Efficient Fully Convolutional Network and Optimization Approach for Robotic Grasping Detection Based on RGB-D Images  

作　　者：NIE Wei LIANG Xinwu 聂卫;梁新武

机构地区：[1]School of Aeronautics and Astronautics,Shanghai Jiao Tong University,Shanghai 200240,China

出　　处：《Journal of Shanghai Jiaotong university(Science)》2025年第2期399-416,共18页上海交通大学学报(英文版)

基　　金：the National Natural Science Foundation of China(No.62173230);the Program of Science and Technology Commission of Shanghai Municipality(No.22511101400)。

摘　　要：Robot grasp detection is a fundamental vision task for robots.Deep learning-based methods have shown excellent results in enhancing the grasp detection capabilities for model-free objects in unstructured scenes.Most popular approaches explore deep network models and exploit RGB-D images combining colour and depth data to acquire enriched feature expressions.However,current work struggles to achieve a satisfactory balance between the accuracy and real-time performance;the variability of RGB and depth feature distributions receives inadequate attention.The treatment of predicted failure cases is also lacking.We propose an efficient fully convolutional network to predict the pixel-level antipodal grasp parameters in RGB-D images.A structure with hierarchical feature fusion is established using multiple lightweight feature extraction blocks.The feature fusion module with 3D global attention is used to select the complementary information in RGB and depth images suficiently.Additionally,a grasp configuration optimization method based on local grasp path is proposed to cope with the possible failures predicted by the model.Extensive experiments on two public grasping datasets,Cornell and Jacquard,demonstrate that the approach can improve the performance of grasping unknown objects.

关 键 词：deep learning object grasping detection fully convolutional neural network robot vision 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]