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

By Dylan Turpin, Liquang Wang, Eric Heiden, Yun-Chun Chen, Miles Macklin, Stavros Tsogkas, Sven J. Dickinson, Animesh Garg. 2022

106 citations recorded by the source corpus.

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 https://graspd-eccv22.github.io/.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Human-Computer Interaction, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Jitendra Malik
2. Sanja Fidler
3. Luc Van Gool
4. Kristen Grauman
5. Trevor Darrell
6. Abhinav Kumar Gupta
7. Cordelia Schmid
8. Andrea Vedaldi

In Control and Systems Engineering

1. Dima Damen
2. David F. Fouhey
3. Dandan Shan
4. Sanja Fidler

In Human-Computer Interaction

1. Dandan Shan
2. Dima Damen
3. David F. Fouhey
4. Amlan Kar
5. Sanja Fidler
6. Jitendra Malik

In Robotics & Control

1. Sanja Fidler

Citations in the corpus

• EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations (2022, background): “[40] Dylan Turpin, Liquan Wang, Eric Heiden, Yun-Chun Chen, Miles Macklin, Stavros Tsogkas, Sven Dickinson, and Animesh Garg.”