The automatic classification of ships from aerial images is a considerable challenge. Previous works have usually applied image processing and computer vision techniques to extract meaningful features from visible spectrum images in order to use them as the input for traditional supervised classifiers. We present a method for determining if an aerial image of visible spectrum contains a ship or not. The proposed architecture is based on Convolutional Neural Networks (CNN), and it combines neural codes extracted from a CNN with a k-Nearest Neighbor method so as to improve performance. The kNN results are compared to those obtained with the CNN Softmax output. Several CNN models have been configured and evaluated in order to seek the best hyperparameters, and the most suitable setting for this task was found by using transfer learning at different levels. A new dataset (named MASATI) composed of aerial imagery with more than 6000 samples has also been created to train and evaluate our architecture. The experimentation shows a success rate of over 99% for our approach, in contrast with the 79% obtained with traditional methods in classification of ship images, also outperforming other methods based on CNNs. A dataset of images (MWPU VHR-10) used in previous works was additionally used to evaluate the proposed approach. Our best setup achieves a success ratio of 86% with these data, significantly outperforming previous state-of-the-art ship classification methods.

Robotic manipulators have to constantly deal with the complex task of detecting whether a grasp is stable or, in contrast, whether the grasped object is slipping. Recognising the type of slippage—translational, rotational—and its direction is more challenging than detecting only stability, but is simultaneously of greater use as regards correcting the aforementioned grasping issues. In this work, we propose a learning methodology for detecting the direction of a slip (seven categories) using spatio-temporal tactile features learnt from one tactile sensor. Tactile readings are, therefore, pre-processed and fed to a ConvLSTM that learns to detect these directions with just 50 ms of data. We have extensively evaluated the performance of the system and have achieved relatively high results at the detection of the direction of slip on unseen objects with familiar properties (82.56% accuracy).

This paper presents a system for the detection of ships and oil spills using side-looking airborne radar (SLAR) images. The proposed method employs a two-stage architecture composed of three pairs of convolutional neural networks (CNNs). Each pair of networks is trained to recognize a single class (ship, oil spill, and coast) by following two steps: a first network performs a coarse detection, and then, a second specialized CNN obtains the precise localization of the pixels belonging to each class. After classification, a postprocessing stage is performed by applying a morphological opening filter in order to eliminate small look-alikes, and removing those oil spills and ships that are surrounded by a minimum amount of coast. Data augmentation is performed to increase the number of samples, owing to the difficulty involved in obtaining a sufficient number of correctly labeled SLAR images. The proposed method is evaluated and compared to a single multiclass CNN architecture and to previous state-of-the-art methods using accuracy, precision, recall, F-measure, and intersection over union. The results show that the proposed method is efficient and competitive, and outperforms the approaches previously used for this task.

Flexible multisensorial systems are a very important issue in the current industry when disassembling and recycling tasks have to be performed. These tasks can be performed by a human operator or by a robot system. In the current paper a robotic system to perform the required tasks is presented. This system takes into consideration the distribution of the necessary tasks to perform the disassembly of a component using several robots in a parallel or in a cooperative way. The algorithm proposed to distribute the task among robots takes into consideration the characteristics of each task and the sequence that needs to be followed to perform the required disassembly of the product. Furthermore, this paper presents a disassembly system based on a sensorized cooperative robots interaction framework for the planning of movements and detections of objects in the disassembly tasks. To determine the sequence of the disassembly of some products, a new strategy to distribute a set of tasks among robots is presented. Subsequently, the visual detection system used for detecting targets and characteristics is described. To carry out this detection process, different well known strategies, such as matching templates, polygonal approach and edge detection, are applied. Finally, a visual-force control system has been implemented in order to track disassembly trajectories. An important aspect of this system is the processing of the sensorial information in order to guarantee coherence. This aspect allows the application of both sensors, visual and force sensors, co-ordinately to disassembly tasks. The proposed system is validated by experiments using several types of components such as the covers of batteries and electronic circuits from toys, and drives and screws from PCs.

Industrial and service robots deal with the complex task of grasping objects that have different shapes and which are seen from diverse points of view. In order to autonomously perform grasps, the robot must calculate where to place its robotic hand to ensure that the grasp is stable. We propose a method to find the best pair of grasping points given a three-dimensional point cloud with the partial view of an unknown object. We use a set of straightforward geometric rules to explore the cloud and propose grasping points on the surface of the object. We then adapt the pair of contacts to a multi-fingered hand used in experimentation. We prove that, after performing 500 grasps of different objects, our approach is fast, taking an average of 17.5 ms to propose contacts, while attaining a grasp success rate of 85.5%. Moreover, the method is sufficiently flexible and stable to work with objects in changing environments, such as those confronted by industrial or service robots.