Project Listing

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 weren’t 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.
This research line proposes to analyze different techniques to be applied to existing deep networks in order to improve their robustness when deployed in any domain. Our proposal is to analyze semi-supervised methods in this context with the aim of implementing real applications for autonomous vehicles.

The main research line of the group is Machine Learning approaches for analyzing and designing Renewable Energy systems, including Wind, Solar and Marine Energy Systems.

One significant line of research of the group focuses on micro-grid (MG) design and optimization problems in smart grids using meta-heuristics and Machine Learning approaches. We are also interested in the application of novel soft computing techniques to smart grids challenges.

Faced with the current global challenges of sustainable development and the mitigation of climate change, there is an urgent need for a transition from the currently dominant linear economy towards a circular economy (CE). here exists a lack of consensus regarding what constitutes a “circular city”, and also the need to determine yet further the rationales and the ways forward how to transform cities towards circular models. With the aim of helping to meet this need, our research will precisely explore these issues by conducting research at three different but interconnected areas: 1. Field Research. The project involves the need to gather new data from relevant public urban institutions and corporate stakeholders by means of a field survey, meetings and interviews. 2. Modelling and Analysis. Upon gathering the data from the field research, our team of researchers will conduct a comprehensive analysis and diagnosis of the inputs. 3. Guidelines and Decision Support. Findings of the field research, modelling and analysis are brought to the scrutiny of the representatives of public and private organizations.

The development of systems for remote sensing is relevant to several applications such as leak detection in industry. Ultrafast fiber lasers represent a reliable source for this application, as they show a stable and with wide-spectrum emission. This Project aims to apply nitride-based ultrafast lasers developed by the Photonics Engineering Group of the University of Alcalá to remote gas detection in energy-production industry. These lasers attains high peak power (in the range of tens KW) linked to ultrashort pulse width (below 200 fs), emitting a powerfull pulsed beam spectraly centred at 1.56 µm, where gases like NH3, CO, CO2 and H2S show important absorption lines.

To promote innovations toward solving energy and environmental problems that are expanding on a global scale today is a difficult challenge for scientists and engineers. Much effort is needed to develop technologies that reduce CO2 emissions and help to overcome the present society depending on fossil fuels as primary energy. Hydrogen has attracted increasing attention as an alternative secondary energy resource, because the reaction of hydrogen with oxygen produces the requested energy and only water as by-product. However, storage and transportation of hydrogen is a difficult issue. Chemistry offers a convenient solution to this problem. This research line aims to offer new possibilities to overcome the energetic problem by using metal-based catalysts for hydrogen storage as a tool. We are looking for talented researchers interested in developing materials for energy efficiency and renewable energy applications based on transition-metal complexes or chemistry.

Climate change and energy shortage represent some of the greatest challenges for humanity. The use of fossil fuels has a significant adverse impact on the environment and is considered a critical cause of global climate change. Therefore, the development of clean and renewable energy is the key way to meet the increasing global energy requirement and to resolve the environmental problems caused by the overuse of large amounts of fossil fuels. Visible-light photoredox catalysis uses visible light as a renewable energy source to promote chemical transformations involving electron transfers. There is an urgent need for clean and renewable fuel so that the development of good catalysts and its assembly into a cell for the photoproduction of hydrogen is seen as one of the most promising sustainable solutions for our present demands. The most used complexes in visible light photocatalysis by their excellent photophysical properties are ruthenium and iridium polypyridyl complexes although their high cost and potential toxicity, causing disadvantages on a big scale. Although great advances have been made in the development of photocatalysts for their application in water splitting, photovoltaic cells, solar energy storage and catalysis, development of new photocatalysts to get more efficient transformations is mandatory and will be the topic of this project.

Photon upconversion, the process wherein light of long wavelength is frequency converted to photons of higher energy, is readily achieved at low incident power through sensitized triplet–triplet annihilation (TTA) in various chromophore combinations spanning the UV to the near-IR. This emerging wavelength-shifting technology truly represents a viable route towards converting low energy terrestrial solar photons into light adequate to drive electron transfer in operational photovoltaics. One of the many possible applications of an efficient and high-energy photon up-conversion would be its use as an elegant way to increase the efficiency of various solar cells. This research will focus on two different families of emitter compounds generated by the replacement of a carbon of a polycyclic aromatic hydrocarbon (PAH) by a heteroatom: azonia aromatic cations (AZAC), if a nitrogen is employed, and azaborines, formally generated by replacing a C=C unit in a PAH with an isoelectronic B−N unit.

The main target of this research project is to deploy robust solutions for automatic activity detection in extended videos. Typically, an advanced intelligent transportation system needs to work with long videos, that normally arrive in an online fashion. These extended videos contain significant spans without any activities and intervals with potentially multiple concurrent fine grained activities. Therefore, it results fundamental to research on novel online methods for the task of activity detection and to implement solutions for the problem of concurrent fine-grained activity detection. This fine-grained capability will play a fundamental role to envision the new era of smart transportation solutions, where the artificial intelligent agents will be able to interact and interpret the environment in a fine-grained fashion, hence extracting more semantic information.

The main objective of this line of research is to apply the most advanced techniques in artificial intelligence and computer vision to address the development of new intelligent transport and mobility solutions. In particular, we will address the problem of advanced vehicle detection and counting approaches for the problems of: a) smart routing; and b) prediction and management of traffic congestions;