• COVID-19
• Publicationsclose
• Research dataclose
• Research softwareclose
• 2019-2023close
• Closed Access close
• Conference object close
• Transport Research close

Part 5: Autonomous Agents; International audience; Autonomous Vehicles (AVs) can potentially reduce the accident risk while a human is driving. They can also improve the public transportation by connecting city centers with main mass transit systems. The development of technologies that can provide a sense of security to the passenger when the driver is missing remains a challenging task. Moreover, such technologies are forced to adopt to the new reality formed by the COVID-19 pandemic, as it has created significant restrictions to passenger mobility through public transportation. In this work, an image-based approach, supported by novel AI algorithms, is proposed as a service to increase autonomy of non-fully autonomous people such as kids, grandparents and disabled people. The proposed real-time service, can identify family members via facial characteristics and efficiently ignore face masks, while providing notifications for their condition to their supervisor relatives. The envisioned AI-supported security framework, apart from enhancing the trust to autonomous mobility, could be advantageous in other applications also related to domestic security and defense.

When searching a database for a topic (e.g. Covid-19), there may not exist a precise match, especially if the topic is novel. Furthermore, the topic may surface in the data under different guises (‘Covid-19,’ ‘coronavirus,’ ‘pandemic’, etc.). The results of a keyword search are limited by the querier’s imagination and familiarity with the data. Such searches have high precision, but low recall. In order to increase the recall of searches, we present the Semantic Search Pipeline, a novel approach to document retrieval that uses distributional semantic models and locality sensitive hashing to expand queries and efficiently identify other relevant documents that may not contain the obvious query terms. We evaluate the pipeline using a dataset curated from financial customer service call centers, resulting in an increase in recall of 32% over a simple keyword baseline, with a negligible drop in precision. Furthermore, we present the notion of concept forging, a process of tracing a topic or concept through time and through its various surface realizations. Applied to Covid-19, the search pipeline retrieves a set of documents that allow us to uncover the short- and long-term effects of Covid-19 on the lives of the people and businesses impacted by it. Although Covid-19 is a timely test case, our search pipeline is general in nature and can be easily applied to any range of topics.

The next few years will be crucial in shaping significant transitions within the realm of sustainability, with mobility having for sure a crucial share. COVID-19 will strongly impact post-pandemic mobility, as new working habits will partly reshape urban areas, with possibly many people living outside metropolitan realities. Hence, novel mobility models need to emerge, smart enough to answer the multifaceted needs of their users, and of course sustainable and energy efficient. Electric Vehicles (EVs) are crucial to support the shift towards green mobility models, and governments all around the globe are shaping their policies to support EV mass adoption. This paper provides a network-based adoption model, whose multi-class agents are potential EV users modeled based on their driving habits, derived from data measured on instrumented vehicles. The network connections are based on physical proximity among users, and a cascade model is used to investigate the dynamics of the unforced adoption mechanism. Then, a policy-design framework is proposed based on the open-loop analysis, and its cost/benefit effects quantified and discussed.

There is increasing commercial interest in the deployment of autonomous aircraft for both passenger and cargo transport. Indeed, with the need for more human-free deliveries, the COVID19 crisis has led to a sharp spike in drone deliveries. This increased demand is putting additional stress on supporting infrastructure like air traffic control, which is already struggling with outdated technology. The recent 737 MAX crashes also highlight the complexities surrounding the development of aircraft autonomy as well as testing and certification. In order to more precisely determine whether universities are keeping pace with both research and education needs from external stakeholders in terms of aerospace autonomy, we conducted a survey that targeted aerospace leaders in academia, industry, and government. The results show there is a significant gap between the education and research aims of academia and what is needed in industry and government. To fill this gap and maintain international superiority in aerospace autonomy, the US needs to promote the convergence in the fields of computer science and aerospace engineering, as well as safety, cybersecurity, and testing. Without such transformation, the US will not be able to maintain its technological superiority in aerospace systems.

The COVID-19 pandemic accelerated the use, sharing, and distribution of data on a global basis. Higher levels of transparency were achieved with continual updates of pandemic related information. The air transportation sector – while by definition an information rich industry – is a notable exception. While different organizations offered aggregated data on air traffic developments on national or airport level, complementary data on air traffic movements for further analysis are not available publicly. This creates a deadlock between addressing the societal needs of monitoring how aviation recovers from the COVID-19 pandemic and addresses the aspirational environmental goals. This paper investigates the feasibility of utilizing open data for the operational performance monitoring at airports. The exploratory work focusses on a subset of the indicators proposed under ICAO’s Global Air Navigation Plan used to assess the operational performance in the arrival phase. A novel approach to characterize and assess the arrival flow management and level of traffic synchronization is presented. This will allow to evaluate on-going air traffic recovery and identify operational bottlenecks. The study is performed as a use-case analysis for three major European airports by comparing the observed performance in the months of March and May for the successive years 2019, 2020, and 2021. The results demonstrate the general feasibility and utility of open data for operational performance monitoring. The classical performance measure for the arrival flow are determined based on the open trajectory data. A geospatial-temporal evaluation support the tracking of traffic synchronisation effort. A higher level of transparency therefore available to the interested public, policy decision-makers and strategic planners with direct feedback on the recovery and actual operational performance. The suitability of the traffic synchronization measure and its parameterization requires further validation across a wider set of airports and will be iteratively refined.

