ABSTRACT. Vessels constitute one of the most cost effective ways of transporting goods around the world. Despite the efforts, maritime accidents still occur, with catastrophic consequences. For this reason, vessels are submitted to periodical inspections for the early detection of cracks and corrosion. These inspections are nowadays carried out at a great cost. In order to contribute to make ship inspections safer and more cost-efficiently, this paper presents a novel Micro-Aerial Vehicle devised as a flying camera that can virtually teleport the human surveyor through the different structures of the vessel hull. The control software has been designed following the Supervised Autonomy paradigm, so that it is in charge of safety related issues such as collision avoidance, while the surveyor, within the main control loop, is supposed to supply displacement commands while he/she is concentrated on the inspection at hand. The paper provides an extensive evaluation of the platform capabilities and usability, both under laboratory conditions and onboard a real vessel, during an inspection campaign.

ABSTRACT. We study the problem of optimally inspecting an underground (underwater) gallery with $k$ agents. We consider a gallery with a single opening and with a tree topology rooted at the opening. Due to the small diameter of the pipes (caves), the agents are small robots with limited autonomy and there is a supply station at the gallery's opening. Therefore, they are initially placed at the root and periodically need to return to the supply station. Our goal is to design off-line strategies to efficiently cover the tree with $k$ small robots. We consider two objective functions: the covering time (maximum collective time) and the covering distance (total traveled distance). The maximum collective time is the maximum time spent by a robot needs to finish its assigned task (assuming that all the robots start at the same time); the total traveled distance is the sum of the lengths of all the covering walks. Since the problems are intractable for big trees, we propose approximation algorithms. Both efficiency and accuracy of the suboptimal solutions are empirically showed for random trees through intensive numerical experiments.

ABSTRACT. This paper addresses the problem of deriving attitude estimation and trajectory tracking strategies for unmanned aerial vehicles (UAVs) using exclusively on-board sensors. The perception of the vehicle position and attitude relative to a structure is achieved by robustly comparing a known geometry with the data provided by a LiDAR sensor, solving an optimization problem and also robustly identifying outliers. Building on this information, several methods are discussed for obtaining the attitude of the vehicle with respect to the structure, including a nonlinear observer to estimate the vehicle attitude on SO(3). A simple nonlinear control strategy is also designed with the objective of providing an accurate trajectory tracking control relative to the structure, and experimental results are provided for the performance evaluation of the proposed algorithms.

ABSTRACT. This paper presents the design of a dual arm aerial manipulation robot consisting of a customized hexarotor platform equipped with a lightweight dual arm manipulator. The proposed design is intended to integrate multiple devices required for building a complete aerial manipulation system, including vision and range sensors, on-board computers, communication devices, navigation systems, along with the manipulator. The developed platform will provide optimum performance in terms of flight time and payload taking into account the current technology available for building these kind of aircrafts. The design of the platform also considers vibration isolation, control and stability, and extended workspace for the manipulator. A lightweight (1.8 Kg) and human-size dual arm manipulator has been integrated in the developed platform. Each arm provides 5 degrees of freedom (DOF) for end effector positioning and orientation. The arms are built using smart servo actuators and a frame structure manufactured in anodized aluminum. The design is validated through rigidity and modal analysis using finite element methods (FEM). The paper also analyses how the efficiency can be improved using ducted fans. The developed platform has been tested in outdoor flights, evaluating the influence of arms motion over the stability of the platform.

ABSTRACT. Ground effect on rotary aircraft has been studied for many decades. Although a large body of research results is now available for conventional helicopters, this topic is just beginning to receive attention in the unmanned aerial vehicles community, particularly for small size UAVs. The objective of this papers is to assess the applicability of a widely-used ground effect model, developed in the middle of the last century by Cheeseman and Bennett, for predicting the ground effect on small rotary UAV. Furthermore, in this paper has been studied other aerodynamics effects associated with flying close to surfaces or obstacles. Test stand has been designed to experiment with different configuration. The experiments of ground effect for a single rotor are consistent with the prediction of Cheeseman and Bennett. Wall ef-fect, ceiling effect and combination of different experiments have been studied in this paper. Lastly, the experiments will be carry out to assess combined effect and even a complete multirotor. The experimental procedures and the implications on the results obtained is also included in the paper.

ABSTRACT. El proyecto PANDORA abarca el desarrollo de un sistema de sensores multivehículo versátil que permite realizar un mapeado 3D a través de un sistema de navegación autónoma tanto en escenarios interiores como exteriores. A partir de las medidas obtenidas utilizando la fusión de LIDARs, GPS, IMU y cámaras de 360º, se realizará una recreación en 3D del escenario mapeado, lo cual permitirá realizar una inspección virtual de gran precisión al operario de la obra. En este artículo se muestra la arquitectura y la sensórica escogidas, así como las principales estrategias de guiado, navegación y control implementadas en un multicóptero para permitir el mapeado a través de un vuelo autónomo ya sea utilizando el sistema GNSS o en ausencia de éste.

ABSTRACT. This paper presents an introduction of U-Space concept. Next, a brief introduction of TARGUS system developed by INDRA is presented. Finally, a number of complex operational scenarios where drones or optional piloted air-crafts in VLL operations has to share the airspace with manned aircrafts are described.

ABSTRACT. This paper provides a summary of the challenges faced by RPAS when operating in very low level (VLL) conditions beyond visual line of sight (BVLOS). These challenges are basically: the need of improved situation awareness (detect and avoid features) for obstacle detection, the need of complex guidance algorithms to avoid the obstacles found, the possibility of data link loss, and the requirements coming from the insertion of the RPAS in controlled airspace, which are being developed now within the UTM concept. The solution to these challenges is not easy, and it implies many developments such as improving the accuracy and integrity of the navigation features of the RPAS, improving the sensors on-board in order to effectively detect obstacles, and implementing collision avoidance algorithms which have to be able to safely avoid them. This paper finally analyses the most common types of collision avoidance algorithms and their characteristics.

ABSTRACT. This short paper presents two projects developed at CATEC where we are pushing the state of the art in autonomy regarding aerial systems. Moreover, the paper introduces the importance of autonomy for European UAV market since it is a key enabling technology for U-Space in VLL operations.

