Region-aware Grasp Framework with Normalized Grasp Space for Efficient 6-DoF Grasping

Siang Chen, Pengwei Xie, Wei Tang, Dingchang Hu, Yixiang Dai, Guijin Wang

Keywords: 6-DoF Grasping, RGBD Perception, Normalized Space, Heatmap

TL;DR: For 6-DoF grasping, we propose Region-aware Grasp Framework consisting of Normalized Grasp Space and a efficient Region-aware Normalized Grasp Network, achieving best grasp detection performance with high efficiency and generalization capability.

Abstract: A series of region-based methods succeed in extracting regional features and enhancing grasp detection quality. However, faced with a cluttered scene with potential collision, the definition of the grasp-relevant region stays inconsistent. In this paper, we propose Normalized Grasp Space (NGS) from a novel region-aware viewpoint, unifying the grasp representation within a normalized regional space and benefiting the generalizability of methods. Leveraging the NGS, we find that CNNs are underestimated for 3D feature extraction and 6-DoF grasp detection in clutter scenes and build a highly efficient Region-aware Normalized Grasp Network (RNGNet). Experiments on the public benchmark show that our method achieves significant >20 % performance gains while attaining a real-time inference speed of approximately 50 FPS. Real-world cluttered scene clearance experiments underscore the effectiveness of our method. Further, human-to-robot handover and dynamic object grasping experiments demonstrate the potential of our proposed method for closed-loop grasping in dynamic scenarios.

Video: https://www.youtube.com/watch?v=RyozevPocX4

Website: https://github.com/THU-VCLab/RegionNormalizedGrasp

Code: https://github.com/THU-VCLab/RegionNormalizedGrasp

Student Paper: yes

Submission Number: 427