The intervention focuses on air carriage and on the Italian provisions issued for the benefit of those passengers whose flight has been cancelled by the carrier or of those who decided to cancel themselves, due to the restrictions to travel imposed by Italian Government or to the restrictions imposed by authorities of the port of landing. Particularly, after a brief description of the legislative decrees issued in the subject matter, the focus is on the voucher system put in place by Italian Government and on the recent guidelines of the UE Commission regarding reimbursement and compensation.

The bike-sharing system (BSS) aims to provide an alternative mode of public transportation that are being adopted in urban cities. The use of the bike for short-distance travel aids in mitigating traffic congestion problems, reduce carbon emissions, and decrease the risk of overcrowding during a pandemic like COVID-19, thereby satisfying the urban-mobility needs of the residents. The key success of incorporating urban-mobility through BSS lies behind the prediction of bikes by identifying the pick-up and drop-off operations in each station. The main challenge includes the demand prediction for the number of bikes available for pick-up and drop-off during a specific point in time. Quantum Computing has been increasingly gaining popularity for its superior computational performance over similar classical algorithms. In this paper, we will illustrate potential applications of Quantum Bayesian networks, which are quantum-equivalent to classical Bayesian networks for probabilistic bike demand prediction.

After COVID-19, a full recovery compared to the 2019 situation with a subsequent growth of global air traffic is expected for the next three to six years [1]. Regarding carbon dioxide emissions, Coronavirus lockdown helped the environment to bounce back, but this will be a temporary situation. It is important to continue investigating additional mitigation measurements to achieve long-term environmental benefits, especially after the recovery. At that point, the question of how to reduce aviation's impact on the climate change will certainly arise again, and will re-gain its importance for the world-wide community. Since no fundamental breakthroughs in CO 2 reduction in aviation are expected in the near future, research should focus on several measures to sustainably reduce the environmental impact of aviation. The air traffic management can contribute to an overall reduction of emissions of greenhouse gases by optimizing traffic flows not only towards maximum airspace capacity and maximum efficiency, but also increasingly towards minimum environmental impact. A set of concept elements that were investigated in the frame of the European-Chinese project Greener Air Traffic Operations (GreAT) can already constitute simple and suitable means towards a greener air traffic management. One of these concept elements is the 'Lowest Impact of Deviation' principle: Whenever two flights need to deviate from their most fuel-efficient route, speed or altitude due to de-conflicting, this deviation should be done by the flight with the lowest fuel consumption, and consequently, with the lowest amount of emissions produced with this maneuver. This principle is currently neither reflected in air traffic control regulations, nor in common practices. In the frame of the work presented in this paper, this principle has been further investigated and analyzed with a fast-time simulation, which models a free route airspace environment under ideal conditions. The flights are generated according to a configurable traffic density. De-conflicting is done automatically either by following the standard right of way rules, which also often serve as a guiding principle for air traffic controllers; or by following the 'Lowest Impact of Deviation' principle. Based on EUROCONTROL’s Base of Aircraft Data (BADA), the simulation estimates the fuel consumption for each flight as well as for the whole simulation, and consequently also the CO 2 emissions, as a function of traffic density.This paper gives basic information about the principle itself, which is then further tailored down and applied to a free route airspace environment for en-route traffic. It briefly describes the used fast time simulation and illustrates the obtained results. This paper quantifies the theoretical benefit that can be achieved by applying the mentioned principle in the described way. When knowing the traffic density of real air traffic control sectors, the results can easily and directly be transferred to them.

Today metro cities in India are facing more problems due the traffic congestion in the roads that connects different neighboring cities. Due to overwilling of population and covid - 19 pandemic that increased the usage private vehicles by the mankind. Many of the existing methods use the sensor to detect the number of vehicles in that location and implied on to the google maps. The model has been proposed to overcome the issue by considering the existing video cameras been installed in different location in the signals and crowed places. The proposed model incorporated in the edge computing through Nvidia Jetson nano for the object detection using Common Objects in Context (COCO) to detect the boundary boxes for the ten categories of the object. The detection Score is obtained by considering probability of the detection boxes identified in the particular location with respect to time. The accuracy level of each object in the frame is detected and filtered based on the threshold value such that the false positive and true negative can be avoided in the Contributory matrix. Based on the results obtained from the model the location wise table that classify the images with respect low medium and High. The proposed model proves that accuracy of predicting the traffic based on three categories as Low, Medium and High are estimated correctly. The results are apprised based on the accuracy of the particular object identified in the image or frame with respect to number of images tested for the accuracy. The mean square errors are assessed based on the number of objects identified on each category in a particular image.