ABSTRACT. Remote Piloted Aircraft Systems (RPAS) are becoming a tool for many applica-tions. Since several years an effort to integrate them in the Air Traffic Manage-ment (ATM) system has been made throughout the world. However, for many RPAS operations flying at Very Low Level (VLL) airspace, outside the conven-tional ATM system, is enough. Nevertheless, to fly at VLL without restrictions or managed in some way would present several safety and security issues. Un-manned Aerial Systems Management (UTM) system based on 4G/5G networks could solve the current problem of flying at VLL airspace.

ABSTRACT. Visual attention plays a central role in natural and artificial systems to control perceptual resources. The classic artificial visual attention systems uses salient features of the image obtained from the information given by predefined filters. Recently, deep neural networks have been developed for recognizing thousands of objects and autonomously generate visual characteristics optimized by training with large data sets. Besides being used for object recognition, these features have been very successful in other visual problems such as object segmentation, tracking and recently, visual attention. In this work we propose a biologically inspired object classification and localization framework that combines Deep Convolutional Neural Networks with foveal vision. First, a feed-forward pass is performed to obtain the predicted class labels. Next, we get the object location proposals by applying a segmentation mask on the saliency map calculated through a top-down backward pass. The main contribution of our work lies in the evaluation of the performances obtained with different non-uniform resolutions. We were able to establish a relationship between performance and the different levels of information preserved by each of the sensing configurations. The results demonstrate that we do not need to store and transmit all the information present on high-resolution images since, beyond a certain amount of preserved information, the performance in the classification and localization task saturates.

ABSTRACT. There are many open issues and challenges in the reinforcement learning field, such as handling high-dimensional environments. Function approximators, such as deep neural networks, have been successfully used in both single- and multi-agent environments with high dimensional state-spaces. The multi-agent learning paradigm faces even more problems, due to the effect of several agents learning simultaneously in the environment. One of its main concerns is how to learn mixed policies that prevent opponents from exploring them in competitive environments, achieving a Nash equilibrium. We propose an extension of several algorithms able to achieve Nash equilibriums in single-state games to the deep-learning paradigm. We compare their deep-learning and tablebased implementations, and demonstrate how WPL is able to achieve an equilibrium strategy in a complex environment, where agents must find each other in an infinite-state game and play a modified version of the Rock Paper Scissors game.

ABSTRACT. In the context of assistive robotics, the robot has to take multiple decisions. We explore the problem where a robot has multiple choices to perform a task and has to select the action that maximizes the success probability, among a repertoire of pre-trained actions. We investigate the case where sensory data is only available before taking the decision, but not while the actions is being performed. In this paper we propose to use Gaussian Mixture Model (GMM) as a decision making system. Our adaptation allows to initialize the model using only one sample per component. We also propose an algorithm to use the result of each execution to keep continuously updating the model, thus adapting the robot behavior to the user and evaluating the effectiveness of each pre-trained action. The proposed algorithm is applied to a robotic shoe dressing problem. Simulated and real experiments show the validity of our approach.

ABSTRACT. Pose invariant object detection and classification plays a critical role in robust image recognition systems and can be applied in a multitude of applications, ranging from simple monitoring to advanced tracking. This paper analyzes the usage of the Bag of Words model for recognizing objects in different scales, orientations and perspective views within cluttered environments. The recognition system relies on image analysis techniques, such as feature detection, description and clustering along with machine learning classifiers. For pinpointing the location of the target object, it is proposed a multiscale sliding window approach followed by a dynamic thresholding segmentation. The recognition system was tested with several configurations of feature detectors, descriptors and classifiers and achieved an accuracy of 87% when recognizing cars from an annotated dataset with 177 training images and 177 testing images.

ABSTRACT. This paper presents an application of machine learning and tactile sensing to rescue robotics. Disaster situations often exhibit low-visibility scenarios where haptic feedback suppose a crucial information for searching possibles victims. To extract haptic information from the environment, a tactile sensor attached to a light-weight robotic arm is employed. Then, methods based on the SURF descriptor, SVM, DCNNs and transfer learning are implemented to classify the data. Besides, a 9-classes experiment is carried out with the aim to compare those procedures. The contact elements used for the experiment are human parts of the arm and typical objects from catastrophe scenarios. The best achieved accuracy of 92.22%, results from the application of the transfer learning procedure using a pre-trained DCNN and fine-tuning the classification layer of the network.

ABSTRACT. In this paper it is proposed the use of a Total Station as odometry helper to improve the localization of UAVs for 3D reconstruction of underside of bridges where typically lacks of GPS signal and steel structures produce might produce interferences on the measures on the UAVs. The information from the Total Station is sent to the UAV through a WIFI network and is fused with data from the IMU as odometry. Robot is also provided with a RGB-D camera which provides pointclouds for building the map.

ABSTRACT. Fruit harvesting is a topic of intereset in agricultural industries. In order to perform this task, robots should be able to recognize and segment fruit in their perceptual environment. Particularly, apple trees are often arranged as planar trellis structures in commercial orchards. The vine-like branches have leaves that can occlude fruit and produce noise in typical depth sensor data that also populates the scene with objects that are not of interest. In this paper, we present a method that uses a Dirichlet mixture of Gaussian processes and a Gibbs-Sampler for segmenting clusters of apples to support selective autonomous harvesting. Furthermore, the model provides probabilistic reconstruction of the entire apple which can be used for better grasping of the fruit.

ABSTRACT. This paper proposes the application of a stereo vision system for estimating and controlling the Cartesian and joint deflection in an anthropomorphic, compliant and ultra-lightweight dual arm designed for aerial manipulation. Each arm pro-vides four degrees of freedom (DOF) for end-effector positioning in a human-like kinematic configuration. A simple and compact spring-lever mechanism in-troduced in all joints provides mechanical compliance to the arms. A color marker attached at the end effector of the arms is visually tracked by a stereo pair installed over the shoulders. The Cartesian position and velocity of the markers is estimated with an Extended Kalman Filter (EKF), while the corre-sponding points in an equivalent stiff-joint manipulator are obtained from the kinematic model and the position of the servos. The Cartesian deflection is de-fined as the difference between these two measurements, obtaining the joint de-flection from the inverse kinematics. The vision-based deflection estimator is validated in test bench experiments: position estimation accuracy, impact re-sponse, passive/active compliance and contact force control.

