RGB-D Grasp Detection via Depth Guided Learning with Cross-modal Attention

TL;DR

This paper introduces DGCAN, a novel RGB-D grasp detection method that leverages depth information with a 6D rectangle representation and cross-modal attention to improve accuracy despite noisy depth data.

Contribution

The paper proposes a depth-guided cross-modal attention network with a 6D grasp representation and a local cross-modal attention module for enhanced grasp detection.

Findings

Outperforms existing methods in simulation and physical tests.

Utilizes a 6D rectangle representation including grasp depth.

Effective fusion of RGB and depth features via cross-modal attention.

Abstract

Planar grasp detection is one of the most fundamental tasks to robotic manipulation, and the recent progress of consumer-grade RGB-D sensors enables delivering more comprehensive features from both the texture and shape modalities. However, depth maps are generally of a relatively lower quality with much stronger noise compared to RGB images, making it challenging to acquire grasp depth and fuse multi-modal clues. To address the two issues, this paper proposes a novel learning based approach to RGB-D grasp detection, namely Depth Guided Cross-modal Attention Network (DGCAN). To better leverage the geometry information recorded in the depth channel, a complete 6-dimensional rectangle representation is adopted with the grasp depth dedicatedly considered in addition to those defined in the common 5-dimensional one. The prediction of the extra grasp depth substantially strengthens feature learning, thereby leading to more accurate results. Moreover, to reduce the negative impact caused by the discrepancy of data quality in two modalities, a Local Cross-modal Attention (LCA) module is designed, where the depth features are refined according to cross-modal relations and concatenated to the RGB ones for more sufficient fusion. Extensive simulation and physical evaluations are conducted and the experimental results highlight the superiority of the proposed approach.