English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a system for learning a challenging dexterous manipulation taskinvolving moving a cube to an arbitrary 6-DoF pose with only 3-fingers trainedwith NVIDIA's IsaacGym simulator. We show empirical benefits, both insimulation and sim-to-real transfer, of using keypoints as opposed toposition+quaternion representations for the object pose in 6-DoF for policyobservations and in reward calculation to train a model-free reinforcementlearning agent. By utilizing domain randomization strategies along with thekeypoint representation of the pose of the manipulated object, we achieve ahigh success rate of 83% on a remote TriFinger system maintained by theorganizers of the Real Robot Challenge. With the aim of assisting furtherresearch in learning in-hand manipulation, we make the codebase of our system,along with trained checkpoints that come with billions of steps of experienceavailable, at https://s2r2-ig.github.io

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