Center for Biophysics and Quantitative Biology

Abstract 

Our human hands are masterpieces of power and precision, capable of typing, hammering, or delicately using chopsticks. Yet most robots today still rely on simple two-finger grippers in controlled settings because dexterous hands are costly and difficult to deploy. To close this gap, I will introduce my LEAP Hands, high-performance, low-cost, and easy-to-assemble robotic hands that have become the most widely used platform for dexterous manipulation research. LEAP Hand V1 employs motor-in-joint actuation for simplicity, while V2 introduces a novel hybrid rigid–soft structure that delivers exceptional strength and durability.  I will then show how large-scale human video/motion data and simulation techniques can teach human-like manipulation skills across diverse environments.  By tightly integrating mechanical design and machine learning, my open-source robot hands achieve unprecedented levels of dexterity for a variety of everyday tasks.

About the Speaker 

Kenneth Shaw is a Ph.D. student in the Robotics Institute at Carnegie Mellon University advised by Prof. Deepak Pathak. He earned his Bachelor's degree in Electrical and Computer Engineering from Georgia Tech and is a recipient of the NSF Graduate Research Fellowship.

 His research focuses on dexterous robot hands, combining mechanical design with learning from human data techniques. He created multiple low-cost, highly dexterous LEAP Hand platforms that are open-source and accessible to the community.

 His work has been recognized as a Best Oral Paper Award Finalist at IEEE Humanoids 2023, on the cover of the IJRR RSS special issue, and as a Best Paper Award Finalist at the Scaling Robot Learning Workshop.  For further details, visit: https://www.kennyshaw.net

 Host: Professor Prashant Mehta