Search

Due to the potential issue of non-rigid deformations in the manufacturing process of mobile phone frames, most existing dispensing automation methods struggled to acquire accurate dispensing positions. For this purpose, an innovative approach of dispensing trajectory generation was proposed, which addressed the limitations associated with previous methods. Firstly, the phone frames were scanned using a 3D laser profiler, then a point cloud registration algorithm based on the pose graph was introduced to reconstruct the point clouds of frames. The template-based approach was employed, and the dispensing trajectory for template was manually annotated. Subsequently, the template was aligned with the target by a non-rigid registration algorithm based on the deformation graph, thereby the transformed trajectory was obtained. Furthermore, a trajectory refinement strategy was presented to generate the robust, accurate dispensing trajectory of the target. Extensive experiments demonstrate that the errors of the generated dispensing trajectories were consistently below 0.01 mm, and the speed can meet the real-time requirement of practical applications.

Copyright of Chinese Journal of Intelligent Science & Technology is the property of Beijing Xintong Media Co., Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this work, we revisit CNN architectures for sequence modeling, focusing on human trajectory prediction tasks. Forecasting human trajectories has been extensively explored as a sequence modeling problem, with many studies utilizing CNNs. Unlike conventional approaches that apply 1D convolution or 2D convolution over heatmap representations, we propose a novel architecture that applies 2D convolution directly over raw trajectory coordinates. Our method employs a coarse-to-fine strategy to refine trajectory predictions. We evaluated our approach on the ETH/UCY and Stanford Drone Datasets, demonstrating significant improvements. Our method sets a new state-of-the-art on the Stanford Drone Dataset, improving prediction accuracy and outperforming existing methods. • Unlike conventional approaches using CNNs for sequence modeling, e.g., 1D convolution or 2D convolution over the heatmap representation, we propose an architecture that applies 2D convolution over raw trajectory coordinates. • With proper padding and kernel sizes, the proposed method performs 1D convolution, 1D dilated convolution, separating coordinates convolution, and mixing features in one forward pass. • We evaluated the proposed approach on the ETH/UCY and Stanford Drone Dataset, and the proposed method improved the performance by a safe margin, setting a new state-of-the-art result on Stanford Drone Dataset. [ABSTRACT FROM AUTHOR]

Abstract: Trajectory generation for nonlinear control systems is an important and difficult problem. In this paper, we provide a constructive method for hierarchical trajectory refinement. The approach is based on the recent notion of -related control systems. Given a control affine system satisfying certain assumptions, we construct a -related control system of smaller dimension. Trajectories designed for the smaller, abstracted system are guaranteed, by construction, to be feasible for the original system. Constructive procedures are provided for refining trajectories from the coarser to the more detailed system. [Copyright &y& Elsevier]