Piksel (Italy)

AI-eXpress (AIX) is an AI-enabled flight acquisition and processing framework, that embarks on satellites and then brings into the market a new concept of satellite a service. AIX makes available in-orbit resources/services on-demand: services shall include EO data acquisition, processing (i.e., actionable information extraction), downlink, and distribution. Ready-made applications (e.g., fire detection and warning service) will be available on a dedicated app store, and services can be also combined to build custom applications. Valuable information can be then transferred back to Earth as notifications and alerts, or directly exploited on-board in autonomous decisions workflows. The data that is demonstrated to be not relevant to user applications can be processed and then deleted, thus freeing space in memory and using less bandwidth. Furthermore, emerging NewSpace companies may now test their innovative AI algorithms and their proof-of-concept directly in space and prove their value to the market. Traditional space institutions and research entities may test a new approach changing from “makers” to “enablers”. AIX is developed, by Planetek Italia, D-Orbit and AIKO within the ESA Incubed program and the services will be available from Q4\2024.

FUTURE is an Italian mission designed to redefine autonomous navigation by exclusively relying on visual observations, eliminating the need for conventional ranging measurements and Global Navigation Satellite System (GNSS) dependencies. The mission is developed in the frame of the ALCOR program [1] of the Italian Space Agency. FUTURE LEO nanosatellite mission has the objective to demonstrate in orbit the capability of determining the spacecraft orbit with only visual observation, without relying on radiometric measurements (range and range-rate), or on the GNSS positioning systems. Given the current state of the art, this project enhances autonomous navigation capabilities in LEO via natural and artificial features on the surface of the Earth. This project can prove an innovative low-cost and autonomous navigation technique possibly applicable to any planetary orbiter. By orbiting in LEO, it was possible to exploit available GNSS signals as a source of truth, to validate the performance and of the payload data. Furthermore, opportunistic observations with other celestial objects, or in different observation spectrum ranges (Thermal IR), can be carried out to validate autonomous navigation techniques spanning different scales. The solution will make use of state of art automation algorithms, sensors, processing units and software solutions to obtain spacecraft position and velocity information. The proposed mission is composed by one Tyvak 6U nanosatellite based on the Triumph platform and leverages the extensive background of the consortium in on-board image processing, artificial intelligence and navigation. The payload hardware and the software were traded off and selected during the preliminary design phase of the project, considering different options available with relative advantages and disadvantages. The payload hardware will be provided by Tyvak, while the payload software and algorithms will be developed and provided by AIKO and Politecnico di Milano. Finally, a combination of Tyvak’s and ALTEC’s ground infrastructure will be used, to operate the spacecraft, validate the effective performance of the systems and the fulfilment of mission objectives.

Abstract The European Green Deal and its target to achieve a 90% reduction in transport-related greenhouse gas emissions by 2050 together with the new European Union Urban Mobility Framework put urban mobility and logistics in the spotlight of European mobility policies. Research and innovation are paramount to respond to the challenges and to further improve mobility and transport systems in cities, while fully tackling the negative impacts of transport. This study provides a review of recent trends, challenges and achievements of European research and innovation initiatives in urban mobility and logistics and examines their alignment with the overarching transport and mobility policy objectives. The paper identifies relevant projects that focus on urban mobility, using the Transport Research and Innovation Monitoring and Information System (TRIMIS) database. It identifies the main trends in European research and discusses main areas of development and key achievements. It also presents recommendations for future research priorities and initiatives.

