Interdisciplinary Exploration of Generalizable Manipulation Policy Learning:
Paradigms and Debates

Introduction

Acquiring generalizable manipulation policies through data-driven, learning-based approaches is a fundamental problem in robotics. Despite advancements in this field, there are many unresolved questions that have resulted in a variety of, sometimes conflicting, paradigms. This workshop is designed to bring together researchers and practitioners from a diverse range of disciplines, robotics, vision, graphics, machine learning to share their insights and perspectives, with the goal of advancing interdisciplinary collaboration and promoting the development of innovative, new paradigms in generalizable manipulation policy learning. More specifically, we aim to discuss questions that are important for the future development of this field, including but not limited to:

• What action space is suitable for generalizable manipulation policy learning?
• What are the criteria for simulation in the context of generalizable manipulation policy learning?
• How realistic should the simulation be for sim-to-real?
• What data collection approaches are suitable for generalizable manipulation policy learning?
• What visual observation representation is suitable for generalizable manipulation policy learning?

Our targeted participants are researchers and engineers who are interested in the field of robotics and embodied AI, and have a background in machine learning, computer vision, computer graphics, natural language processing or related areas. The workshop will also be of interest to practitioners in industry who are working on the development of intelligent robots and other related systems.

In affiliation to this workshop, we are also organizing the ManiSkill2 Challenge, which is a large-scale robotic manipulation challenge that seeks to benchmark generalizable robotic agents that can interact with the 3D world. We will announce winners and host winner presentations in this workshop.

Call for Papers

We encourage participants to submit their research in the form of a single PDF. Submissions may be up to 4 pages in length, including figures, excluding references and any supplementary material. Please use the RSS conference template. Accepted papers will be presented in a poster session and selected papers as spotlight talks. All submitted contributions will go through a double blind review process. The contributed papers will be made available on the workshop's website. However, this does not constitute an archival publication and no formal workshop proceedings will be made available, meaning contributors are free to publish their work in archival journals or conferences.

Paper topics

A non-exhaustive list of relevant topics:

• Computer vision for robot manipulation
  • 3D-based approaches tailored for reinforcement/imitation learning
  • Affordance prediction
  • Pre-trained models
  • Perception from Interaction
• Reinforcement/imitation learning
  • Large-scale RL/IL training
  • Multi-task learning
  • Few-shot imitation learning
• Efficient and affordable data collection
• Data augmentation techniques for generalizable policy learning
• Foundation models for generalizable policy learning
• Hardware design
• Other topics about generalizable manipulation policy learning

We invite submissions that address the topic of generalizable manipulation policy learning. If you have any doubts about whether your submission aligns with the workshop's focus, please feel free to reach out to us for clarification.

Submission Website:

https://cmt3.research.microsoft.com/rssgmpl2023

Important Dates:

• June 12, 2023 Submission Deadline (11:59pm PT)
• June 16, 2023 Acceptance Notification
• June 23, 2023 Camera Ready Deadline
• July 10, 2023 Workshop