GrainGrasp: Dexterous Grasp Generation with Fine-grained Contact Guidance

TL;DR

GrainGrasp introduces a novel approach for dexterous robotic grasping by predicting fine-grained contact maps for each fingertip and optimizing grasp strategies solely from point cloud data, enabling human-like manipulation.

Contribution

The paper presents a new grasp generation method that uses contact guidance and point cloud-based optimization, improving dexterity and precision in robotic grasping tasks.

Findings

Effective contact map prediction for each fingertip.

Grasp strategies generated solely from point cloud data.

Experimental validation shows improved grasping accuracy.

Abstract

One goal of dexterous robotic grasping is to allow robots to handle objects with the same level of flexibility and adaptability as humans. However, it remains a challenging task to generate an optimal grasping strategy for dexterous hands, especially when it comes to delicate manipulation and accurate adjustment the desired grasping poses for objects of varying shapes and sizes. In this paper, we propose a novel dexterous grasp generation scheme called GrainGrasp that provides fine-grained contact guidance for each fingertip. In particular, we employ a generative model to predict separate contact maps for each fingertip on the object point cloud, effectively capturing the specifics of finger-object interactions. In addition, we develop a new dexterous grasping optimization algorithm that solely relies on the point cloud as input, eliminating the necessity for complete mesh information of the object. By leveraging the contact maps of different fingertips, the proposed optimization algorithm can generate precise and determinable strategies for human-like object grasping. Experimental results confirm the efficiency of the proposed scheme.