Search

Microgrids/nanogrids of prosumers must be able to adapt to new business opportunities related to energy trading. Therefore, highly accepted hierarchical control strategies should be modified to allow deliberate energy interchange among prosumers, even when the microgrid they are integrated in, operates islanded. This is the main contribution of this paper, as energy exchange between prosumers is rarely addressed when they are islanded from the main grid. This work proposes a comprehensive hierarchical control strategy for a multibus nanogrid of prosumers, each of them having photovoltaic generation, battery energy storage systems and loads, in such a way that different voltage and power setpoints for each prosumer allow such energy interchange. Power flow inside the nanogrid is controlled to guarantee the technical feasibility of the obtained setpoints. The proposed control strategy is defined and experimentally validated in both islanded and grid-connected modes, by means of a laboratory-scale prototype. In addition, a smooth transition between the two modes is demonstrated. An adequate capability of the power converters to follow setpoints is proved, with acceptable transient behavior.

This work is based in the cascade connection of several H-bridges as input side of a multiport smart transformer. This paper is focused on finding the best control strategy for this stage, turning from previous individual controllers to a centralized control. This control strategy must guarantee a stable voltage in the DC bus of the desired value, and achieve a unity power factor. In addition, it has been solved another problem derived from applying the control strategy, that was a distortion in the input current caused by a third harmonic component.

This article is about the cascade connection of several H-bridges as the input side of a multi-port Smart Transformer. The paper discusses its unipolar control strategy with two different modulation techniques by connecting different loads in each module or port. The operation of both techniques and the distribution of voltage and current is analyzed using co-simulation with PSIM and SIMULINK. The best technique is determined with the study from the harmonic and efficiency point of view.

Smart spaces are environments equipped with a set of sensors with the main objective of understanding humans’ behavior within them, their interactions and to improve human-machine interfaces. Audiovisual tracking is used to know people’s position in the environment and if they are talking, through the use of cameras and microphones. In this work we present an audiovisual tracking solution with a single camera and microphone array in a distributed configuration. Our idea is to exploit the estimation of azimuth and elevation from audio information to be fused with the position estimation obtained from a Viola and Jones based observation model. The fact that the microphone array is not co-located with the camera will allow to reduce the distance estimation uncertainty from the video model and improve tracking accuracy. The system was evaluated on the AV16.3 database on single speaker sequences, outperforming results of state-of-the-art, under these conditions.

In this article a power flow control strategy based on proportional-resonant current controller in a three-phase 3L-T-type qZSI connected to the grid to regulate the active power flow exchanged with the main grid is analyzed. This topology is quite promising in renewable energy application as the photovoltaic systems. The different components of the system are described and calculated as well as the control strategy, the current control loop based on αβ stationary reference frame and the special modulation method which includes alternating shoot-through states between upper and lower impedance networks. Simulation results illustrate and validate the proposed solution.

This paper presents a simulation framework for the development and testing of UTM functionalities. The simulator is based on the U-space functional architecture and services. U-space includes pre-flight services (before the UAV is allowed to take-off) and in-flight services (when the UAV is flying). There are many in-flight services that are not currently implemented (or only partialy) and, as far as we know, there is not a simulation framework that tackle this. Our UTM simulator is based on the Robot Operating System (ROS) and Gazebo and it allows to implement and test U-space in-flight services, speeding up their development and allowing to implement new functionalities. We show the implementation of a use-case of the EU-funded project GAUSS that involves rotary and fix-wing UAVs flying on a shared environment.

This paper presents the first application of the multi-purpose ROS-MAGNA [1] framework to a real inspection mission performed with a team of multiple UAS. This framework makes transparent the type of autopilot on-board and creates the state machines that control the behaviour of the different UAS from the specification of the multi-UAS mission. In addition, it integrates a virtual world generation tool to manage the environment’s information and visualize the geometrical objects of interest to properly follow the progress of the mission. Due to its flexibility, it can be applied to the inspection of different photovoltaic plants with teams of UAS. The paper describes the system architecture and the human machine interface developed for the mission management by the personnel of the photovoltaic plant. Finally, we show both simulations results and real flight experiments on a photovoltaic plant located in Utrera (Spain).

This paper studies an operation strategy for a single-phase grid-connected 3LT-type qZSI to regulate the active and reactive power flows. This topology is quite promising in photovoltaic system. The different elements are properly calculated, providing simulation results with a good concordance with the theoretical predictions.