ABSTRACT. We propose a novel 3D navigation system for autonomous vehicle path-planning. The system processes a point-cloud data from an rgb-d camera and creates a 3D occupancy grid with adaptable cell size. Occupied grid cells contain normal distribution characterizing the data measured in the area of the cell. The normal distributions are then used for cell classification, traversability, and collision checking. The space of traversable cells is used for path-planning. The ability to work in three-dimensional space allows autonomous robots to operate in highly structured environments with multiple levels, uneven surfaces, and vari- ous elevated and underground crossings. That is important for the usage of robots in real-world scenarios such as in urban areas and for disaster rescue missions.

ABSTRACT. La reconstrucción 3D densa de escenas es de gran interés tanto para la navegación de robots como para el modelado 3D de objetos o la realidad aumentada. En este artículo se describe la arquitectura de un sistema capaz de generar una reconstrucción 3D densa del entorno utilizando una cámara monocular. Para ello se ha implementado un algoritmo de estéreo basado en movimiento capaz de calcular un mapa de profundidad en cada imagen para su posterior integración en un mapa denso. La utilización de una cámara monocular permite evitar las desventajas en cuanto al rango y las condiciones de funcionamiento de otros tipos de sensores como las cámaras RGB-D o los pares estéreo. El sistema propuesto ha sido validado tanto en conjuntos de datos sintéticos en escenas interiores como en entornos reales exteriores.

ABSTRACT. The aim of this paper is to introduce an innovative machinery result of combining cable suspended robot technology based on parallel kinematics with a traditional gantry crane. This machinery has been named Cablecrane. Its purpose is to keep the same load capabilities as in traditional gantry cranes while enabling full 6 degrees of freedom (DOF) control of the payload.

This means that the payload is fully controlled in position and orientation while it is being manipulated. Thus, precision load handling and movement without oscillations are possible in any direction, in any orientation.

In addition, combined with appropriate calibration, sensors and integrated CNC controller, most of manipulation tasks in plant can be programmed and automatized.

The final result is an increase in production, full plant automation and enhanced plant safety.

ABSTRACT. To realize human-robot collaboration in manufacturing, industrial robots need to share an environment with humans and to work hand in hand. This introduces safety concerns but also provides the opportunity to take advantage of human-robot interactions to control the robot. The main objective of this work to provide HRI without compromising safety issues in a realistic industrial context. In the paper, a region-based filtering and reasoning method for safety has been developed and integrated into a human-robot collaboration system. The proposed method has been successfully demonstrated keeping safety during the showcase evaluation of the European robotics challenges.

ABSTRACT. There is a lack of quality indexes to evaluate grasps that are more likely to allow a hand-to-hand transfer of an object during a manipulation task. In order to overcome it, this paper presents a proposal of grasp transfer quality measures to evaluate how easy or feasible is that an object grasped by one hand could be grasped by another hand to perform a hand-to-hand transfer. Experiments were conducted to evaluate the proposed grasp transfer quality measures using different objects and the model of a real robotic hand.

ABSTRACT. Flexibility on assembly lines implies the use of nowadays techniques on programming and robotics, as well as the implementation of a framework that supports the needed for information to cope with the adaptation to current production lines. This paper presents the effort on combine company request with a common base for Factory of the Future implementation in Tecnalia. The overall structure is introduced and two projects are used to explain how the testing and preliminary technology transfer is being tested. Open source tools and existing de-facto standards has been used to define specification regarding reconfigurable system architectures, resource data models and control.

ABSTRACT. UAS operate in a complex and uncertain environment where the information is obtained through non-ideal sensors. Obstacle avoidance is critical in many missions, both tele-operated by an operator, and those of autonomous character. However, the performance of avoidance algorithms depends on the type of operating environment, imperfect nature of information, and uncertainty of system dynamics and control outcome. Furthermore, non-deterministic nature of adopted solutions and architectures makes the evaluation somehow limited. With ongoing research, we established that the previous work on the avoidance and reactive control has not adequately addressed the performance, nor the most important dependencies affecting the system behaviour. We developed simulation environment that reflects the influence of the most vital parameters on the avoidance system. The implications are twofold, providing the evaluation framework for assessing the reactive avoidance algorithms and preparing a starting ground in the design phase.

ABSTRACT. This paper reports preliminary investigations concerning the development of a LIDAR based sense and avoid system with a low computational footprint for small Unmanned Air Vehicles (UAVs). The focus is on the integration with nominal flight control systems and on computational feasibility. The proposed system decomposes the sense and avoid problem into the following components detection, space assessment, escape trajectory estimation and avoidance execution. The control logic is encoded with the help of a hybrid automaton. The properties of the system are studied with the help of approximations to time slices of the UAV reach set.

ABSTRACT. In this paper, we propose a reactive algorithm for a dual arm aerial robot during its navigation phase. This algorithm takes into account not only the aerial platform dynamics but also the constraints imposed by the dual-arm manipulator. The UAV is fully and continuously controlled using velocity commands but the arms are only allowed to move between a set of predefined configurations. The arms configurations are bounded in order to achieve a reduced solution space for collision checking. The reactive navigation algorithm is based on commands from a higher-level path planner and receives as input point-cloud sensor readings. This work is within the framework of the AEROARMS project, so we consider the dual-arm aerial platform developed in the project. Thus, a simple but realistic model for velocity dynamics of the mentioned UAV has been obtained by means of real data, and the proposed method has been tested in a SITL simulation framework.

ABSTRACT. This paper proposes a novel solution for improving visual localization in an active fashion. The solution, based on artificial potential field, associates each feature in the current image frame with an attractive or neutral potential energy. The resultant action drives the vehicle towards the goal, while still favouring feature rich areas within a local scope. Since no map is required, it is a lightweight solution and can be employed in a complementary fashion with SLAM. Experimental results with a mini quadrotor equipped with a downward looking camera demonstrates that the proposed method can effectively drive the vehicle to the goal through a path that prevents localization failure.

ABSTRACT. Missing tools is a problem in aircraft factories. It may reduce the productivity of the assembly line and missing items may cause FOD (Foreign Object Damage) if they are lost inside the aerostructure. This paper proposes a method which uses aerial robots to search and locate missing tools. Each tool will be equipped with a radio tag with an ID that can listen and respond to request messages from the aerial robot. Thus, the robot can take range measurements to the missing tools from different locations while performing other tasks in the factory. The range measurements are used to estimate the location of every missing tool using a Particle Filter (PF) which will eventually converge to an Extended Kalman Filter (EKF). The proposed method was evaluated and validated in real experiments performed in an emulated scenario very similar to the real factory. Preliminary tests were also performed in the Airbus DS CBC factory with good results.

