The terms and conditions for the reuse of this version of the manuscript are specified in the publishing policy. For all terms of use and more information see the publisher's website. When citing, please refer to the published version of the article as indicated above.

In this paper, an approach for fast and accurate segmentation of Deformable Linear Objects (DLOs) named FASTDLO is presented. A deep convolutional neural network is employed for background segmentation, generating a binary mask that isolates DLOs in the image. Thereafter, the obtained mask is processed with a skeletonization algorithm and the intersections between different DLOs are solved with a similarity-based network. Apart from the usual pixel-wise color-mapped image, FASTDLO also describes each DLO instance with a sequence of 2D coordinates, enabling the possibility of modeling the DLO instances with splines curves, for example. Synthetically generated data are exploited for the training of the data-driven methods, avoiding expensive collection and annotations of real data. FASTDLO is experimentally compared against both a DLO-specific approach and general-purpose deep learning instance segmentation models, achieving better overall performances and a processing rate higher than 20 FPS.

In this paper an innovative algorithm for instance segmentation of wires called Ariadne+ is presented. Although vastly present in many manufacturing environments, the perception and manipulation of wires is still an open problem for robotic applications. Wires are Deformable Linear Objects (DLOs) lacking of any specific shape, color and feature. The proposed approach uses deep learning and standard computer vision techniques aiming at their reliable and time effective instance segmentation. A deep convolutional neural network is employed to generate a binary mask showing where wires are present in the input image, then graph theory is applied to create the wire paths from the binary mask through an iterative approach that aims to maximize the graph coverage. In addition, the B-Spline model of each instance, useful in manipulation tasks, is provided. The approach has been validated quantitatively and qualitatively using a manually labelled test dataset and by comparing it against the original Ariadne algorithm. The timings performances of the approach have been also analyzed in depth.

In this paper, the problem of identifying optimal grasping poses for cloth-like deformable objects is addressed by means of a four-steps algorithm performing the processing of the data coming from a 3D camera. The first step segments the source pointcloud, while the second step implements a wrinkledness measure able to robustly detect graspable regions of a cloth. In the third step the identification of each individual wrinkle is accomplished by fitting a piecewise curve. Finally, in the fourth step, a target grasping pose for each detected wrinkle is estimated. Compared to deep learning approaches where the availability of a good quality dataset or trained model is necessary, our general algorithm can find employment in very different scenarios with minor parameters tweaking. Results showing the application of our method to the clothes bin picking task are presented.

No abstract