2nd Workshop on Dexterous Manipulation: Design, Perception and Control

Introduction

This workshop aims to pioneer the exploration of learning-based strategies for achieving dexterous manipulation in robotics. Dexterous manipulation is among the most challenging problems in robotics, and this event seeks to provide insights and viewpoints for researchers and attendees on this subject. We will delve into current research and advancements in the hardware design of dexterous manipulators, generalizable manipulation learning approaches, and sensing technologies like tactile sensors.

Following our first dexterous manipulation workshop in RSS 2023. This workshop is Intended for a wide range of audiences, including researchers, engineers, and students with a strong foundation or interests in machine learning, computer vision, robotics, and related fields. The workshop promises a rich dialogue among leading experts from academic and industrial backgrounds. Accepted papers will have a chance to be presented in poster sessions and contributed talks. Through these events, participants will gain insights into the latest breakthroughs and collaborative opportunities, setting the stage for future innovations in robotic learning.

Invited Speakers

Seoul National University

MIT, Toyota Research Institute

He Wang

Peking University

(listed alphabetically)

Workshop Schedule

Time (GMT+1)	Event
08:45 - 08:50	Introduction and Opening Remark
08:50 - 09:15	Invited Talk and Mini-Discussion 1
09:15 - 09:40	Invited Talk and Mini-Discussion 2
09:40 - 10:00	Spotlight Talks 1
10:00 - 10:30	Coffee Break + Poster Session + Real Robot Demo Session
10:30 - 10:55	Invited Talk and Mini-Discussion 3
10:55 - 11:20	Invited Talk and Mini-Discussion 4
11:20 - 11:45	Invited Talk and Mini-Discussion 5
11:45 - 12:30	Tutorial
12:30 - 14:00	Lunch Break
14:00 - 14:25	Invited Talk and Mini-Discussion 6
14:25 - 14:50	Invited Talk and Mini-Discussion 7
14:50 - 15:15	Invited Talk and Mini-Discussion 8
15:15 - 15:30	Spotlight Talks 2
15:30 - 16:00	Coffee Break + Poster Session + Real Robot Demo Session
16:00 - 17:00	Panel Discussion
17:00 - 17:15	Closing Remark & Award Ceremony

Call for Papers

In this workshop, our goal is to bring together researchers from various fields of robotics, such as control, optimization, learning, planning, sensing, hardware, etc., who work on dexterous manipulation. We encourage researchers to submit work in the following areas, or related fields (the list is not exhaustive):

Learning for Dexterous Manipulation:

Can we expect a foundation policy for most daily dexterous manipulation tasks, or will each task require its own policy?
How can learning-based policies handle dynamic tasks that require high-frequency control?
How can we improve the generalization capability or the sample efficiency of policy learning in dexterous manipulation?

Planning and Optimization in Dexterous Manipulation:

How to scale up planning/optimization methods to high DoF systems?
How to leverage both planning/optimization methods and learning methods to get the best of both worlds?
How can we make dexterous hands compliant?

Simulation for contact-rich manipulation:

How to better model the contacts between the hand and object?
How can we speed up simulation in the presence of frequent contacts?

Hardware design for Dexterous Manipulation:

Is it possible to build a low-cost dexterous hand?
What kind of hand design can make manipulation easier?
What benefits do soft hands bring?
Novel mechanisms that improve robotic hand performance.

Data collection in Dexterous Manipulation:

How do we leverage human hand data in the wild to improve policy learning in dexterous manipulation?
How to develop low-cost, easy-to-use teleoperation systems for large-scale demonstration data?
How do we leverage planning methods to generate large-scale demonstration data in simulation?

Tactile Sensing for Manipulation:

What's the role of tactile sensing for dexterous manipulation?
How to use tactile data efficiently for control or policy learning?

Any additional related topics not already covered in the above list 😄

Submission Guidelines

Submission Portal: OpenReview
Paper Length: Submissions could be 4-page short papers, excluding references, acknowledgements, and appendices.
Format:
- The format requirement follows the RSS 2024 main conference. Paper template: LaTeX and Word
- Please include the references and supplementary materials in the same PDF as the main paper.
- The maximum file size for submissions is 100MB. Submissions that violate the RSS style (e.g., by decreasing margins or font sizes) or page limits may be rejected without further review. More information on format can be found here
Dual Submission for Other Conference:
- Papers to be submitted or in preparation for submission to other major venues (including CoRL 2024) in the field are allowed.
- We also welcome published works as long as explicitly stated at the time of submission.
Visibility: Submissions and reviews will not be public. Only accepted papers will be made public.