Daxin Liu

A random rough surface topography significantly influences the surface contact result. In existing studies that solve the contact problem with random rough surfaces by Isogeometric analysis (IGA), finding the slave point’s closest point on the master random rough surface during the contact detection process is often tackled using intelligent optimization algorithms, such as genetic algorithm (GA), which can be computationally expensive. In order to promote the efficiency of contact detection, we propose a piecewise closest point projection algorithm (PCPPA). Since the geometry in IGA is represented by Non-Uniform Rational B-Spline (NURBS), the PCPPA splits the master random rough surface into multiple local regions by its knot vectors’ element values, and defines an influence radius to determine the influenced local regions that should be considered when finding the slave point’s closest point. The traditional closest point projection algorithm is utilized to find the slave point’s local closest point on each influenced local region. The global closest point is selected from these local closest points by comparing their distances to the slave point. Based on the contact problem between an elastomer cube and a rigid cuboid, both of which have random rough surface, hyper-parameter optimization of the GA is carried out firstly to find the optimal hyper-parameters to minimize its computation time while ensuring correct contact detection results. Secondly, by comparing with the optimal GA, the effectiveness and efficiency promotion of the proposed PCPPA are investigated. It is shown that the computation time of the proposed PCPPA is 8%–20% of that of the optimal GA. Finally, the contact problem solving results obtained through the IGA using the PCPPA-based contact detection method, the IGA using the GA-based contact detection method, and the finite element analysis are compared with one another. It is validated that the discrepancies among these results are very small.

Estimating the 6D poses of industrial parts is a fundamental task in automated industries. However, the scarcity of industrial part datasets and the effort involved to retrain networks present challenges when estimating poses for unseen parts. Although a few pre-trained networks demonstrate effectiveness on unseen objects, they often struggle to encode correct viewpoint for unseen industrial parts, which have significant geometrical differences compared to the pre-trained objects. Additionally, they overlook the viewpoint non-uniformity that frequently occurs in industrial settings, resulting in significant 3D rotation errors. To address these issues, a novel 6D pose estimator for unseen industrial parts is proposed. First, a Self-to-Inter (S2I) viewpoint encoder is introduced to efficiently generate discriminative descriptors that capture the viewpoint information of the observed image. The S2I viewpoint encoder utilizes an Inter-viewpoint attention module to facilitate prior viewpoint communication and leverages a saliency descriptor selection strategy to boost inference speed. Second, a viewpoint alignment module (VAM) is established and integrated with the ICP refiner. The VAM aligns non-uniform viewpoints in an analytical paradigm, leading to enhanced efficiency of the refinement process and more accurate final predictions. Experimental results on the LINEMOD dataset demonstrate competitive performance compared to state-of-the-art methods. Furthermore, the experiments conducted on eight unseen industrial parts validate the exceptional generalizability of our method, highlighting its potential in industrial applications.

Accurate 3D object segmentation in point clouds is a basis for industrial robot applications, such as robot manipulation and digital twin, which require an understanding of the 3D environment. However, the unstructured and disordered nature of point clouds makes it challenging, especially for the incomplete 3D data under a single view in the real-world scenario. To this end, this paper proposes a novel 3D object segmentation framework (3DT-Seg) based on Cross-Window Point Transformer (CP-Former). CP-Former captures the long-range dependencies between local windows and latent semantic boundaries to enhance the point-wise features extracted from irregular point clouds via a bidirectional cross-attention mechanism. In addition, a contrastive learning loss and an adaptive dual aggregation strategy are introduced on semantic transition regions during the semantic supervising and instance clustering process, respectively. In this way, the latent boundary information is further utilized to improve the overall segmentation performance. Experiments on the popular benchmark (SI3DS) dataset show the state-of-the-art performance of the proposed approach in terms of semantic and instance segmentation. Furthermore, a real-world point cloud dataset (IP-Cloud) for the robotic grasping task is presented to fully validate the effectiveness of our method in practice, where it also achieves remarkable performance.