6-DoF Contrastive Grasp Proposal Network
arXiv:2103.15995
Abstract
Proposing grasp poses for novel objects is an essential component for any robot manipulation task. Planning six degrees of freedom (DoF) grasps with a single camera, however, is challenging due to the complex object shape, incomplete object information, and sensor noise. In this paper, we present a 6-DoF contrastive grasp proposal network (CGPN) to infer 6-DoF grasps from a single-view depth image. First, an image encoder is used to extract the feature map from the input depth image, after which 3-DoF grasp regions are proposed from the feature map with a rotated region proposal network. Feature vectors that within the proposed grasp regions are then extracted and refined to 6-DoF grasps. The proposed model is trained offline with synthetic grasp data. To improve the robustness in reality and bridge the simulation-to-real gap, we further introduce a contrastive learning module and variant image processing techniques during the training. CGPN can locate collision-free grasps of an object using a single-view depth image within 0.5 seconds. Experiments on a physical robot further demonstrate the effectiveness of the algorithm.
arXiv commentTo appear on 2021 International Conference on Robotics and Automation (ICRA 2021)
References in corpus (6)
- Contrastive Multiview Coding
- Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
- UniGrasp: Learning a Unified Model to Grasp with Multifingered Robotic Hands
- Classification based Grasp Detection using Spatial Transformer Network
- Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data
- Real-world Multi-object, Multi-grasp Detection