2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand, 27-30 Oct. 2019, Elderly population is increasing year after year in the developed countries. However, the knowledge of actual mobility needs of senior drivers is scarce. In this paper, we present a naturalistic driving study (NDS) focused on older drivers through smartphone technology and using our DriveSafe app. Our system automatically generates a driving analysis report based on objective indicators. The proposal supposes an improvement over the traditional surveys and observers, and represents an advance over the current NDSs by using smartphones instead of complex instrumented vehicles. Our method avoids the problems of manual annotation by using an automatic method for data reduction information. Furthermore, a comparison between traditional questionnaires and information provided by our system is carried out and conclusions are presented., Ministerio de Economía y Competitividad, Dirección General de Tráfico, Comunidad de Madrid

In this paper a detailed analysis of a bidirectional buck boost converter used for charging/discharging a supercapacitor is carried out. The analysis takes into account conduction parameters of semiconductors and resistances of inductors, determining the variation of different performance indeces when the charge (and voltage) of supercapacitor varies.

This work proposes a new method for face and mouth tracking using video cameras. This method has been proposed to be used in intelligent spaces as an initial stage to provide information to higher level applications. The method incorporates the classifiers of the Viola and Jones detection method, modified to provide a probabilistic output previously proposed by the authors, useful for tracking with particle filter. The method combines classifiers trained to detect specific poses (frontal and side face views), building an independent likelihood model of pose changes. We also propose to combine the model in several cameras to allow the mouth tracking in a three-dimensional space. The system has been evaluated on the AV16.3 database sequences showing good results in both precision and recall when using a single camera (in a bidimensional space), and an error below 3cm when using three cameras (in a three-dimensional space).

2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France, 9-12 June 2019, Pixel-wise semantic segmentation unifies distinct scene perception tasks in a coherent way, and has catalyzed notable progress in autonomous and assisted navigation, where a whole surrounding perception is vital. However, current mainstream semantic segmenters are normally benchmarked against datasets with narrow Field of View (FoV), and most visionbased navigation systems use only a forward-view camera. In this paper, we propose a Panoramic Annular Semantic Segmentation (PASS) framework to perceive the entire surrounding based on a compact panoramic annular lens system and an online panorama unfolding process. To facilitate the training of PASS models, we leverage conventional FoV imaging datasets, bypassing the effort entailed to create dense panoramic annotations. To consistently exploit the rich contextual cues in the unfolded panorama, we adapt our real-time ERF-PSPNet to predict semantically meaningful feature maps in different segments and fuse them to fulfill smooth and seamless panoramic scene parsing. Beyond the enlarged FoV, we extend focal length-related and style transfer-based data augmentations, to robustify the semantic segmenter against distortions and blurs in panoramic imagery. A comprehensive variety of experiments demonstrates the qualified robustness of our proposal for realworld surrounding understanding., Ministerio de Economía y Competitividad, Comunidad de Madrid

2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France, 9-12 Jun. 2019, Perception in autonomous vehicles has progressed exponentially in the last years thanks to the advances of visionbased methods such as Convolutional Neural Networks (CNNs). Current deep networks are both efficient and reliable, at least in standard conditions, standing as a suitable solution for the perception tasks of autonomous vehicles. However, there is a large accuracy downgrade when these methods are taken to adverse conditions such as nighttime. In this paper, we study methods to alleviate this accuracy gap by using recent techniques such as Generative Adversarial Networks (GANs). We explore diverse options such as enlarging the dataset to cover these domains in unsupervised training or adapting the images on-the-fly during inference to a comfortable domain such as sunny daylight in a pre-processing step. The results show some interesting insights and demonstrate that both proposed approaches considerably reduce the domain gap, allowing IV perception systems to work reliably also at night., Ministerio de Economía y competitividad, Comunidad de Madrid

This paper presents a general framework for the definition and management of cooperative missions for multiple Unmanned Aircraft Systems (UAS) based on the Robot Operating System (ROS). This framework makes transparent the type of autopilot on-board and creates the state machines that control the behaviour of the different UAS from the specification of the multi-UAS mission. In addition, it integrates a virtual world generation tool to manage the information of the environment and visualize the geometrical objects of interest to properly follow the progress of the mission. The framework supports the coexistence of software-in-the-loop, hardware-in-the-loop and real UAS cooperating in the same arena, being a very useful testing tool for the developer of UAS advanced functionalities. To the best of our knowledge, it is the first framework which endows all these capabilities. The paper also includes simulations and real experiments which show the main features of the framework.

