Deep Learning Method for Grasping Novel Objects Using Dexterous Hands.

Robotic grasping ability lags far behind human skills and poses a significant challenge in the robotics research area. According to the grasping part of an object, humans can select the appropriate grasping postures of their fingers. When humans grasp the same part of an object, different poses of the palm will cause them to select different grasping postures. Inspired by these human skills, in this article, we propose new grasping posture prediction networks (GPPNs) with multiple inputs, which acquire information from the object image and the palm pose of the dexterous hand to predict appropriate grasping postures. The GPPNs are further combined with grasping rectangle detection networks (GRDNs) to construct multilevel convolutional neural networks (ML-CNNs). In this study, a force-closure index was designed to analyze the grasping quality, and force-closure grasping postures were generated in the GraspIt! environment. Depth images of objects were captured in the Gazebo environment to construct the dataset for the GPPNs. Herein, we describe simulation experiments conducted in the GraspIt! environment, and present our study of the influences of the image input and the palm pose input on the GPPNs using a variable-controlling approach. In addition, the ML-CNNs were compared with the existing grasp detection methods. The simulation results verify that the ML-CNNs have a high grasping quality. The grasping experiments were implemented on the Shadow hand platform, and the results show that the ML-CNNs can accurately complete grasping of novel objects with good performance.

The diagnosis and successful replication of a clinical case of Duck Spleen Necrosis Disease: An experimental co-infection of an emerging unique reovirus and Salmonella indiana reveals the roles of each of the pathogens.

Duck spleen necrosis disease (DSND) is an emerging infectious disease that causes significant economic loss in the duck industry. In 2018, a duck reovirus (named DRV/GX-Y7) and Salmonella indiana were both isolated from the spleens and livers of diseased ducks with DSND in China. The DRV/GX-Y7 strain could propagate in the Vero, LMH, DF-1 and DEF cells with obvious cytopathic effects. The genome of DRV/GX-Y7 was 23,418 bp in length, contained 10 dsRNA segments, ranging from 3959 nt (L1) to 1191 nt (S4). The phylogenetic analysis showed that the DRV/GX-Y7 strain was in the same branch with the new waterfowl-origin reovirus cluster, but was obviously far distant from the clusters of other previous waterfowl-origin reoviruses Muscovy duck reovirus (MDRV) and goose-origin reovirus (GRV), broiler/layer-origin reovirus (ARV) and turkey-origin reovirus (TRV). The RDP and SimPlot program analysis revealed that there were two potential genetic reassortment events in the M2 and S1 segments of the genome. In order to have a clear insight into the pathogenic mechanism of DRV/GX-Y7 and S. Indiana in clinical DSND, an infection experiment was further conducted by challenging commercial ducklings with the two isolates individually and with both. The results showed that DRV/GX-Y7 produced severe hemorrhagic and/or necrotic lesions in the immune organs (thymus, spleen, and bursae) of experimentally infected ducklings. And, that the co-infection of DRV/GX-Y7 and S. Indiana could greatly enhance the pathogenesis by increasing the morbidity and mortality in ducklings whose clinical symptoms and lesions were similar to the natural clinical DSND cases. In summary, the results suggested that the pathogen causing duck spleen necrosis was an emerging unique genetic reassortment strain of duck Orthoreovirus that was significantly different from any previously reported waterfowl-derived Orthoreovirus and the co-infection with the Salmonella isolate could increase the severity of the disease.