Radio Frequency Fingerprinting (RFF) refers to the technique for identifying and classifying wireless devices on the basis of their physical characteristics, which appear in the digital signal transmitted in space. Small differences in the radio frequency front-end of the wireless devices are generated across the same wireless device model during the implementation and manufacturing process. These differences create small variations in the transmitted signal, even if the wireless device is still compliant with the wireless standard. By using data analysis and machine-learning algorithms, it is possible to classify different electronic devices on the basis of these variations. This technique has been well proven in the literature, but research is continuing to improve the classification performance, robustness to noise, and computing efficiency. Recently, Deep Learning (DL) has been applied to RFF with considerable success. In particular, the combination of time-frequency representations and Convolutional Neural Networks (CNN) has been particularly effective, but this comes at a great computational cost because of the size of the time-frequency representation and the computing time of CNN. This problem is particularly challenging for wireless standards, where the data to be analyzed is extensive (e.g., long preambles) as in the case of the LoRa (Long Range) wireless standard. This paper proposes a novel approach where two pre-processing steps are adopted to (1) improve the classification performance and (2) to decrease the computing time. The steps are based on the application of Variational Mode Decomposition (VMD) where (in opposition to the known literature) the residual of the VMD application is used instead of the extracted modes. The concept is to remove the modes, which are common among the LoRa devices, and keep with the residuals the unique intrinsic features, which are related to the fingerprints. Then, the spectrogram is applied to the residual component. Even after this step, the computing complexity of applying CNN to the spectrogram is high. This paper proposes a novel step where only segments of the spectrogram are used as input to CNN. The segments are selected using a machine-learning approach applied to the features extracted from the spectrogram using the Local Binary Pattern (LBP). The approach is applied to a recent LoRa radio frequency fingerprinting public data set, where it is shown to significantly outperform the baseline approach based on the full use of the spectrogram of the original signal in terms of both classification performance and computing complexity.

Abstract The present contribution provides preliminary empirical findings concerning the first-in-literature independent experimental characterization of a commercially viable automated driving system in Europe. In particular, the paper reports on the testing campaign involving a type-approved Automated Lane Keeping System (ALKS) equipped vehicle and its comparison with the comparable driving assistance feature technology from the same vehicle: the Adaptive Cruise Control (ACC) system. The results suggest that the ALKS shows substantially enhanced performances with respect to ACC. In particular, both the string stability metrics and the reaction time show remarkable improvements. Additionally, the increased stability is not obtained via resorting to a significantly higher time gap which further motivates that string stable car-following is indeed feasible.

<div class="section abstract"><div class="htmlview paragraph">The EU projects reaching net-zero emissions by 2050, thus reducing CO<sub>2</sub> emissions is a priority in the European Climate Law published in 2021. The transport sector is the second contributor to CO<sub>2</sub>, responsible for around 26% of EU greenhouse gasses emissions. In 2020, GHG (greenhouse gas) emissions from transport in the EU have dropped by 12.7% due to the COVID-19 pandemic. As society comes back to normality, vehicles use is increasing again. To reach the emission targets, new vehicles can introduce CO<sub>2</sub>-reducing eco-innovative technologies. So far, these technologies accepted under WLTP are light-emitting diodes and efficient alternators. Nevertheless, many other technologies have potential as eco-innovations. In the past, eco-innovative technologies have contributed to reducing EU CO<sub>2</sub> emissions. In 2018, the fleet of newly registered cars with eco-innovations saved around 11000 tonnes of CO<sub>2</sub>. An increasing tendency is seen in 2019: 21000 tonnes of CO<sub>2</sub> were saved at fleet level. During 2020, new car registrations with eco-innovations were higher, having the potential to save around 40000 tonnes of CO<sub>2</sub> at fleet level. Despite their positive impact, their CO<sub>2</sub>-reducing effect can be diminished when two of these technologies interact with each other. The presence of the lighting system and the alternator lowers the CO<sub>2</sub> savings if compared to the summation of the savings of each technology separately. The impact of the interactions of approved eco-innovations can imply a decrease of 9% of the sum of the CO<sub>2</sub> savings from each technology considered independent from the other.</div></div>

Mandatory targets are set in Europe for Carbon Dioxide (CO2) emissions of light-duty vehicles. EU law recognises the potential of certain innovative technologies to contribute to reducing CO2 emissions. Vehicle systems and innovations are becoming increasingly complex, and the accurate quantification of their benefits increasingly difficult. The study investigates the potential of the CO2MPAS simulator to serve this purpose. Two innovative technologies were studied, Light-emitting diode (LED) lighting systems, efficient alternators (EA), and their combination. The model was validated on detailed test results from eight vehicles. A total of 452 passenger cars, for which test data were available, were subsequently simulated using CO2MPAS simulator. The mean simulated CO2 savings was 0.91gCO2/km (LED lights), 0.98 gCO2/km (EA), and 1.78 gCO2/km (combined). Results show that simulated CO2 savings were comparable to those calculated using the existing standardised method. For gasoline and diesel vehicles respectively, the difference in CO2 savings between simulated and existing method was 2.8% and 0.14% in the LED lights case, and 0.6% and 0.67% in the alternator case. In the combined case, the difference was calculated to be 1.7% and 0.34%. Similar approaches could be used in the future for accurately capturing the benefits of more complex technologies.

