Closing the Reality Gap in Sim2real Transfer for Robotic Manipulation


Organizers: Sebastian Höfer, Ankur Handa, Kamal Kuzhinjedathu, Marc Toussaint, Dieter Fox

Website: http://sim2real.github.io

Physical simulation is an important tool for robotic manipulation. Although simulation has been well-established for robotics education and integrated robot software testing, there is an ongoing debate about transferring manipulation capabilities learned in simulation to reality, a concept termed sim2real transfer.

Simulation draws its appeal from the fact that it is much faster, cheaper, safer and more informative (e.g., auto-generated labels) than real-world experimentation. Recent advances have shown how to take advantage of simulation and address the sim2real transfer for tasks such as object detection, autonomous driving and grasp point detection. However, sim2real transfer for general manipulation skills still raises significant challenges, such as contact simulation, simulation of closed-loop manipulation, and sensor fidelity.

In this workshop, we invite well-known researchers to share new ideas across this multidisciplinary field. We will shed light on questions such as: What is the potential impact of sim2real transfer for robotic manipulation? What methods exist and work best in the context of manipulation? To what extent can sim2real transfer reduce or avoid training on real robots altogether?