3DSGrasp: 3D Shape-Completion for Robotic Grasp

2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA(2023)

Cited 3|Views62
No score
Abstract
Real-world robotic grasping can be done robustly if a complete 3D Point Cloud Data (PCD) of an object is available. However, in practice, PCDs are often incomplete when objects are viewed from few and sparse viewpoints before the grasping action, leading to the generation of wrong or inaccurate grasp poses. We propose a novel grasping strategy, named 3DSGrasp, that predicts the missing geometry from the partial PCD to produce reliable grasp poses. Our proposed PCD completion network is a Transformer-based encoder-decoder network with an Offset-Attention layer. Our network is inherently invariant to the object pose and point's permutation, which generates PCDs that are geometrically consistent and completed properly. Experiments on a wide range of partial PCD show that 3DSGrasp outperforms the best state-of-the-art method on PCD completion tasks and largely improves the grasping success rate in real-world scenarios. The code and dataset are available at: https://github.com/NunoDuarte/3DSGrasp.
More
Translated text
Key words
3D shape-completion,complete 3D Point Cloud Data,grasping action,grasping success rate,inaccurate grasp,missing geometry,named 3DSGrasp,novel grasping strategy,object pose,Offset-Attention layer,partial PCD show,PCD completion network,PCD completion tasks,real-world robotic grasping,reliable grasp poses,robotic grasp,sparse viewpoints,Transformer-based encoder-decoder network,wrong grasp
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined