LEAP Hand:

Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning

Kenneth Shaw         Ananye Agrawal         Deepak Pathak
Carnegie Mellon University
RSS 2023


Dexterous manipulation has been a long-standing challenge in robotics. While machine learning techniques have shown some promise, results have largely been currently limited to simulation. This can be mostly attributed to the lack of suitable hardware. In this paper, we present LEAP Hand, a low-cost dexterous and anthropomorphic hand for machine learning research. In contrast to previous hands, LEAP Hand has a novel kinematic structure that allows maximal dexterity regardless of finger pose. LEAP Hand is low-cost and can be assembled in 4 hours at a cost of 2000 USD from readily available parts. It is capable of consistently exerting large torques over long durations of time. We show that LEAP Hand can be used to perform several manipulation tasks in the real world—from visual teleoperation to learning from passive video data and sim2real. LEAP Hand significantly outperforms its closest competitor Allegro Hand in all our experiments while being 1/8th of the cost. We release the URDF model, 3D CAD files, tuned simulation environment, and a development platform with useful APIs on our website at http://leaphand.com

Kinematics and Dexterity:

LEAP hand demonstrates side to side dexterity in both the finger up and finger down configuration.
This is thanks to its universal abduction-adduction mechanism.


LEAP Hand costs under $2000 and can be assembled in under three hours using only common hand tools.

Sim2Real Pipeline using Isaac Gym

Open-source and available here
Also check out our followup work: Dexterous Functional Grasping


LEAP Hand is one of the strongest robotic hands available today
Strength Results Table


LEAP Hand can accurately complete repeated motions without overheating

Repeatability Test Graph Repeatability Test Caption

Human-like Versatility

LEAP Hand can grasp a wide variety of objects easily
Grasping Test Table
Teleoperation Test Table

Teleoperation from Uncalibrated Human Video

Behavior Cloning with Internet Videos

Behavior Cloning Results Table


Our recent live demo at RSS 2023, thanks Aleksei Petrenko for the video!


      title={LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning},
      author={Shaw, Kenneth and Agarwal, Ananye and Pathak, Deepak},
      journal={Robotics: Science and Systems (RSS)},


We thank Shikhar Bahl, Russell Mendonca, Unnat Jain and Jianren Wang for fruitful discussions about the project. KS is supported by NSF Graduate Research Fellowship under Grant No. DGE2140739. This work is supported by ONR N00014-22-1-2096 and the DARPA Machine Common Sense grant.