ABSTRACT. This paper addresses preliminary results of integration of a mobile node in a wireless sensor network for an urban information system. The proposed mobile node has been designed with a modular and scalable architecture that allows changing the set of sensors in short time. An implementation of the mobile node, including sensors for gas concentrations and environmental parameters, has been installed on an electric vehicle and tested in real scenarios in the city of Malaga.

ABSTRACT. This paper presents the design and initial experimentation of a novel robot-sensor network security architecture that exploits the synergies between robots and sensor networks to provide high security level with moderate resource consumption. The robot implements security functionalities that in traditional schemes are assumed by the sensor nodes and the Base Station. In contrast to traditional sensor network security schemes, it is not sensor nodes but the robot who discovers other sensor nodes and establishes the network topology, involving important security advantages. This paper presents the design of the architecture, its main advantages and shows its validity in initial field experiments.

ABSTRACT. A Robust Model Predictive Control (MPC) scheme for the control of formations of Autonomous Underwater Vehicles (AUVs) is presented ad discussed discussed. This application domain is extremely relevant and exhibits very difficult challenges: (i) slow, low data-rate acoustic communications, (ii) significant perturbations inherent to the hydrodynamic environment, (iii) unexpected emergence of obstacles, and (iv) severe onboard computation constraints. While the later aspect is discussed by the Reach Set MPC scheme implementation which maximizes the a priori off-line computation as enabled by as much as possible invariant data, the other challenges are accommodated by considering a more conservative version of this MPC scheme which involves a number of intermediate steps and, thus, exhibits a reasonably greater on-line computational burden.

ABSTRACT. This paper presents Robobo in the context of higher education. Robobo is a low-cost educational mobile robot that combines a simple wheeled base with a smartphone, which provides the latest technology to the robot. With Robobo, students can develop their own projects through ROS using cameras, microphones or high-resolution screens, bringing teaching closer to the real requirements of the market they will find when they finish their studies. In this work, we describe the hardware and software development we have carried out. Furthermore, we show an exemplifying case of student project that shows the potentiality of this platform in this context.

ABSTRACT. ROS Industrial (ROS-I) is an effort to deploy the Robot Operating System (ROS) for industrial manufacturing applications. The ROS-I activities are organised by the ROS Industrial consortium (RIC). With the EU-funded project ROSIN, which started in 2017, the ROS-I activities are further supported. The project will give out funds for developing ROS-I components. As a further important measure, the ROSIN project focuses on education measures for training a large number of students and industry professionals to become specialists in ROS-I. In this paper, we outline the broad ROSIN education programme, which consists of a series of summer schools, a professional academy and intends to provide the course contents in Massive Open Online Courses as well.

ABSTRACT. Engineering degrees require a strong background in Physical Sciences and Mathematics, demanding a high level of conceptualization and abstract reasoning that many students do not possess at the entry level of their high education studies. This can cause students demotivation and dropout, a situation that Higher Education institutions have felt the need to cope with. One methodology to address this problem is to introduce the use of robots on the classes. This tool has unique characteristics, both technical and societal, that may potentially contribute to increase students' motivation and engagement, which are key factors on their academic success. This paper presents the rationale, challenges and methodology used to introduce robots as a tool to teach introductory electronics to first year students of the Masters course in Electronics and Telecommunications Engineering at the University of Aveiro. The paper also reports evaluation indicators that result from two different surveys, one generic, carried out in the scope of the Quality Assurance System of the University, and another one developed specifically to evaluate the course. The results confirm that there is a clear and overall positive impact. Particularly significant are the gains on the students motivation and subject comprehension, without a noticeable impact on the course difficulty and required effort. It is also specially relevant that students are strongly in favor of keeping robot's usage due to its impact on both knowledge and motivation.

ABSTRACT. In 58 Italian Public Comprehensive Institutes (Istituti Comprensivi), that include Primary and Elementary schools, 4,505 students experimented the use of a mobile robot, Sapientino Doc by Clementoni, to learn curricula matters such as Mathematics, Geometry and Geography (MGG). The project 'A scuola di coding con Sapientino}' was developed during the 2016/2017 regular school year for about 4 months (March-2017). The schools were distributed throughout Italy and involved 248 classes, 4,505 students from 5 to 8 years old, and 167 teachers. The aim of the research is to demonstrate a learning gain in Mathematics, Geometry and Geography, after the students use a mobile robot during regular lessons held by their own teachers in their classrooms. In this paper, we present the methodology used to develop the project and the results of data analysis.

ABSTRACT. Recently, constructing mosaic images becomes an active field in several computer vision and graphic applications. In this paper, a panoramic image construction using monocular camera is proposed. In this approach, AGAST algorithm is used to extract the keypoints; in order to obtain reliable results for real-time applications. In addition, based on the homography between the panoramic and the new image, the rotation matrix is obtained, and the new image can be projected on a plane parallel to panorama. Finally, image illumination is compensated over the whole image, and the calculation of the pixels contributed by each frame in the overlapping areas. The proposed approach has been verified with real flights, and the obtained results show the robustness of constructing panoramic image with minimal loosing in the information. Furthermore, the results prove the ability of the proposed approach to create panoramic images in real-time applications.

ABSTRACT. The complexity of autonomous Aerial Manipulators (AMs), i.e. Unmanned Aerial Vehicle (UAV) + Robot Manipulator (RM), is growing faster as per our demand of being able to perform complex tasks. This complexity makes the control system to have to take into account somehow the RM dynamics, otherwise the overall behaviour of the system could be compromised. In this work, we thoroughly analyse the overall performance of the AM with a widespread controller designed neglecting the RM dynamics. In particular, the performances under the induced forces/torques provided by a compound interaction of movements of the RM (vibrations) and aerodynamic effects. For the case of study, we consider an UAV multicopter and a generic redundant RM. A complete analysis with realistic simulations on a benchmark is reported.

