The road traffic safety situation is severe worldwide and exploring driving behavior is a research hotspot since it is the main factor causing road accidents. However, there are few studies investigating how to evaluate real-time traffic safety of driving behavior and the number of driving behavior safety levels has not yet been thoroughly explored. This paper aims to propose a framework of real-time driving behavior safety level classification and evaluation, which was validated by a case study of driving simulation experiments. The proposed methodology focuses on determining the optimal aggregation time interval, finding the optimal number of safety levels for driving behavior, classifying the safety levels, and evaluating the driving safety levels in real time. An improved cross-validation mean square error model based on driver behavior vectors was proposed to determine the optimal aggregation time interval, which was found to be 1s. Three clustering techniques were applied, i.e., k-means clustering, hierarchical clustering and model-based clustering. The optimal number of clusters was found to be three. Support vector machines, decision trees and naïve Bayes classifiers were then developed as classification models. The accuracy of the combination of k-means clustering and decision trees proved to be the best with three clusters.

Platooning of connected automated vehicles (CAVs) on highways has attracted the interest of researchers, companies and administrations for years. This interest has yielded a vast literature on CAV platooning, which generally describes its benefits in terms of traffic efficiency, safety and environmental impacts, among others. However, the boundary conditions of these studies and the reported magnitude of these benefits vary greatly among the different contributions. In this context, this paper presents the result of a comprehensive literature review on CAV platooning on highways, organizing the existing research and establishing links between the different strategies proposed and their expected impacts. Starting points for future investigations are suggested, and the research gaps to be addressed are identified. The analysis performed shows that the current state-of-the-art has two major limitations. First, few CAV platooning strategies have been proven to be asymptotically stable, which should be a requirement for any feasible solution. Second, in most cases, the CAV platooning algorithms are simplistic adaptations from existing car-following models proposed for human driving that, therefore, unnecessarily transfer current traffic-related problems to future cooperative environments.

Urban air mobility (UAM) has recently increased in popularity as an emerging mode of transportation, covering a wide range of applications, for on-demand or scheduled operations of smaller aircraft, in and around metropolitan areas. Due to its novelty and as it has not yet been implemented, UAM research still faces uncertainties. In particular, there is a need to develop a roadmap for the early implementation of passenger air mobility, aiming to identify the most prominent challenges, opportunities, hazards, and risks, but also to highlight the most promising use cases, or on the contrary, the ones associated with the least benefits compared to the risks or complexity they entail. To answer the previous questions, and therefore address this research gap, this study used a two-round Delphi questionnaire, targeting various stakeholder groups (product owners, policymakers, researchers, consultants, investors), leading to a total of 51 experts, out of which 34 also participated in the second round. In the first round, the main challenges, opportunities, and hazards facing the implementation of passenger UAM were identified. Findings on challenges and opportunities that were dependent on use cases only (as opposed to being dependent on technology or external factors) were then fed back into the second round, which helped evaluate the use cases based both on their complexities, as well as the associated benefits. Accordingly, medical/emergency was identified as the best use case and intracity transport as the worst (in terms of complexity vs. benefits). Similarly, a risk analysis evaluated the potential hazards associated with the implementation of UAM and their impacts on the system viability. Community backlash was found to be the most hazardous one, while malicious passenger behavior and improperly designed infrastructure as the least. Findings from this study can help better understand stakeholders’ opinions, highlighting promising use cases, but also risks to be aware of, constituting therefore a roadmap for future implementation.

Advanced driver assistance systems (ADASs) have recently gained popularity as they assist vehicle operators in staying within safe boundaries, helping them thereby to prevent possible collisions. However, despite their success and development, most ADAS use common and deterministic warning thresholds for all drivers in all driving environments. This may occasionally lead to the issuance of annoying inadequate warnings, due to the possible differences between drivers, the changing environments and driver statuses, thus reducing their acceptance and effectiveness. To fill this gap, this paper proposes adaptive algorithms for commonly used warnings based on real-time traffic environments and driver status including distraction and fatigue. We proposed adaptive algorithms for headway monitoring, illegal overtaking, over-speeding, and fatigue. The algorithms were then tested using a driving simulator. Results showed that the proposed adaptive headway warning algorithm was able to automatically update the headway warning thresholds and that, overall, the proposed algorithms provided the expected warnings. In particular, three or four different warning types were designed to distinguish different risk levels. The designed real-time intervention algorithms can be implemented in ADAS to provide warnings and interventions tailored to the driver status to further ensure driving safety.

Artificial intelligence (AI) is a disruptive technology promising to revolutionize the relationship between humans and urban environments. While the forms of human-machine interaction are becoming increasingly natural and naturalized, the impacts of such interactions for individuals and society are far from simple to grasp. As AI and Urban AI-related systems are being adopted by local governments and public authorities in support of public service delivery, it becomes increasingly important to involve communities in discussing impacts and working towards acceptable trade-offs in terms of the risks and benefits AI can represent to everyday life. Participation is often part of the discourse around policymaking and urban governance, yet the gap between decision-makers and city-makers within urban governance is not resolved. Besides, the barriers participatory processes hold to be accessible and inclusive stem now from lack of AI literacy and overall awareness on why and how participation can be a pillar of policymaking. We propose an urban governance framework for assessing the collective challenges of AI focused on people centeredness and public participation. Our contribution to the field of urban governance is a piloted framework designed and implemented in collaboration with city representatives, supra governmental organizations and non-governmental organizations and respective lessons learned.

Technological advances are disrupting mobility patterns and transport technologies, both on the ground and in the air. The latter has been recently observed in the research community of urban air mobility (UAM). Research in this area has studied several areas of its implementation, such as vehicle concepts, infrastructure, transport modeling, or operational constraints. Few studies however have focused on evaluating this service as an alternative among existing transportation systems. This research presents an approach for the selection of indicators for a multi-criteria analysis for the assessment of UAM, in a case study of Upper Bavaria, Germany. A 5-stage approach is showcased including an expert assessment for the relevance and feasibility of indicators, based on two rating scales. A threshold for selection is presented, applied and validated for both scales. The results included a list of indicators for assessing the potentials of UAM integration to existing public transportation systems; the chosen indicators were then compared against existing ones for sustainable urban mobility. A high match between resulting indicators and previous ones further validate the results, and suggest that there is a need for an iterative approach in the assessment of disruptive transport technologies.