DIAGONAL POINT BY POINT SURFACE DEVELOPMENT METHOD BASED ON NURBS SURFACE FOR BLANK SHAPE ESTIMATION OFCOVER PANEL

According to the characteristics of a complex cover panel, its geometry shape is described by the NURBS surface with great description capability. With the reference to the surface classification determined by Gauss curvature, the proportion of the mid-surface area between before and after being developed is derived from the displacement variation of the mid-surface in the normal vector direction of the sheet metal during the sheet metal forming process. Hereby, based on the curve development theory in differential geometry, a novel diagonal point by point surface development method is put forward to estimate a complex cover panel＇s blank contour efficiently. By comparing the sample＇s development result of diagonal point by point surface development method with that of available one-step method, the validity of the proposed surface development method is verified.

Array Shape Estimation Using Partitioned Eigenstructure Method with Sources in Unknown Localizations

Advanced array processing approaches require accurate knowledge of the location of individual element in a sensor array.Most array shape estimation methods require the directions of sources.In this paper,an array shape estimation method based on eigen-decomposition is presented.The directions of sources do not need to be considered in advance and optimal array shape is generated through a series of iterations.To further improve the accuracy of this algorithm,a partitioned eigenstructure method is introduced.Numerical simulations using non-partitioned and partitioned method are conducted to verify the performance of the proposed technique.

Shape estimation for a TPU-based multi-material 3D printed soft pneumatic actuator using deep learning models

Real-time proprioception presents a significant challenge for soft robots due to their infinite degrees of freedom and intrinsic compliance.Previous studies mostly focused on specific sensors and actuators.There is still a lack of generalizable technologies for integrating soft sensing elements into soft actuators and mapping sensor signals to proprioception parameters.To tackle this problem,we employed multi-material 3D printing technology to fabricate sensorized soft-bending actuators(SBAs)using plain and conductive thermoplastic polyurethane(TPU)filaments.We designed various geometric shapes for the sensors and investigated their strain-resistive performance during deformation.To address the nonlinear time-variant behavior of the sensors during dynamic modeling,we adopted a data-driven approach using different deep neural networks to learn the relationship between sensor signals and system states.A series of experiments in various actuation scenarios were conducted,and the results demonstrated the effectiveness of this approach.The sensing and shape prediction steps can run in real-time at a frequency of50 Hz on a consumer-level computer.Additionally,a method is proposed to enhance the robustness of the learning models using data augmentation to handle unexpected sensor failures.All the methods are efficient,not only for in-plane 2D shape estimation but also for out-of-plane 3D shape estimation.The aim of this study is to introduce a methodology for the proprioception of soft pneumatic actuators,including manufacturing and sensing modeling,that can be generalized to other soft robots.

Feature detection and description for image matching:from hand-crafted design to deep learning

In feature based image matching,distinctive features in images are detected and represented by feature descriptors.Matching is then carried out by assessing the similarity of the descriptors of potentially conjugate points.In this paper,we first shortly discuss the general frame-work.Then,we review feature detection as well as the determination of affine shape and orientation of local features,before analyzing feature description in more detail.In the feature description review,the general framework of local feature description is presented first.Then,the review discusses the evolution from hand-crafted feature descriptors,e.g.SIFT(Scale Invariant Feature Transform),to machine learning and deep learning based descriptors.The machine learning models,the training loss and the respective training data of learning-based algorithms are looked at in more detail;subsequently the various advantages and challenges of the different approaches are discussed.Finally,we present and assess some current research directions before concluding the paper.