ABSTRACT. Flying autonomously in a workspace populated by obstacles is one of the main challenges when working with Unmanned Aerial Vehicles (UAV). To address this challenge this paper presents a model predictive ight controller that drives the UAVthroughcollision-free trajectories to reach a given pose or follow a waypoint path. The major advantage of this approach lies on the ability to perform planning and control at the same time by considering a predened set of obstacles as ellipsoidal constraints in the optimal control program. In addition, the delays are cosidered in the prediction by an experimental rst order with delay model of the system. Successful experiments using a motion capture system and a lowcost UAV prove its efectiveness for real-time sense-and-avoid and surveillance applications.

ABSTRACT. Due to the variety of applications of multirotor and fixed-wing unmanned aerial vehicles (UAVs) and their highly energy-limited flight time, there is a strong need for optimization methods in order to ensure the best tracking quality of reference signals changes. In this paper, the use of one of the most recent population-based, bio-inspired, search algorithm for the automatic search for optimal parameters of fixed-gain controller according to the predefined cost function, was proposed. The cuttlefish algorithm (CFA) was used. It is a new, batch, meta-heuristic algorithm which mimics the mechanism of colour changing behaviour used by the cuttlefish to solve numerical global optimization problems, and in the paper – to explore the three-dimensional, limited space of parameters of the most commonly used controller type, i.e. PID. This controller was proposed in order to control the altitude of unmanned aerial vehicle. The simulation research results were presented. A comparative study was conducted for the closed-loop control system with the model of unmanned quadrotor helicopter and following controllers: PID (tuned by the CFA), classical PD, fuzzy PD and fractional-order PD controller (tuned by the Particle Swarm Optimization algorithm). The optimization procedure in the cuttlefish algorithm used a minimization of an exemplary cost function, i.e. Integral of Absolute Error (IAE).

ABSTRACT. En este artículo se presenta un novedoso sistema de aplicación robotizada de sellante sobre perfiles de piezas recanteadas de material compuesto, en el contexto del sector aeronáutico. Este sistema ha sido desarrollado con el fin de obtener una solución viable, versátil y de bajo coste en el proceso de sellado, atendiendo a los exigentes requisitos de calidad empleados en la industria aeronáutica. El sistema propuesto está constituido por un robot manipulador, un dispositivo de triangulación láser para la verificación dimensional del cordón de sellante, un cabezal electromecánico-neumático como efector final especialmente diseñado para la aplicación, y un software SCADA para el control y supervisión de las variables del proceso.

ABSTRACT. El objetivo de este artículo es presentar y analizar la robotización de procesos de fabricación según el concepto de Industria 4.0 y su impacto en las empresas de la industria aeronáutica. Para ello, se describe en primer lugar la evolución de la automatización de estos procesos en las últimas décadas. Posteriormente, se analiza la situación presente a la luz del nuevo concepto de Industria 4.0, con un especial énfasis en la robotización de procesos. En este contexto, se definen las peculiaridades de la aplicación de los principios de la Industria 4.0 a la industria aeronáutica. Finalmente, se presentan algunas soluciones para la robotización de procesos de fabricación, de inspección y ensayos mecánicos típicos en la Aeronáutica. Estas soluciones, que pueden ser ejemplos paradigmáticos de lo que persigue la Industria 4.0, han sido desarrolladas por el Centro Tecnológico CATEC en colaboración con empresas del sector.

ABSTRACT. El objetivo de este artículo es presentar un sistema robotizado para el taladrado de apilados de piezas formados por revestimientos aeronáuticos con rigidizadores, así como una metodología integral para el diseño ágil de la trayectoria de las herramientas de corte y el control del proceso de taladrado. Este sistema ha sido desarrollado con el fin de obtener una solución flexible, robusta y de bajo coste en los procesos de taladrado de montaje, atendiendo a los exigentes requisitos de calidad empleados en la industria aeronáutica. El sistema propuesto emplea un manipulador robótico de alta precisión, un cabezal de taladrado comercial y un SCADA específicamente diseñado, que permite cargar la trayectoria de las herramientas usando cualquier software de diseño de propósito general. Adicionalmente, este SCADA es útil para monitorizar los principales parámetros del proceso de taladrado, sirviendo esto para anticipar problemas de desgaste prematuro de las herramientas o para responder rápidamente en caso de colisiones accidentales.

ABSTRACT. En este artículo se presenta un sistema automatizado innovador para el pintado y detección de defectos en piezas aeronáuticas complejas. El sistema completo está formado por tres subsistemas: un sistema automatizado para el pintado electroestático con reciprocadores, un sistema robotizado para la asistencia al inspector en la detección de defectos en las superficies de las piezas pintadas y un sistema robotizado para el repintado posterior de las piezas en los lugares con faltas de pintura. El procedimiento de pintado electrostático, que ya viene empleándose desde hace tiempo en tuberías y piezas sencillas, se propone ahora para el pintado de piezas mecanizadas de geometría compleja. La automatización de todos los procesos mencionados, mediante el empleo de reciprocadores, perchas, utillajes específicos, visión artificial y robótica colaborativa, supone una gran mejora en la productividad y versatilidad de los procesos de pintado aeronáutico.

ABSTRACT. This paper is focused on creating semantic 3D models of unstructured warehouses from coloured point clouds. Several scans from different locations of a laser scanner are integrated into a unique 3D dataset that is afterwards processed. The paper presents an efficient 3D processing algorithm that is able to segment, recognize and locate the existing materials of a storage place. The obtained 3D model provides to logistic managers precise and valuable information, such as: the current location of the stock, the free space for coming merchandises or the occupied volume variations between two scanning sessions taken at different times. The method has been tested under noise conditions in simulated scenarios and the extracted model has been compared with a ground truth model. The good results demonstrate that this approach could be useful in the logistic field

ABSTRACT. In this work, a crop inspection system is presented. A mobile plat-form, based on a commercial electric vehicle, is equipped with different on-board sensors to inspection annual crops (maize, cereal, etc.) and multi-annual crops (orchards, vineyards, etc.). The use of a low-cost RGB-D sensor, the Mi-crosoft Kinect v2 sensor, for the inspection of woody crops is tested. A method to generate automatic 3D reconstructions of large areas, such as a complete crop row, from the information directly supplied by the RGB-D sensor is shown as well as a procedure to correct the drift that appears in the reconstruction of crop rows. All these methods were tested and validated in real fields at different times throughout 2016. The development presented in this paper is a promising technology to achieve better crop management, which will increase crop yield.

