Pose estimation is an essential technology for product grasping and assembly in intelligent manufacturing. Finding local correspondences between the 2-D image and the 3-D model is the key step to estimate the 6-D pose of an object. However, when the objects are textureless, it is difficult to identify distinguishable point features. In this article, we propose a novel deep learning framework called the pseudo-Siamese graph matching network to tackle the problem of feature matching of textureless objects and estimate accurate object poses with a single RGB-only image. We utilize a pseudo-Siamese network structure to learn the similarity between the 2-D image features and the 3-D mesh model of the object. A fully convolutional network and a graph convolutional network are used to extract high-dimensional deep features of the 2-D image and the 3-D model, respectively. Dense 2-D–3-D correspondences are inferred using the pseudo-Siamese matching network. Then, the pose of the object is calculated by the Perspective-n-Point and random sample consensus (RANSAC) methods. Experiments on the LINEMOD dataset and a grasping task for metal part show the accuracy and robustness of our proposed method. ¹

Conventional moment-based visual servoing methods suffer from several problems in industrial applications due to the utilization of high-order image moments. In this paper, we analyze the shortcomings of the moment-based visual servoing from the viewpoint of practical industrial applications, and propose a novel moment-based 2 1/2D visual servoing method for grasping textureless planar parts. We use hybrid visual features that combine image moments with 3D rotation in the Cartesian space to control the robot motion. Instead of applying high-order image moments, we use rotation features, which provide a decoupled interaction matrix that is full rank and with no local minimum in the control scheme. Furthermore, to estimate the relative rotation of the textureless part in real time, a new estimation method based on a cross-correlation analysis is proposed. The proposed visual servoing method provides a better motion control and 3D trajectory of the robot arm and remains stable in the workspace. Experimental results demonstrated the effectiveness of the method.

At present, discrete workshops demand higher transportation efficiency, but the traditional scheduling strategy of the logistics systems can no longer meet the requirements. In a transportation system with multiple automated guided vehicles (multi-AGVs), AGV path conflicts directly affect the efficiency and coordination of the whole system. At the same time, the uncertainty of the number and speed of AGVs will lead to excessive cost. To solve these problems, an AGVs Multi-Objective Dynamic Scheduling (AMODS) method is proposed which is based on the digital twin of the workshop. The digital twin of the workshop is built in the virtual space, and a two-way exchange and real-time control framework based on dynamic data is established. The digital twin system is adopted to exchange data in real time, create a real-time updated dynamic task list, determine the number of AGVs and the speed of AGVs under different working conditions, and effectively improve the efficiency of the logistics system. Compared with the traditional scheduling strategy, this paper is of practical significance for the scheduling of the discrete workshop logistics systems to improve the production efficiency, utilization rate of resources, and dynamic response capability.

We introduce MP6D, a public dataset which is used for 6D pose estimation of Metal Parts in industrial environments. The dataset consists of 20 metal parts made of aluminum alloy material which are commonly used in factories. To the best of our knowledge, this is the first dataset of metal parts with simultaneous multi-target, occluded, and illumination changes. The color homogeneity, textureless and light-reflecting properties raise great challenges for estimating the pose of the objects. To improve the accuracy of the ground-truth pose, we propose a novel bi-directional optimization method to minimize the projection errors of all the objects in the dataset. Our main insight is to iteratively optimize the union pose of multi-object in single-frame and the relative pose of each single object with respect to the Aurco-board through multi-frame information. We compare our dataset with several well-known pose estimation datasets. The results demonstrate that the accuracy of our dataset is superior to the others. We also provide the baselines for some state-of-the-art pose estimation methods upon our dataset for the comparison of further studies.

TheSixdegrees of freedom 6DoF pose estimation of texture-less objects provides a spatial understanding of industrial scenes and is the basis for accurate object manipulation. Recent studies have shown that the introduction of known model information and initial poses helps CNNs-based methods achieve better performance in complex scenes. However, the mapping from image space to pose space learned by neural networks is dimensionally lifting. Due to the lack of depth information, it is difficult for neural networks to capture local clues on texture-less surfaces and directly regress the relative 3-D translation and 3-D rotation. Instead, we propose a novel framework named REG-Net, which transforms the 6DoF pose estimation task into a 2-D keypoint registration problem. The proposed network first encodes regional prior information using multi-representation, utilizes the globally-consistent offset attention module to align 2-D keypoint features in a long range, and then estimates offsets and potential regions of keypoints. The proposed regional PnP simultaneously adjusts the keypoint locations in a short range and outputs the pose. This framework compresses the learning space of the network from 3-D to 2-D. Extensive experiments on two benchmark datasets demonstrate the robustness and accuracy of REG-Net. We further demonstrate the effectiveness of REG-Net in the reflective industrial part grasping applications.