6D pose estimation is a common and important task in industry. Obtaining the 6D pose of objects is the basis for many other functions such as bin picking, autopilot, etc. Therefore, many corresponding studies have been made in order to improve the accuracy and enlarge the range of application of various approaches. After several years of development, the methods of 6D pose estimation have been enriched and improved. Although some predecessors have analyzed the methods and summarized them in detailed, there have been many new breakthroughs in recent years. To understand 6D pose estimation better, this paper will make a new and more detailed review of 6D pose estimation. We divided these methods into two approaches: Learning-based approaches and non-learning-based approaches, including 2D-information-based approach and 3D-information-based approach. Additionally, we introduce the challenges that exist in 6D pose estimation. Finally, we compare the performance of different methods qualitatively and discuss the future development trends of the 6D pose estimation.

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.

Laser stripe center extraction is a critical step for a structured-light system, which plays an important role in industrial fields. However, existing center extraction methods are mainly for simple objects, where the stripe contours are relatively clear and no fake stripe areas caused by surface texture or surface reflection disturb the extraction of the real stripe area. To develop center extraction methods for complex objects, this paper proposed a new laser stripe extraction method based on the features of the laser stripe. After extracting seed points of the laser stripe using an extreme value method and connected component analysis, we can determine the stripe directions from the seed points and iteratively grow the centerline of the laser stripe. Finally, a gray-gravity method is used to extract the accurate center points of the laser stripe based on the obtained centerline. Experiments on 2D image laser stripe extraction and real 3D reconstruction application verified the robustness and accuracy of the proposed method.