Timezone: »

 
Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World Trifinger
Arthur Allshire · Mayank Mittal · Varun Lodaya · Viktor Makoviychuk · Denys Makoviichuk · Felix Widmaier · Manuel Wuethrich · Stefan Bauer · Ankur Handa · Animesh Garg

@
in Deep Reinforcement Learning »
Event URL: https://openreview.net/forum?id=wtgr3SDx25c »

We present a system for learning a challenging dexterous manipulation task involving moving a cube to an arbitrary 6-DoF pose with only 3-fingers trained with NVIDIA's IsaacGym simulator. We show empirical benefits, both in simulation and sim-to-real transfer, of using keypoints as opposed to position+quaternion representations for the object pose in 6-DoF for policy observations and in reward calculation to train a model-free reinforcement learning agent. By utilizing domain randomization strategies along with the keypoint representation of the pose of the manipulated object, we achieve a high success rate of 83\% on a remote TriFinger system maintained by the organizers of the Real Robot Challenge. With the aim of assisting further research in learning in-hand manipulation, we make the codebase of our system, along with trained checkpoints that come with billions of steps of experience available, at \url{https://sites.google.com/view/s2r2}

Author Information

Arthur Allshire (University of Toronto)
Mayank Mittal (ETH Zurich)
Varun Lodaya (University of Toronto)
Viktor Makoviychuk (NVIDIA)
Denys Makoviichuk (Snap Inc)
Felix Widmaier (MPI for Intelligent Systems, Tübingen)
Manuel Wuethrich (Max Planck Institute for Intelligent Systems)
Stefan Bauer (Max Planck institute)
Ankur Handa (Imperial College London)
Animesh Garg (University of Toronto, Nvidia, Vector Institute)

I am a Assistant Professor of Computer Science at University of Toronto and a Faculty Member at the Vector Institute. I work on machine learning for perception and control in robotics.

More from the Same Authors