Grasping is an essential skill for robots to interact with humans and the environment. In this paper, we build a vision-based, robust, and real-time robotic grasping approach with fully convolutional neural network. The main component of our approach is a grasp detection network with oriented anchor boxes as detection priors. Because the orientation of detected grasps is significant, which determines the rotation angle configuration of the gripper, we propose the orientation anchor box mechanism to regress grasp angle based on predefined assumption instead of classification or regression without any priors. With oriented anchor boxes, the grasps can be predicted more accurately and efficiently. Besides, to accelerate the network training and further improve the performance of angle regression, angle matching is proposed during training instead of Jaccard index matching. Fivefold cross-validation results demonstrate that our proposed algorithm achieves an accuracy of 98.8% and 97.8% in image-wise split and object-wise split, respectively, and the speed of our detection algorithm is 67 frames per second (FPS) with GTX 1080Ti, outperforming all the current state-of-the-art grasp detection algorithms on Cornell Dataset both in speed and accuracy. Robotic experiments demonstrate the robustness and generalization ability in unseen objects and real-world environment, with the average success rate of 90.0% and 84.2% of familiar things and unseen things, respectively, on Baxter robot platform.

The visual-semantic gap between the visual space (visual features) and semantic space (semantic attributes) is one of the main problems in the Generalized Zero-Shot Learning (GZSL) task. The essence of this problem is that the structure of manifolds in these two spaces is inconsistent, which makes it difficult to learn embeddings that unify visual features and semantic attributes for similarity measurement. In this work, we tackle this problem by proposing a multi-modal aggregated posterior aligning neural network based on Wasserstein Auto-encoders (WAE) which learns a shared latent space for visual features and semantic attributes. The key to our approach is that the aggregated posterior distribution of the latent representations encoded from visual features of each class is encouraged to be aligned with a Gaussian distribution predicted by the corresponding semantic attribute in the latent space. On one hand, requiring the latent manifolds of visual features and semantic attributes to be consistent preserves the inter-class association between seen and unseen classes. On the other hand, the aggregated posterior of each class is directly defined as a Gaussian in the latent space, which provides a reliable way to synthesize latent features for training classification models. Using the AWA1, AWA2, CUB, aPY, FLO, and SUN benchmark datasets, we extensively conducted comparative evaluations to demonstrate the advantages of our method over state-of-the-art approaches.

Laterite ore is one of the important sources of nickel (Ni). However, it is difficult to liberate Ni from ore structure during reduction roasting. This paper provided an effective way for a robust recovery of Ni from laterite ore by H₂ reduction using sodium thiosulfate (Na₂S₂O₃) as a promoter. . It was found that a Ni content of 9.97% and a Ni recovery of 99.24% were achieved with 20 wt% Na₂S₂O₃ at 1,100°C. The promoting mechanism of Na₂S₂O₃ in laterite ore reduction by H₂ was also investigated. The thermogravimetric results suggested the formation of Na₂Mg₂SiO₇, Na₂SO₃, Na₂SO₄, and S during the pyrolysis of laterite with Na₂S₂O₃, among which the alkali metal salts could destroy the structures of nickel-bearing silicate minerals and hence release Ni, while S could participate in the formation of the low-melting-point eutectic phase of FeS-Fe. The formation of low-melting-point phases were further verified by the morphology analysis, which could improve the aggregation of Ni-Fe particles due to the capillary forces of FeS-Fe as well as the enhanced element migration by the liquid phase of sodium silicates during reduction.