ABSTRACT. This work proposes an automatic method to detect ancient symbols written in stone. The proposed method takes into account well-known techniques used in computer vision to identify the contour of the symbols in the image. The two-stage method consists of segmentation and localization processes. Segmentation process includes a pre-processing step, edge detection and thresholding. Localization process is based on two conditions that take into account several parameters, like the distance between points, and the orientation and the continuity of the edges. This proposal has been applied to localize Egyptian cartouches (borders enclosing the name of a king) and stonemason’s marks from images obtained under varying lighting conditions (controlled and natural lighting). The proposed method is compared favorably against other methods based on chain coding, neural networks and statistical correlation. The promising results give new possibilities to identify and recognize complex symbols and ancient texts.

ABSTRACT. This paper describes a estimator architecture for a Formula Student Prototype, based on data from an inertial measurement unit (IMU), a global positioning system (GPS), and from the underlying dy- namic model of the car. Non-linear dynamic model of the car and re- alistic models for the sensors are presented. The estimates of attitude, rate-gyro bias, position, velocity and sideslip, based on Kalman lter- ing techniques. The resulting system is validated on a Formula Student prototype an assessed given ground truth data obtained by a set of dif- ferential GPS receivers installed onboard.

ABSTRACT. Torque Vectoring (TV) has the objective to substitute the need of a mechanical dierential, while improving the handling and response of the wheeled vehicle. This work addresses the design of a torque vectoring system in an rear wheel driven formula student prototype. The proposed solution resorts to a PID controller for yaw rate tracking with an evenly distributed torque to each wheel. Also an LQR scheme is discussed, for tracking the yaw rate and the lateral velocity. To assess and design, rst a 7 degree of freedom (DOF) non linear model is constructed, followed by a linear 2 DOF model, both validated with real data. The linear model, is used to design and simulate the proposed controllers. When the controller is within the desired parameters it is tested in the non linear model. Tests with the vehicle are performed to verify the contribution of the controller to the overall performance of the vehicle.

ABSTRACT. This paper presents a novel approach for plan generation, selection and pruning of trajectories for autonomous driving, capable of dealing with dynamic complex environments, such as driving in urban scenarios. The planner first discretizes the plan space and searches for the best trajectory and velocity profile of the vehicle. The main contributions of this work are the use of G2-splines for path generation and a method that takes into account accelerations and passenger comfort for generating and pruning velocity profiles based on 3rd order splines, both fulfilling kinodynamic constraints. The proposed methods have been implemented in a motion planner in MATLAB and tested through simulation in different representative scenarios, involving obstacles and other moving vehicles. The simulations show that the planner performs cor- rectly in different dynamic scenarios, maintaining the passenger comfort.

ABSTRACT. Battery Electric Vehicles have high potentials for the modern transportations, however, they are facing limited cruising range. To address this limitation, we present a semi-autonomous ecological driver assistance system to regulate the velocity with energy-efficient techniques. The main contribution of this paper is the design of a real-time nonlinear receding horizon optimal controller to plan the online cost-effective cruising velocity. Instead of conventional l2-norms, a deadzone-quadratic penalty function for the nonlinear model predictive controller is proposed. Obtained field experimental results demonstrate the effectiveness of the proposed method for a semi-autonomous electric vehicle in terms of real-time energy-efficient velocity regulation and constraints satisfaction.

ABSTRACT. This work explores the potential of game theory to solve the task allocation problem in multi-robot missions. The problem considers a swarm with dozens of drones that only know their neighbors, as well as a mission that consists of visiting a series of locations and performing certain activities. Two algorithms have been developed and validated in simulation: one competitive and another cooperative. The first one searches the best Nash equilibrium for each conflict where multiple UAVs compete for multiple tasks. The second one establishes a voting system to translate the individual preferences into a task allocation with social welfare. The results of the simulations show both algorithms work under the limitation of communications and the partial information, but the competitive algorithm generates better allocations than the cooperative one.

ABSTRACT. This article presents a new approach to the interception of moving targets in large and complex scenarios. The path planning for interception is based on the Risk-RRT algorithm, which is enhanced by integrating additional information from Fast Marching Method algorithms. Two different techniques based on that method were adapted and integrated with the Risk-RRT algorithm, the travel distance to the target location and the probability of interception at a given point. The proposed approach has effectively combined the environment information with the kinodynamic path planning created by Risk-RRT. The combination of those two algorithms proved to be capable of on-line planning and following an effective interception path, while keeping functions of obstacle evasion, handling of uncertainties and reactive navigation.

ABSTRACT. Solving the robot localization problem is one of the most necessary requirement for autonomous robots. Several methodologies can be used to determine its location as accurately as possible. What makes this difficult is the existence of uncertainty in the sensing of the robot. The uncertain information needs to be combined in an optimal way. This paper stresses a Kalman filter to combine information from the odometry and Ultra Wide Band Time of Flight distance modules, which lacks the orientation. The proposed system validated in a real developed platform performs the fusion task which outputs position and orientation of the robot. It is used to localize the robot and make a 3 DoF scanning of magnetic field in a room. Other examples can be pointed out with the same localization techniques in service and industrial autonomous robots.

ABSTRACT. Fast Marching Method has been applied to many fields such as image processing or path planning. For path planning, the Anisotropic Fast Marching Method can be used, which allows computing paths with small gradient, a very interesting characteristic for outdoor robots such as the mars rovers. This paper studies the quality of the different paths that can be computed looking into the height changes, gradient of the path, gradient of the terrain (as surface) and curvature, when the anisotropy index is changed.

ABSTRACT. In this paper, a customized interface developed in the framework of the ROBOT FASE II project is described. This project aimed at improving the productivity of two FANUC ARCMate 100iC MIG welding robots with R-30iA controllers mounted in an 8 meters-high mobile gantry crane at Navantia company in Puerto Real, Spain. The solution designed for welding application by the University of Cadiz consists of four parts (1) a library of piece templates including relevant information for each piece to be welded, including obviously the typical piece geometry shape and dimensions, but also all parameters needed for welding(sequence, intensity of the arc, waving description,…) and optimized to get a perfect result by a professional welder team (2) a coordinate measuring arm used to capture 3D information from the real world, (3) a software to generate automatically the optimized FANUC welding program using both the template and the 3D information captured by the arm, adapting the template to real-world coordinates and orientation, (4) and finally an FTP interface to transmit the optimized welding program to each robot for immediate welding operation. The use of this solution for welding operation has reduced robot programming time from hours to minutes for a typical structure allowing an important increase of productivity at Navantia company.

