MonoGraspNet: 6-DoF Grasping with a Single RGB Image

TL;DR

MonoGraspNet introduces an RGB-only 6-DoF grasping approach that effectively handles photometrically challenging objects by leveraging 2D features, outperforming depth-based methods in such scenarios.

Contribution

The paper presents the first RGB-only 6-DoF grasping pipeline using 2D keypoints and normal maps, overcoming limitations of depth sensors on transparent and reflective objects.

Findings

Achieves competitive grasping on common objects

Surpasses depth-based methods on photometrically challenging objects

Provides a new annotated dataset for multi-view grasping

Abstract

6-DoF robotic grasping is a long-lasting but unsolved problem. Recent methods utilize strong 3D networks to extract geometric grasping representations from depth sensors, demonstrating superior accuracy on common objects but perform unsatisfactorily on photometrically challenging objects, e.g., objects in transparent or reflective materials. The bottleneck lies in that the surface of these objects can not reflect back accurate depth due to the absorption or refraction of light. In this paper, in contrast to exploiting the inaccurate depth data, we propose the first RGB-only 6-DoF grasping pipeline called MonoGraspNet that utilizes stable 2D features to simultaneously handle arbitrary object grasping and overcome the problems induced by photometrically challenging objects. MonoGraspNet leverages keypoint heatmap and normal map to recover the 6-DoF grasping poses represented by our novel representation parameterized with 2D keypoints with corresponding depth, grasping direction, grasping width, and angle. Extensive experiments in real scenes demonstrate that our method can achieve competitive results in grasping common objects and surpass the depth-based competitor by a large margin in grasping photometrically challenging objects. To further stimulate robotic manipulation research, we additionally annotate and open-source a multi-view and multi-scene real-world grasping dataset, containing 120 objects of mixed photometric complexity with 20M accurate grasping labels.