ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact

IROS 2019

Samarth Brahmbhatt¹, Ankur Handa², James Hays¹, Dieter Fox²

Georgia Tech Robotics¹, NVIDIA Robotics²

Abstract

Grasping and manipulating objects is an important human skill. Since most objects are designed to be manipulated by human hands, anthropomorphic hands can enable richer human-robot interaction. Desirable grasps are not only stable, but also functional: they enable post-grasp actions with the object. However, functional grasp synthesis for high-DOF anthropomorphic hands from object shape alone is challenging. We present ContactGrasp, a framework that allows functional grasp synthesis from object shape and contact on the object surface. Contact can be manually specified or obtained through demonstrations. Our contact representation is object-centric and allows functional grasp synthesis even for hand models different than the one used for demonstration. Using a dataset of contact demonstrations from humans grasping diverse household objects, we synthesize functional grasps for three hand models and two functional intents.

Paper bib code

We develop a grasp sampler based on GraspIt!, and a non-linear optimzer based on DART for optimizing grasps to agree with contact demonstrations from ContactDB. Here's a look at the process:

This video shows the grasps generated by our algorithm for GraspIt!'s HumanHand20DOF, the Allegro Hand, and the Barrett Hand, for two different post-grasp functional intents - 'use' and 'handoff':