Pixel-wise semantic segmentation is capable of unifying most of driving scene perception tasks, and has enabled striking progress in the context of navigation assistance, where an entire surrounding sensing is vital. However, current mainstream semantic segmenters are predominantly benchmarked against datasets featuring narrow Field of View (FoV), and a large part of vision-based intelligent vehicles use only a forward-facing camera. In this paper, we propose a Panoramic Annular Semantic Segmentation (PASS) framework to perceive the whole surrounding based on a compact panoramic annular lens system and an online panorama unfolding process. To facilitate the training of PASS models, we leverage conventional FoV imaging datasets, bypassing the efforts entailed to create fully dense panoramic annotations. To consistently exploit the rich contextual cues in the unfolded panorama, we adapt our real-time ERF-PSPNet to predict semantically meaningful feature maps in different segments, and fuse them to fulfill panoramic scene parsing. The innovation lies in the network adaptation to enable smooth and seamless segmentation, combined with an extended set of heterogeneous data augmentations to attain robustness in panoramic imagery. A comprehensive variety of experiments demonstrates the effectiveness for real-world surrounding perception in a single PASS, while the adaptation proposal is exceptionally positive for state-of-the-art efficient networks., Ministerio de Economía y Competitividad, Comunidad de Madrid

2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand, 27-30 Oct. 2019., This paper presents two new approaches to detect surrounding vehicles in 3D urban driving scenes and their corresponding Bird’s Eye View (BEV). The proposals integrate two state-of-the-art Convolutional Neural Networks (CNNs), such as YOLOv3 and Mask-RCNN, in a framework presented by the authors in [1] for 3D vehicles detection fusing semantic image segmentation and LIDAR point cloud. Our proposals take advantage of multimodal fusion, geometrical constrains, and pre-trained modules inside our framework. The methods have been tested using the KITTI object detection benchmark and comparison is presented. Experiments show new approaches improve results with respect to the baseline and are on par with other competitive state-of-the-art proposals, being the only ones that do not apply an end-to-end learning process. In this way, they remove the need to train on a specific dataset and show a good capability of generalization to any domain, a key point for self-driving systems. Finally, we have tested our best proposal in KITTI in our driving environment, without any adaptation, obtaining results suitable for our autonomous driving application., Ministerio de Economía y Competitividad, Comunidad de Madrid

Intersection navigation comprises one of the major ingredient of Intelligent Transportation Systems (ITS) for Visually Impaired Pedestrians (VIP), who are the most vulnerable road users that should be protected with a high priority in metropolitan areas. Robotic vision-based assistive technologies sprung up over the past few years, which focused on specific scene objects using monocular detectors or depth sensors. These dividual solutions have reached impressive detectable range and accuracy with relatively short running time, and enhanced the intersection perception to a large degree. However, simultaneously enabling all detectors incurs a long delay and becomes computationally prohibitive on wearable embedded systems. In this work, we propose to seize CNN-based per-pixel semantic segmenter to cover navigational perception needs in a unified way. This is not only critical to perceive crosswalk position (where to cross roads), traffic light signal (when to cross roads), but also to analyze the states of other pedestrians and vehicles (whether safe to cross roads). At the centroid of our unification proposal is a deep learning architecture, aspired to attain efficient and robust semantic understanding. A comprehensive variety of experiments demonstrates the advanced accuracy over state-of-art algorithms/segmenters while maintaining high inference speed on a real-world navigation assistance system.

Traversability perception constitutes an important task for robotics and visually impaired people, which aims to detect obstacle-free paths that allow individuals to ambulate with suitable navigational aids. However, approaches that help prevent stepping into water areas are rare in state-of-art autonomous or assisted navigation systems. To address water hazard detection, this paper proposes a pRGB-D-SS perception framework, which incorporates: Polarization imaging (p), RGB-D sensory awareness and real-time Semantic Segmentation (SS). More specifically, as large water areas and small water puddles exhibit different characteristics, the detection of these two kinds of hazards pursue different pipelines. In our contribution, large water areas are detected together with traversable areas through pixel-wise semantic segmentation. Comparatively, the detection of water puddles extends the convolutional neural network based segmentation by using polarized RGB-D information as the primary cue. Beyond enhanced traversability awareness, it enables a unified framework of water hazard detection, which has been evaluated in a comprehensive variety of real-world surroundings on two wearable systems including a pair of commercial intelligent spectacles and a customized prototype, demonstrating the speeded-up efficiency and augmented sensorial/environmental robustness.

