6-DoF Grasp Detection in Clutter with Enhanced Receptive Field and Graspable Balance Sampling

TL;DR

This paper introduces an enhanced grasp detection method that improves recognition of small-scale grasps in cluttered environments by expanding receptive fields and focusing on small object features, achieving state-of-the-art results.

Contribution

It proposes a novel receptive field enhancement and a graspable balance sampling module to boost small-scale grasp recognition and generalization in 6-DoF grasp detection.

Findings

Achieved approximately 10% improvement in AP@k on GraspNet-1Billion dataset.

Validated effectiveness through deployment in pybullet simulation.

Enhanced recognition of small objects in cluttered scenes.

Abstract

6-DoF grasp detection of small-scale grasps is crucial for robots to perform specific tasks. This paper focuses on enhancing the recognition capability of small-scale grasping, aiming to improve the overall accuracy of grasping prediction results and the generalization ability of the network. We propose an enhanced receptive field method that includes a multi-radii cylinder grouping module and a passive attention module. This method enhances the receptive field area within the graspable space and strengthens the learning of graspable features. Additionally, we design a graspable balance sampling module based on a segmentation network, which enables the network to focus on features of small objects, thereby improving the recognition capability of small-scale grasping. Our network achieves state-of-the-art performance on the GraspNet-1Billion dataset, with an overall improvement of approximately 10% in average precision@k (AP). Furthermore, we deployed our grasp detection model in pybullet grasping platform, which validates the effectiveness of our method.