Hybrid Physical Metric For 6-DoF Grasp Pose Detection

TL;DR

This paper introduces a hybrid physical metric and a multi-resolution network to improve 6-DoF grasp pose detection accuracy in cluttered environments, achieving a 90.5% success rate in real-world tests.

Contribution

It proposes a novel hybrid physical metric for grasp evaluation and a multi-resolution network architecture for better grasp confidence prediction.

Findings

Hybrid metric improves grasp confidence scoring.

FGC-GraspNet enhances detection precision.

Achieves 90.5% success in real-world cluttered scenes.

Abstract

6-DoF grasp pose detection of multi-grasp and multi-object is a challenge task in the field of intelligent robot. To imitate human reasoning ability for grasping objects, data driven methods are widely studied. With the introduction of large-scale datasets, we discover that a single physical metric usually generates several discrete levels of grasp confidence scores, which cannot finely distinguish millions of grasp poses and leads to inaccurate prediction results. In this paper, we propose a hybrid physical metric to solve this evaluation insufficiency. First, we define a novel metric is based on the force-closure metric, supplemented by the measurement of the object flatness, gravity and collision. Second, we leverage this hybrid physical metric to generate elaborate confidence scores. Third, to learn the new confidence scores effectively, we design a multi-resolution network called Flatness Gravity Collision GraspNet (FGC-GraspNet). FGC-GraspNet proposes a multi-resolution features learning architecture for multiple tasks and introduces a new joint loss function that enhances the average precision of the grasp detection. The network evaluation and adequate real robot experiments demonstrate the effectiveness of our hybrid physical metric and FGC-GraspNet. Our method achieves 90.5\% success rate in real-world cluttered scenes. Our code is available at https://github.com/luyh20/FGC-GraspNet.