Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TrifingerDownload PDF

12 Oct 2021 (modified: 08 Sept 2024)Deep RL Workshop NeurIPS 2021Readers: Everyone
Abstract: 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}
Supplementary Material: zip
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/transferring-dexterous-manipulation-from-gpu/code)
0 Replies

Loading