INESC TEC Repository
Not a member yet
2130 research outputs found
Sort by
Simultaneous Underwater Navigation and Mapping
Get PDFThe use of underwater autonomous vehicles has been growing, allowing the performance of tasks that cause inherent risks to Human, namely in inspection processes near to structures. With growth in usage of systems with autonomous navigation, visual acquisition methods have also gotten more developed because, they have appealing cost and they also show interesting results when operate at a short distance. It is possible to improve the quality of navigation through visual SLAM techniques which can map and locate simultaneously and its key aspect is the detection of revisited areas. These techniques are not usually applied to underwater scenarios and, therefore, its performance in environment is unknown. The paper presents a more reliable navigation system for underwater vehicles, resorting to some visual SLAM techniques from literature. The results, conducted in a realistic scenario, demonstrated the ability of the system to be applied to underwater environment.</jats:p
MixAR
No full textMixAR, a full-stack system capable of providing visualization of virtual reconstructions seamlessly integrated in the real scene (e.g. upon ruins), with the possibility of being freely explored by visitors, in situ, is presented in this article. In addition to its ability to operate with several tracking approaches to be able to deal with a wide variety of environmental conditions, MixAR system also implements an extended environment feature that provides visitors with an insight on surrounding points-of-interest for visitation during mixed reality experiences (positional rough tracking). A procedural modelling tool mainstreams augmentation models production. Tests carried out with participants to ascertain comfort, satisfaction and presence/immersion based on an in-field MR experience and respective results are also presented. Ease to adapt to the experience, desire to see the system in museums and a raised curiosity and motivation contributed as positive points for evaluation. In what regards to sickness and comfort, the lowest number of complaints seems to be satisfactory. Models' illumination/re-lightning must be addressed in the future to improve the user's engagement with the experiences provided by the MixAR system.</jats:p
Map-Matching Algorithms for Robot Self-Localization: A Comparison Between Perfect Match, Iterative Closest Point and Normal Distributions Transform
Get PDFThe self-localization of mobile robots in the environment is one of the most fundamental problems in the robotics navigation field. It is a complex and challenging problem due to the high requirements of autonomous mobile vehicles, particularly with regard to the algorithms accuracy, robustness and computational efficiency. In this paper, we present a comparison of three of the most used map-matching algorithms applied in localization based on natural landmarks: our implementation of the Perfect Match (PM) and the Point Cloud Library (PCL) implementation of the Iterative Closest Point (ICP) and the Normal Distribution Transform (NDT). For the purpose of this comparison we have considered a set of representative metrics, such as pose estimation accuracy, computational efficiency, convergence speed, maximum admissible initialization error and robustness to the presence of outliers in the robots sensors data. The test results were retrieved using our ROS natural landmark public dataset, containing several tests with simulated and real sensor data. The performance and robustness of the Perfect Match is highlighted throughout this article and is of paramount importance for real-time embedded systems with limited computing power that require accurate pose estimation and fast reaction times for high speed navigation. Moreover, we added to PCL a new algorithm for performing correspondence estimation using lookup tables that was inspired by the PM approach to solve this problem. This new method for computing the closest map point to a given sensor reading proved to be 40 to 60 times faster than the existing k-d tree approach in PCL and allowed the Iterative Closest Point algorithm to perform point cloud registration 5 to 9 times faster. © 2018 Springer Science+Business Media B.V., part of Springer Natur
Optimal bidding strategy for an aggregator of prosumers in energy and secondary reserve markets
Get PDFIntegrated planning of inbound and outbound logistics with a Rich Vehicle Routing Problem with Backhauls
No full textA data-driven particle filter for terrain based navigation of sensor-limited autonomous underwater vehicles
No full textDevelopment of an Electrohydraulic Variable Buoyancy System
Get PDFThe growing needs in exploring ocean resources have been pushing the length and complexity of autonomous underwater vehicle (AUV) missions, leading to more stringent energy requirements. A promising approach to reduce the energy consumption of AUVs is to use variable buoyancy systems (VBSs) as a replacement or complement to thruster action, since VBSs only require energy consumption during limited periods of time to control the vehicle's floatation. This paper presents the development of an electrohydraulic VBS to be included in an existing AUV for shallow depths of up to 100 m. The device's preliminary mechanical design is presented, and a mathematical model of the device's power consumption is developed, based on data provided by the manufacturer. Taking a standard mission profile as an example, a comparison between the energy consumed using thrusters and the designed VBS is presented and compared
