3rd Workshop on Dexterous Manipulation: Learning and Control with Diverse Data

Introduction

Dexterous manipulation is one of the hardest problems in robotics. Despite decades of research, robots still struggle with tasks that human hands perform effortlessly. Solving this challenge requires breakthroughs in multiple fields—mechanical design, motion planning, control, and machine learning. This workshop brings together experts across these disciplines to explore what’s missing and what’s next.

We invite researchers working on dexterous robotic manipulation, manipulator design, tactile sensing, visual perception, and human hand understanding from video. Attendees will have the opportunity to participate in discussions, present posters, and give contributed talks. Panelists and speakers, drawn from these research communities, include leading experts from both academia and industry.

Invited Speakers

Ankur Handa

NVIDIA

Wanxin Jin

Arizona State University

(listed alphabetically)

Workshop Schedule

Time (UTC -8)	Event
08:55 - 09:00	Introduction and Opening Remark
09:00 - 09:30	Invited Talk (Karen Liu)
09:30 - 10:00	Invited Talk (Sudharshan Suresh)
10:00 - 10:30	Invited Talk (Jessica Yin)
10:30 - 11:00	Spotlight Session 1: ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomy HuDOR: Bridging the Human to Robot Dexterity Gap through Object-Oriented Rewards RUKA: Rethinking the Design of Humanoid Hands with Learning DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation Scaffolding Dexterous Manipulation with Vision-Language Models
11:00 - 11:30	Poster / Demo Session
11:30 - 12:00	Invited Talk (Ankur Handa)
14:00 - 14:30	Invited Talk (Russ Tedrake)
14:30 - 15:00	Invited Talk (Wanxin Jin)
15:00 - 15:30	Invited Talk (Huazhe Xu)
15:30 - 16:00	Spotlight Session 2 DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies Reinforcement Learning for Ambidextrous Bimanual Manipulation via Morphological Symmetry Learning Particle-Based World Model from Human for Robot Dexterous Manipulation DEXOS: Hand Exoskeleton System for Teaching Robot Dexterous Manipulation In-The-Wild Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation ImVR: Immersive VR Teleoperation System for General Purpose Dexterous Contact-Rich Manipulation via the Contact Trust Region
16:00 - 16:30	Poster / Demo Session
16:30 - 17:25	Panel Discussion
17:25 - 17:30	Closing Remark & Award Ceremony

Accepted Papers

Call for Papers/Demos

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.

Each accepted short paper will be eligible for a poster presentation. Selected papers will also have the opportunity to give a short spotlight talk. Note: Both poster and spotlight presentations must be given in person.

We are particularly excited to offer a platform for showcasing real-world robotic systems. Even without a formal paper, we encourage submissions of videos demonstrating your robots in action. For those able to attend in person, there will be opportunities to showcase your robots live at the workshop! We encourage researchers to submit work in the following areas (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 for Paper and Demo: OpenReview
Paper Submission Guideline:

Paper Length: Submissions could be 4-page short papers, excluding references, acknowledgements, and appendices.
Format:
- The format requirement follows the RSS 2025 main conference. Paper template: LaTeX and Word
- Please include the references and appendix in the same PDF as the main paper and submit optional videos as zip file in supplementary.
- The maximum file size is 100MB. 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.

Demo Submission Guideline:

Summary Document: Please upload a summary document as a pdf. There is no page and format requirement for this pdf.
Demo Video: Please upload video demos as a single zip under the supplementary material field in OpenReview.