DASH:

A Framework for Designing Anthropomorphic Soft Hands through Interaction

Pragna Mannam*   Kenneth Shaw*   Dominik Bauer   Jean Oh   Deepak Pathak   Nancy Pollard  
Carnegie Mellon University
IEEE Humanoids 2023
*denotes equal contribution
Best Oral Paper Award Finalist

Abstract

Modeling and simulating soft robot hands can aid in design iteration for complex and high degree-of-freedom (DoF) morphologies. This can be further supplemented by iterating on the design based on its performance in real world manipulation tasks. However, iterating in the real world requires a framework that allows us to test new designs quickly at low costs. In this paper, we present a framework that leverages rapid prototyping of the hand using 3D-printing, and utilizes teleoperation to evaluate the hand in real world manipulation tasks. Using this framework, we design a 3D-printed 16-DoF dexterous anthropomorphic soft hand (DASH) and iteratively improve its design over five iterations. Rapid prototyping techniques such as 3D-printing allow us to directly evaluate the fabricated hand without modeling it in simulation. We show that the design improves over five design iterations through evaluating the hand’s performance in 30 real-world teleoperated manipulation tasks. Testing over 900 demonstrations shows that our final version of DASH can solve 19 of the 30 tasks compared to Allegro, a popular rigid hand in the market, which can only solve 7 tasks. We open-source our CAD models as well as the teleoperated dataset for further study.

Task Videos

Scissor
Pen
Drill
M&M
Softball
Plush Dinosaur
Mustard
Cube Flip
Grape off of Stem
Cup Pouring
Hammer
Wooden Cylinder
Egg
Dry Erase
Cloth
Pringles Can
Wine Glass
Card Pickup From Deck
Plastic Bag
Cup Stacking and Unstacking
Chopsticks
Screwdriver
Chip
Tennis Ball
Plush Broccoli
Spam Box
Bin Picking
Dice Rotation In Hand
Drawer
1 in. Block Stacking