Learning Preferential Perceptual Exposure for HDR Displays
Get PDFHigh dynamic range (HDR) displays are capable of displaying a wider dynamic range of values than conventional displays. As HDR content becomes more ubiquitous, the use of these displays is likely to accelerate. As HDR displays can present a wider range of values, traditional strategies for mapping HDR content to low dynamic range (LDR) displays can be replaced with either directly displaying values, or using a simple shift mapping (exposure adjustment). The latter approach is especially important when considering ambient lighting, as content viewed in a dark environment may appear substantially different to a bright one. This paper seeks to identify an exposure value which is suitable for displaying specific HDR content on an HDR display under a range of ambient lighting levels. Based on data captured with human participants, this paper establishes user preferred exposure values for a variety of maximum display brightnesses, content and ambient lighting levels. These are then used to develop two models to predict preferred exposure. The first is based on linear regression using straightforward image statistics which require minimal computation and memory to be computed, making this method suitable to be directly used in display hardware. The second is a model based on convolutional neural networks (CNN) to learn image features which best predict exposure values. The CNN model generates better results than the first model at the cost of memory and computation time. © 2013 IEEE
Validating the Hybrid ERTMS/ETCS Level 3 concept with Electrum
Get PDFThis paper reports on the development of a formal model for the Hybrid ERTMS/ETCS Level 3 concept in Electrum, a lightweight formal specification language that extends Alloy with mutable relations and temporal logic operators. We show how Electrum and its Analyzer can be used to perform scenario exploration to validate this model, namely to check that all the operational scenarios described in the reference document are admissible, and to reason about expected safety properties, which can be easily specified and model checked for arbitrary track configurations. We also show how the Analyzer can be used to depict scenarios (and counter-examples) in a graphical notation that is logic-agnostic, making them understandable by stakeholders without expertise in formal specification. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature
USING VIRTUAL SCENARIOS TO PRODUCE MACHINE LEARNABLE ENVIRONMENTS FOR WILDFIRE DETECTION AND SEGMENTATION
Get PDF<p><strong>Abstract.</strong> Today’s climatic proneness to extreme conditions together with human activity have been triggering a series of wildfire-related events that put at risk ecosystems, as well as animal and vegetal patrimony, while threatening dwellers nearby rural or urban areas. When intervention teams - firefighters, civil protection, police - acknowledge these events, usually they have already escalated to proportions hardly controllable mainly due wind gusts, fuel-like solo conditions, among other conditions that propitiate fire spreading.</p> <p>Currently, there is a wide range of camera-capable sensing systems that can be complemented with useful location data - for example, unmanned aerial systems (UAS) integrated cameras and IMU/GPS sensors, stationary surveillance systems - and processing components capable of fostering wildfire events detection and monitoring, thus providing accurate and faithful data for decision support. Precisely in what concerns to detection and monitoring, Deep Learning (DL) has been successfully applied to perform tasks involving classification and/or segmentation of objects of interest in several fields, such as Agriculture, Forestry and other similar areas. Usually, for an effective DL application, more specifically, based on imagery, datasets must rely on heavy and burdensome logistics to gather a representative problem formulation. What if putting together a dataset could be supported in customizable virtual environments, representing faithful situations to train machines, as it already occurs for human training in what regards some particular tasks (rescue operations, surgeries, industry assembling, etc.)?</p> <p>This work intends to propose not only a system to produce faithful virtual environments to complement and/or even supplant the need for dataset gathering logistics while eventually dealing with hypothetical proposals considering climate change events, but also to create tools for synthesizing wildfire environments for DL application. It will therefore enable to extend existing fire datasets with new data generated by human interaction and supervision, viable for training a computational entity. To that end, a study is presented to assess at which extent data virtually generated data can contribute to an effective DL system aiming to identify and segment fire, bearing in mind future developments of active monitoring systems to timely detect fire events and hopefully provide decision support systems to operational teams.</p>
</jats:p