ABSTRACT. This paper presents an automated robotic welding system adapted for shipbuilding in large shipyards. This solution has been devised in the shipyard of Navantia located in the south of Spain, in the context of ROBOT FASE II R&D project. It also presents the human teams that have developed this welding system. The article explains the 3 parts that make up the welding system. The location of the robotic welding arm of the Fanuc brand is detailed in the first part. In addition, the gantry and spatial coordinate axes are described and indicated where the robotic arm is housed. The second part contains the system capture of the coordinates in the space for the reading of the singular points to be soldered. These points are measured by a portable measuring arm. The last part is composed of the system of communication between the different parts throughout the computer. The computer is responsible for synchronizing the measuring arm and the robotic welding arm by translating the points to be soldered.

ABSTRACT. In the Industry 4.0 context, and more particularly in the framework of the new naval building paradigm Shipyard 4.0, various enabling technologies appear. These technologies are communication technologies and Internet of the Things, in conjunction with processing tools, security and information analysis, Big Data, robotics, artificial intelligence, simulation, augmented reality and additive manufacturing, that allow the development of the new industrial paradigm sometimes referred to as the Fourth Industrial Revolution or Industry 4.0. It aims the efficiency of the processes, optimizing decision-making along all the product life cycle. Additive manufacturing is one of the pillars on which this new industrial production way is based. With several decades of history and the recent expiration of patents, this technology has suffered a breath-taking development in the last few years, evolving from a prototyping technology towards a production technology with several unique characteristics that will lead to its consolidation among the conventional manufacturing processes. According to ASTM, additive manufacturing technologies are classified, depending on the used material and energy supply, into seven categories: Photopolymerization, material deposition, binder injection, material extrusion, powder bed fusion, lamination manufacturing and direct energy deposition. Navantia is leading the project “3DCABINS: Development of additive manufacturing materials and technologies for the production of cabins in the naval sector”, with the support of INNANOMAT Research Group from Cádiz University. This project has been co-funded by CEIMAR Foundation through the “I Convocatoria de Proyectos de Innovación Empresarial con Proyección Territorial”. 3DCABINS project focuses on the development of toilet modules for big vessels, using additive manufacturing techniques, specifically by fused deposition modelling (FDM). One of the main achievements of this project has been the development and implementation of a big format FDM 3D printer. This development has been needed due to the big volume, in the order of cubic meters, of the parts to be produced. A technological surveillance work regarding big format 3D printers, both in the market and the research field, has been done.

This study has allowed defining and developing a prototype of 3D printer with unique characteristics in Europe. The main characteristics of this equipment are a working volume over three cubic meters, and the capacity to work with different polymer based materials in the form of pellets, to a production speed much bigger than that of the commercial 3D printers. Two work lines have been followed, which are presented in this communication. On one hand, a methodology for the selection and development of eligible materials has been developed, fulfilling the requirements of the parts to be installed in a ship and to be approved by the correspondent classification societies. In particular, several design requirements have been covered, concerning the volume of the part to be made (1,7 m x 1,1 m x 2,1 m) and other functional characteristics (halogen free fireproof materials, acoustic isolation, humidity absorption absence, surface finishing and structural behaviour), following the standards of naval sector classification societies. On the other hand, a study and selection of the specific additive manufacturing software have been performed in order to best fit the needs of the project. As a result, a well arranged and distributed workflow has been defined. Thus, integration and exchange of digital model files are optimized to get the maximum potential of the tools and the conforming possibilities that additive manufacturing technologies offer. To achieve this, a review of computer aided design (CAD) and computer aided engineering (CAE) software has been required, as well as a review of other emerging software specific for additive manufacturing technologies. The following aspects have been analysed and applied: computer aided design, simulation, lattice design, quality and file review, and slicing software. Once the material selection and development processes concluded, and after needed software was identified, we have proceeded to the development of a digital toilet mock up combining topological optimization and advanced CAD modelling. Current works are focused in the construction of a one-to-one scale functional prototype using the developed FDM 3D printer. These works are currently in progress, and the end of the project is due to conclude in the last quarter of 2017.

ABSTRACT. Offshore wind industry is expected to experiment a significant growth in following years. NAVANTIA has identified this fact as an excellent opportunity to diversify its activity, traditionally centered on naval military industry. With this aim, some years ago NAVANTIA started to follow an ambitious strategic plan becoming nowadays a reference supplier of products and services for offshore wind sector. A good example is the agreement that NAVANTIA and IBERDROLA signed for the supply of 29 jackets for the WIKINGER wind farm that it is being installed in Germany. The jackets are big steel tubular structures anchored to the ocean floor at 35-60m of depth, acting as structural support for wind towers. One critical element of the jackets are the nodes, where structural loads concur. Manual welding of steel tubes to build a node is a critical operation, often being a bottle neck in the manufacturing process. Due to that, NAVANTIA looked for an automated and high-productivity solution able to reduce welding time and maximize the quality of arc welds. With this aim, NAVANTIA carried out an R&D project in collaboration with ARTABRO SAMDEU, ELECTRO RAYMA, INTAF PROMECAN and AIMEN Technology Centre, called FEWIND, under the INNTERCONECTA program (ITC-20133027), in which a robotized welding cell of X-geometry nodes for jackets was developed. This paper describes the developed welding cell constituted by the following elements: Five-axis manipulator system for nodes, welding robot, welding power source, welding seam tracker system and dimensional control system of welded nodes.

ABSTRACT. Cybersecurity in autonomous systems is a growing concern. Currently most research robotic systems are built using ROS framework, along with other commercial software. The goal of this paper is to improve ROS security features by using encrypted communications and semantic rules to ensure a correct behavior. To encrypt communications, Advanced Encryption Standard algorithm has been applied. Then, the framework ROSRV has been used to define semantic rules for ROS messages. In order to test this proposal, two experiments have been carried out: in the first one, plain-text communications are not allowed and must be blocked; in the second one, rules for detecting denial of service attacks are tested against a real attack performed on a Real-Time Locating System, used by a mobile robot to estimate its location.

ABSTRACT. The calibration of an accelerometer, and a gyroscope is performed. A linear sensor model have been used. The triaxial sensor calibration algorithm is based on the minimization of a cost function, and is performed offline. Calibration hardware has been designed, and used to get the calibration data. The algorithm has been tested with the acquired data, and the calibration results are presented. Although the sensor model is linear, some experiences about dealing with non-linearities are exposed.

