE RAS TC on "Computer & Robot Vision". We also appreciate the endorsement of the workshop by the IEEE RAS TC's on "Multi-Robot Systems", "Robot Learning", and "Algorithms for Planning and Control of Robot Motion".

Thank you everyone for your contributions to the workshop!