Learning for Soft Robots:
Hard Challenges for Soft Systems
Conference on Robot Learning 2023 - Workshop
November 6, 2023, Atlanta, GA, USA (hybrid)
Location: Hub 2
Posters: Muse 1
Email: l4sr-workshop@googlegroups.comÂ
Zoom: Link
Abstract
Recent advancements in soft robots have introduced a paradigm shift in the field of robotics by leveraging compliant materials and flexible structures to enable versatile and adaptable machines. However, the inherent morphological complexity and compliance of soft robots present unique challenges for traditional sensing and control techniques. To maximize the utility of soft robots, there is a pressing need to develop intelligent learning algorithms that can capture and exploit the rich dynamics and compliance of these systems. By incorporating learning algorithms, soft robots may acquire new skills, adapt to varying environments, and interact seamlessly with humans and the world around them.
This hybrid workshop aims to bring together researchers and practitioners from diverse disciplines to explore the growing intersection of soft robotics and machine learning. The workshop will provide a platform to discuss recent advancements, share insights, and foster collaboration in the area of learning for soft robots. Additionally, we will discuss the broader impact potential of these soft robotic systems in fostering accessible robotics education and sustainability.Â
ScheduleÂ
8:25 - 9:00: Introduction
8:25 - 8:30: Opening Remarks
8:30 - 9:00: Edward Adelson
9:00 - 9:30: Josie Hughes
9:30 - 10:00: Robert Katzschmann
10:00 - 10:30: Oliver Brock
10:30 - 11:00: Coffee Break
11:00 - 11:30: Zeynep Temel
11:30 - 12:00: Panel discussion 1
Panelists: Edward Adelson, Josie Hughes, Robert Katzschmann, Oliver Brock, Zeynep Temel
12:00 - 12:30: Poster Session
12:30 - 1:30: Lunch Break
1:30 - 2:00: Thomas Thuruthel
2:00 - 2:30: Kostas Bekris
2:30 - 3:15: Spotlight Talks
3:15 - 3:30: Coffee Break
3:45 - 4:15: Ram Vasudevan
4:15 - 4:45: Chuang Gan
4:45 - 5:15 [30 min]: Panel discussion 2
Panelists: Thomas Thuruthel, Kostas Bekris, Ram Vasudevan, Chuang Gan
5:15 - 5:20 [5 min]: Closing remarks
Accepted Papers
COMPOSER: Scalable and Robust Modular Policies for Snake Robots
Visual Servoing for Pose Control of Hybrid Continuum Manipulator in an Unstructured Environment
DeRi-Bot: Learning to Collaboratively Manipulate Rigid Objects via Deformable Objects
Thin-Shell Object Manipulations With Differentiable Physics Simulations
Plan-Guided Reinforcement Learning for Whole-Body Manipulation
Differentiable Fluid-Structure Interaction Solver for Free-Floating Robots
Multimodal Learning of Soft Robot Dynamics using Differentiable Filters
Object Recognition and Force Estimation with the GelSight Baby Fin Ray
Call for Papers
Important Dates:Â
Submission Deadline: October 09, 2023 23:59 GMT
Decisions: October 16, 2023
Camera Ready: November 5, 2023
Workshop: November 6, 2023
Topics of Interest
We invite researchers working on any intersection of learning and soft robotics to share with our diverse community their projects. Â
Topics of interest include but are not limited to:Â
Learning Soft Body Dynamics
Soft Sensors and Embodied Perception
Soft Robot Control and Applied Reinforcement Learning
Soft Robot Manipulation
Adaptive and Resilient Soft Robots
Human-Robot Interaction with Soft Robots
State Estimation of Soft Robots
Soft Simulation and Virtual Environments
Smart Wearables and Soft Haptic Devices
Submission Info
We solicit up to 4 page (excluding references) submissions conforming to the CoRL 2023 Template. The review process will be double-blind and will use OpenReview.
Submissions can include: late-breaking results, material under review, archived, or previously accepted work (please make a note of this in the submission).
Please note the accepted contributions will be presented in an interactive poster format (non-archival). A small set of these will be featured as spotlight talks. The accepted contributions and posters will be posted on the workshop website upon author approval.
We do encourage participants to bring their robots for demonstration purposes during the poster sessions and spotlight talks. *Details TBD*