ABSTRACT. This paper proposes a methodology for automatic characterization of phase resetting controllers for quick balance recovery after loss of it during biped locomotion. The system allows to easily characterize and design useful phase resetting controllers using a simulation environment. Several experiments have been performed using a NAO humanoid robot in order to automatically characterize and test the phase resetting mechanism. Notwithstanding, it can be implemented by using any humanoid robot with a similar kinematic structure. Once the controllers are characterized, the proposed system detects the robot’s current state through the information provided by its inertial sensors and then applies the correct phase resetting in a short period of time in order to quickly recover the robot’s balance. The proposed control scheme reacts quickly whenever unknown external perturbations are applied to the robot’s body by using the proposed phase resetting mechanism.

ABSTRACT. The use of teleoperation systems can provide substantial advantages in various fields such as remote explosive dismantling and rescue operations, as well as improve the accuracy on certain tasks like surgery. These systems offer feedback mainly based on visual information of the task performed showing relevant data of the systems used as well as their surroundings. Our proposal involves the use of haptic devices to remotely control a robot in order for the user to receive haptic feedback alongside the visual information. In a first design that several experts evaluated, it was concluded that the interface used had to be substantially improved. This communication describes the process developed to design and evaluate an interface to improve user interaction with the teleoperation system.

ABSTRACT. Staged at Piombino, Italy in September 2015, euRathlon 2015 was the world's first multi-domain (air, land and sea) multi-robot search and rescue competition. In a mock disaster scenario inspired by the 2011 Fukushima NPP accident the euRathlon 2015 Grand Challenge required teams of robots to coop-erate to map the area, and missing workers and stem a leak. The second edition of the competition will be held also in Piombino in September 2017, under the name of ERL Emergency and as part of the new European Robotics League ini-tiative. In this paper we outline the euRathlon 2015 and the ERL Emergency 2017 Grand Challenge, and the results and lessons learned from euRathlon 2015.

ABSTRACT. This paper proposes the whole system scheme designed for the autonomous landing of a multicopter on a moving platform. It ex- plains the hardware and software architecture and shows obtained re- sults of some successful tests. Also, the proposed system was validated and compared during the MBZIRC robotics competition in March 2017.

ABSTRACT. The use of maps allows mobile robots to navigate between known points in an environment. Using maps allows to calculate routes avoiding obstacles and not being stuck in dead ends. This paper shows how to integrate 3D perceptions on a map to obtain obstacle-free paths when obstacles are not at the level of 2D sensors, but elevated. Chairs and tables usually pose a problem when only one can see the legs with a 2D laser, although they present a high hurdle with a much larger area. This approach builds a static map starting from the construction plans of a building. A long-term map is started from the static map, and up- dated when adding and removing furniture, or when doors are opened or closed. A short-term map represents dynamic obstacles such as people. Obstacles are perceived by merging all available information, both 2D laser and RGB-D cameras, into a compact 3D probabilistic representa- tion. This approach is appropriate for fast deployment and long-term operations in office or domestic environments, able to adapt to changes in the environment. This work is designed for domestic environments, and has been tested in the RoboCup@home competition, where robots must navigate in an environment that changes during the tests.

ABSTRACT. In this paper, we describe a navigation system requiring very few computational resources, but still providing performance that are comparable with standard commonly used tools. This lightweight navigation system is thus suitable for robots with low computational resources and provides interfaces for both ROS and NAOqi environments. We have successfully tested the software on different robots and in different situations, including SoftBank Pepper robot for RoboCup@Home SSPL competitions and on small home-made robots for RoboCup@Home Education workshops. The developed software is simple and easy to understand. It is released open-source and as Debian package so that it can be easily installed by many young researchers for robotic competitions and educational activities.

ABSTRACT. The use of the odometry and SLAM visual methods in autonomous vehicles has been growing. Optical sensors provide valuable information from the scenario that enhance the navigation of autonomous vehicles. Although several visual techniques are already available in the literature, their performance could be significantly affected by the scene captured by the optical sensor. In this context, this paper presents a comparative analysis of three monocular visual odometry methods and three stereo SLAM techniques. The advantages, particularities and performance of each technique are discussed, to provide information that is relevant for the development of new research and novel robotic applications.

ABSTRACT. This paper addresses the problem of vehicle detection using a little explored LIDAR's modality: the reflection intensity. LIDAR reflection measures the ratio of the received beam sent to a surface, which depends upon the distance, material, and the angle between surface normal and the ray. Considering a 3D-LIDAR mounted on board a robotic vehicle, which is calibrated with respect to a monocular camera, a Dense Reflection Map (DRM) is generated from the projected sparse LIDAR's reflectance intensity, and inputted to a Deep Convolutional Neural Network (ConvNet) object detection framework for the vehicle detection. The performance on the KITTI is superior to some of the approaches that use LIDAR's range-value, and hence it demonstrates the usability of LIDAR's reflection for vehicle detection.

ABSTRACT. Object identification in images taken from moving vehicles is still a complex task within the computer vision field due to the dynamism of the scenes and the poorly defined structures of the environment. This research proposes an efficient approach to perform recognition on images from a stereo camera, with the goal of gaining insight of traffic scenes in urban and road environments. We rely on a deep learning framework able to simultaneously identify a broad range of entities, such as vehicles, pedestrians or cyclists, with a frame rate compatible with the strong requirements of onboard automotive applications. The results demonstrate the capabilities of the full perception system for a wide variety of situations, thus providing valuable information to understand the scenario ahead of the vehicle.

ABSTRACT. In the Intelligent Transportation Systems Society (ITSS), the research interest on intelligent vehicles is increasing during the last few years. Accordingly, this paper presents the advances in the develop- ment of the ROS-based (Robot Operating System) software architecture for intelligent vehicles. The main contribution of the architecture is its powerfulness, flexibility, and modularity, which allows the researchers to develop and test different algorithms. The architecture has been tested on different platforms, autonomous ground vehicles from the iCab (Intel- ligent Campus Automobile) project and in the intelligent vehicle based on Advanced Driver Assistance Systems (ADAS) incorporated from IvvI 2.0 (Intelligent Vehicle based on Visual Information) project.