The availability of large amounts of Sentinel-2 data has been a trigger for its increasing exploitation in various types of applications. It is, therefore, of importance to understand the limits above which these data still guarantee a meaningful outcome. This paper proposes a new method to quantify and specify restrictions of the Sentinel-2 imagery in the context of checks by monitoring, a newly introduced control approach within the European Common Agriculture Policy framework. The method consists of a comparison of normalized difference vegetation index (NDVI) time series constructed from data of different spatial resolution to estimate the performance and limits of the coarser one. Using similarity assessment of Sentinel-2 (10 m pixel size) and PlanetScope (3 m pixel size) NDVI time series, it was estimated that for 10% out of 867 fields less than 0.5 ha in size, Sentinel-2 data did not provide reliable evidence of the activity or state of the agriculture field over a given timeframe. Statistical analysis revealed that the number of clean or full pixels and the proportion of pixels lost after an application of a 5-m (1/2 pixel) negative buffer are the geospatial parameters of the field that have the highest influence on the ability of the Sentinel-2 data to qualify the field’s state in time. We specified the following limiting criteria: at least 8 full pixels inside a border and less than 60% of pixels lost. It was concluded that compliance with the criteria still assures a high level of extracted information reliability. Our research proved the promising potential, which was higher than anticipated, of Sentinel-2 data for the continuous state assessment of small fields. The method could be applied to other sensors and indicators.

The Global Human Settlement Layer (GHSL) produces new global spatial information, evidence-based analytics and knowledge describing the human presence on the planet based mainly on two quantitative factors: i) the spatial distribution (density) of built-up structures and ii) the spatial distribution (density) of resident people. Both factors are observed in the long-term temporal domain and per uniform surface units in order to support trends and indicators for monitoring the implementation of international framework agreements. The GHSL uses various input data including global, multi-temporal archives of fine-scale satellite imagery, census data, and volunteered geographic information. In this paper, we present the characteristics of GHSL information to demonstrate how original frameworks of data and tools rooted on Earth Observation could support Sustainable Development Goals monitoring. In particular, we demonstrate the reach of gridded, open and free, local yet globally consistent, multi-temporal data in filling the data gap for the Sustainable Development Goal 11. Our experiments produce a global estimate for the Land Use Efficiency indicator (SDG 11.3.1) for 10,000 urban centers, calculating the ratio of land consumption to population growth rate that took place between 1990 and 2015. The results of our research demonstrate that there is a potential to lift SDG 11.3.1 from a tier 2 as GHSL provides a global baseline for the essential variables called by the SDG 11.3.1 metadata.

A global navigation satellite system (GNSS)-based navigation is a challenging task in a signal-degraded environments where GNSS signals are distorted by multipath and attenuated by fading effects: the navigation solution may be inaccurate or unavailable. A possible approach to improve accuracy and availability is the joint use of measurements from different GNSSs and quality check algorithms; this approach is investigated here using live GPS and Galileo signals. A modified receiver autonomous integrity monitoring (RAIM) algorithm, including geometry and separability checks, is proposed to detect and exclude erroneous measurements: the multi-constellation approach provides redundant measurements, and RAIM exploits them to exclude distorted observations. The synergy between combined GPS/Galileo navigation and RAIM is analyzed using live data; the performance is compared to the accuracy and availability of a GPS-only solution. The tests performed demonstrate that the methods developed are effective techniques for GNSS-based navigation in signal-degraded environments. The joint use of the multi-constellation approach and of modified RAIM algorithms improves the performance of the navigation system in terms of both accuracy and availability.