S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes

Abstract

Grasping is among the most fundamental and long-lasting problems in robotics study. This paper studies the problem of 6-DoF(degree of freedom) grasping by a parallel gripper in a cluttered scene captured using a commodity depth sensor from a single viewpoint. We address the problem in a learning-based framework. At the high level, we rely on a single-shot grasp proposal network, trained with synthetic data and tested in real-world scenarios. Our single-shot neural network architecture can predict amodal grasp proposal efficiently and effectively. Our training data synthesis pipeline can generate scenes of complex object configuration and leverage an innovative gripper contact model to create dense and high-quality grasp annotations. Experiments in synthetic and real environments have demonstrated that the proposed approach can outperform state-of-the-arts by a large margin.

arXiv commentAccepted at the Conference on Robot Learning (CoRL) 2019. Project webpage is available here: https://sites.google.com/view/s4ggrapsing

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Grasp2Vec: Learning Object Representations from Self-Supervised Grasping
• On the Continuity of Rotation Representations in Neural Networks
• Learning 6-DoF Grasping and Pick-Place Using Attention Focus
• Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers

Cited by in corpus (6)

• TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline
• Efficient and Accurate Candidate Generation for Grasp Pose Detection in SE(3)
• Machine Learning for Robotic Manipulation
• AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions
• The State of Lifelong Learning in Service Robots: Current Bottlenecks in Object Perception and Manipulation
• REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter