The role of uncertainty and how it is tackled in robotic grasping and manipulation

The aim is to bring together researchers with different approaches to grasping and manipulation, from the classical analytical/physics modeling based background and from the purely data-driven direction. Invited speakers come from diverse research backgrounds/communities (planning, control, learning, perception, AI, neuroscience). Invited speakers will get a 20 minute slot (with an additional 10 min for questions) to present their latest work relevant to the workshop theme, also including the limits and opportunities that they see with these approaches, raising discussion points. We will discuss open questions on the state of the art in grasp and manipulation planning and the proposed directions of new research efforts that will be raised during the talks by the speakers. We will organize an interactive poster session, allowing more contributors to present their work and have detailed discussions with the workshop attendees. Contributed papers will be published on the website and invited to present a poster. We hope to include many contributors and have fruitful discussions between invited speakers, active contributors, and the audience.

Program

9:00 - 9:05 Introduction

9:05 - 9:35 Matei Ciocarlie, Columbia University, USA (remote), Object recognition and manipulation with tactile fingers

9:35 - 10:05 Robert Platt, Northeastern University, USA (remote), Learning on the real robot using equivariant models

10:05 - 10:35 Chi Zu, Maebashi Institute of Technology, Japan, Releasing Manipulation with Learning Control

10:35 - 10:45 Break

10:45 - 11:15 Benjamin Rosman, University of the Witwatersrand, South Africa (remote), Multi-task manipulation through behaviour composition

11:15 - 11:45 Wenzhen Yuan, CMU, USA (remote), Attempt to model the uncertain world with tactile sensing: taking grasping as an example

11:45 - 12:00 Poster teasers

12:00 - 13:00 Lunch

13:00 - 13:30 Aldo Faisal, Imperial College London, UK (remote), What do we need to understand to go beyond robotics at the monkey level?

13:30 - 14:00 Kelsey Allen, DeepMind, UK, Robust modeling and manipulation using learned simulators

14:00 - 14:30 Ken Goldberg, UC Berkeley, USA, Grasping Uncertainty in Sensing, Control, and Physics

14:30 - 15:00 Panel

15:00 - 15:30 Poster Session

15:30 - 16:00 Maximo Roa, DLR, Germany (remote), Environment-aware manipulation strategies for a variable stiffness hand

16:00 - 16:30 Felix von Drigalski, Mujin, Japan, Uncertainty in Industrial Applications: Challenges and Approaches

16:30 - 17:00 Georgia Chalvatzaki, TU Darmstadt, Germany, Scaling learning of manipulation skills with models, priors, and structure

17:00 Closing