Getting the Ball Rolling: Learning a Dexterous Policy for a Biomimetic Tendon-Driven Hand

Yasunori Toshimitsu, Benedek Forrai, Barnabas Gavin Cangan, Ulrich Steger, Manuel Knecht, Stefan Weirich, Robert K. Katzschmann
This work introduces the biomimetic tendon-driven Faive Hand and its system architecture, which uses tendon-driven rolling contact joints to achieve a 3D printable, robust high-DoF hand design. We model each element of the hand and integrate it into a GPU simulation environment to train a policy with RL, and achieve zero-shot transfer of a dexterous in-hand sphere rotation skill to the physical robot hand.
project website: srl-ethz.github.io/get-ball-r...
arxiv: arxiv.org/abs/2308.02453

[@user-fx3uw1sf8c]

Outstanding work! The flexibility is the same as that of a human hand!

[@FlyingPoptart101]

Looks super promising! Nicely done!

[@AI_Overlord]

Awesome work

[@buffonator7858]

cool :)

[@christopherd.winnan8701]

Do you source all of your components locally?
What do you estimate is the cost breakdown for your latest iteration?

[@HolahkuTaigiTWFormosanDiplomat]

０．０