Semantic perception is a key enabler in robotics, which supposes a very resourceful and efficient manner of applying vision information for upper-level navigation and manipulation tasks. Given the challenges on specular semantics such as water hazards, transparent glasses and metallic surfaces, polarization imaging has been explored to complement the RGB-based pixel-wise semantic segmentation because it reflects surface characteristics and provides additional attributes. However, polarimetric measurements generally entail prohibitively expensive cameras and highly accurate calibrations. Inspired by the representation power of Convolutional Neural Networks (CNNs), we propose to predict polarization information from monocular RGB images, precisely per-pixel polarization difference. The core of our approach is a cluster of efficient deep architectures building on factorized convolutions, hierarchical dilations and pyramid representations, aimed to produce both semantic and polarimetric estimations in real time. Comprehensive experiments demonstrate the qualified accuracy on a wearable exoskeleton humanoid robot.

This paper presents a real-time approach to detect and localize surrounding vehicles in urban driving scenes. We propose a multimodal fusion framework that processes both 3D LIDAR point cloud and RGB image to obtain robust vehicle position and size in a Bird's Eye View (BEV). Semantic segmentation from RGB images is obtained using our efficient Convolutional Neural Network (CNN) architecture called ERFNet. Our proposal takes advantage of accurate depth information provided by LIDAR and detailed semantic information processed from a camera. The method has been tested using the KITTI object detection benchmark. Experiments show that our approach outperforms or is on par with other state-of-the-art proposals but our CNN was trained in another dataset, showing a good generalization capability to any domain, a key point for autonomous driving.

This work presents an energy management strategy based on scheduling battery operation in prosumer systems, according to forecast data available 24 hours in advance. The proposed method seeks to reach a beneficial compromise between prosumers and distribution grid operators, independently of specific economic context or technical regulations. An improvement to deal with forecast inaccuracy is carried out. Results demonstrate that it offers good properties regarding energy management, with a stored energy reserve estimation, battery lifetime preservation and self-consumption and self-sufficiency enhancement.

Intelligent Vehicles (IV) and navigational assistance for the Visually Impaired (VI) are becoming highly coupled, both fulfilling safety-critical tasks towards the utopia of all traffic participants. In this paper, the main purpose is to leverage recently emerged methods for self-driving technology, and transfer them to augment perception and aid navigation in ambient assisted living. More precisely, we put forward to seize pixel-wise semantic segmentation to support curb negotiation and traversability awareness, along the pathway of visually impaired individuals. At the crux of our perception unification framework is an effort to attain efficient understanding by proposing a deep architecture built on residual factorized convolution and pyramidical representation. A comprehensive set of experiments demonstrates the accurate scene parsing results with promise of real-time inference speed. Crucially, real-world performance over state-of-art approaches qualifies the proposed framework for assistance when deployed to two wearable navigation systems, including a pair of commercial smart glasses and a prototype of customized device.

Semantic Segmentation methods play a key role in today’s Autonomous Driving research, since they provide a global understanding of the traffic scene for upper-level tasks like navigation. However, main research efforts are being put on enlarging deep architectures to achieve marginal accuracy boosts in existing datasets, forgetting that these algorithms must be deployed in a real vehicle with images that were not seen during training. On the other hand, achieving robustness in any domain is not an easy task, since deep networks are prone to overfitting even with thousands of training images. In this paper, we study in a systematic way what is the gap between the concepts of “accuracy” and “robustness”. A comprehensive set of experiments demonstrates the relevance of using data augmentation to yield models that can produce robust semantic segmentation outputs in any domain. Our results suggest that the existing domain gap can be significantly reduced when appropriate augmentation techniques regarding geometry (position and shape) and texture (color and illumination) are applied. In addition, the proposed training process results in better calibrated models, which is of special relevance to assess the robustness of current systems.

Active research on computer vision accelerates the progress in autonomous driving. Following this trend, we aim to leverage the recently emerged methods for Intelligent Vehicles (IV), and transfer them to develop navigation assistive technologies for the Visually Impaired (VI). This topic grows notoriously challenging as it requires to detect a variety of scenes towards higher level of assistance. Computer vision based techniques with monocular detectors or depth sensors sprung up within years of research. These separate approaches achieved remarkable results with relatively low processing time, and improved the mobility of visually impaired people to a large extent. However, running all detectors jointly increases the latency and burdens the computational resources. In this paper, we put forward to seize pixel-wise semantic segmentation to cover the perception needs of navigational assistance in a unified way. This is critical not only for the terrain awareness regarding traversable areas, sidewalks, stairs and water hazards, but also for the avoidance of short-range obstacles, fast-approaching pedestrians and vehicles. At the heart of our proposal is a combination of efficient residual factorized network (ERFNet), pyramid scene parsing network (PSPNet) and 3D point cloud based segmentation. This approach proves to be with qualified accuracy and speed for real-world applications by a comprehensive set of experiments on a wearable navigation system.