Deformation-Aware Data-Driven Grasp Synthesis

TL;DR

This paper introduces a novel grasp synthesis method that incorporates object stiffness information into deep learning models, enabling robots to adapt their grasping strategies for deformable objects with varying stiffness, validated through simulation and real-world experiments.

Contribution

It proposes integrating object stiffness as an input to deep grasp planning networks and creates a new synthetic dataset for training on deformable objects.

Findings

Significant improvement in grasp success rate with stiffness-aware approach

Ability to generate different grasp strategies based on object stiffness

Validated effectiveness on both simulated and real-world objects

Abstract

Grasp synthesis for 3D deformable objects remains a little-explored topic, most works aiming to minimize deformations. However, deformations are not necessarily harmful -- humans are, for example, able to exploit deformations to generate new potential grasps. How to achieve that on a robot is though an open question. This paper proposes an approach that uses object stiffness information in addition to depth images for synthesizing high-quality grasps. We achieve this by incorporating object stiffness as an additional input to a state-of-the-art deep grasp planning network. We also curate a new synthetic dataset of grasps on objects of varying stiffness using the Isaac Gym simulator for training the network. We experimentally validate and compare our proposed approach against the case where we do not incorporate object stiffness on a total of 2800 grasps in simulation and 420 grasps on a real Franka Emika Panda. The experimental results show significant improvement in grasp success rate using the proposed approach on a wide range of objects with varying shapes, sizes, and stiffness. Furthermore, we demonstrate that the approach can generate different grasping strategies for different stiffness values, such as pinching for soft objects and caging for hard objects. Together, the results clearly show the value of incorporating stiffness information when grasping objects of varying stiffness.