Instance-wise Grasp Synthesis for Robotic Grasping

TL;DR

This paper introduces a single-stage neural network for generating precise, instance-specific grasp configurations for robotic manipulation, demonstrating superior accuracy and real-world applicability in cluttered and multi-object scenarios.

Contribution

The paper presents a novel single-stage grasp synthesis network that simultaneously predicts object masks and grasp configurations, outperforming existing methods in accuracy and efficiency.

Findings

Outperforms state-of-the-art on OCID-Grasp dataset

Achieves competitive results on JACQUARD dataset

Validated through extensive simulations and real robot experiments

Abstract

Generating high-quality instance-wise grasp configurations provides critical information of how to grasp specific objects in a multi-object environment and is of high importance for robot manipulation tasks. This work proposed a novel \textbf{S}ingle-\textbf{S}tage \textbf{G}rasp (SSG) synthesis network, which performs high-quality instance-wise grasp synthesis in a single stage: instance mask and grasp configurations are generated for each object simultaneously. Our method outperforms state-of-the-art on robotic grasp prediction based on the OCID-Grasp dataset, and performs competitively on the JACQUARD dataset. The benchmarking results showed significant improvements compared to the baseline on the accuracy of generated grasp configurations. The performance of the proposed method has been validated through both extensive simulations and real robot experiments for three tasks including single object pick-and-place, grasp synthesis in cluttered environments and table cleaning task.