Grasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Hands

by   Dylan Turpin, et al.

The study of hand-object interaction requires generating viable grasp poses for high-dimensional multi-finger models, often relying on analytic grasp synthesis which tends to produce brittle and unnatural results. This paper presents Grasp'D, an approach for grasp synthesis with a differentiable contact simulation from both known models as well as visual inputs. We use gradient-based methods as an alternative to sampling-based grasp synthesis, which fails without simplifying assumptions, such as pre-specified contact locations and eigengrasps. Such assumptions limit grasp discovery and, in particular, exclude high-contact power grasps. In contrast, our simulation-based approach allows for stable, efficient, physically realistic, high-contact grasp synthesis, even for gripper morphologies with high-degrees of freedom. We identify and address challenges in making grasp simulation amenable to gradient-based optimization, such as non-smooth object surface geometry, contact sparsity, and a rugged optimization landscape. Grasp'D compares favorably to analytic grasp synthesis on human and robotic hand models, and resultant grasps achieve over 4x denser contact, leading to significantly higher grasp stability. Video and code available at


page 1

page 4

page 13

page 21

page 22

page 25

page 26


Fast-Grasp'D: Dexterous Multi-finger Grasp Generation Through Differentiable Simulation

Multi-finger grasping relies on high quality training data, which is har...

Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures by Differentiable Force Closure Estimation

Existing grasp synthesis methods are either analytical or data-driven. T...

FRoGGeR: Fast Robust Grasp Generation via the Min-Weight Metric

Many approaches to grasp synthesis optimize analytic quality metrics tha...

D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions

We introduce the dynamic grasp synthesis task: given an object with a kn...

UniGrasp: Learning a Unified Model to Grasp with N-Fingered Robotic Hands

To achieve a successful grasp, gripper attributes including geometry and...

CPF: Learning a Contact Potential Field to Model the Hand-object Interaction

Estimating hand-object (HO) pose during interaction has been brought rem...

Contact Transfer: A Direct, User-Driven Method for Human to Robot Transfer of Grasps and Manipulations

We present a novel method for the direct transfer of grasps and manipula...

Please sign up or login with your details

Forgot password? Click here to reset