Sie können Operatoren mit Ihrer Suchanfrage kombinieren, um diese noch präziser einzugrenzen. Klicken Sie auf den Suchoperator, um eine Erklärung seiner Funktionsweise anzuzeigen.
Findet Dokumente, in denen beide Begriffe in beliebiger Reihenfolge innerhalb von maximal n Worten zueinander stehen. Empfehlung: Wählen Sie zwischen 15 und 30 als maximale Wortanzahl (z.B. NEAR(hybrid, antrieb, 20)).
Findet Dokumente, in denen der Begriff in Wortvarianten vorkommt, wobei diese VOR, HINTER oder VOR und HINTER dem Suchbegriff anschließen können (z.B., leichtbau*, *leichtbau, *leichtbau*).
Dieses Kapitel vertieft die Errungenschaften und zukünftigen Prioritäten der künstlichen Intelligenz in Verkehrssystemen und konzentriert sich auf EU-finanzierte Projekte im Rahmen von Horizont 2020 und Horizont Europa. Sie unterstreicht das zunehmende Interesse an KI-Anwendungen im Straßenverkehr, wobei sich Sicherheitsbedenken deutlich in Richtung Optimierung und ökologische Nachhaltigkeit verlagern. Der Text untersucht auch den Einsatz künstlicher Intelligenz im Wasser-, Luft- und Schienenverkehr sowie in intermodalen Projekten, die darauf abzielen, kooperative Transportökosysteme zu schaffen. Zu den wichtigsten Errungenschaften zählen der Einsatz künstlicher Intelligenz für vorausschauende Wartung, automatisierte Fahrzeuge, Verkehrsoptimierung und die Verbesserung der Hinderniserkennung im Schienenverkehr. Die zukünftigen Prioritäten konzentrieren sich auf Vision Zero, ökologische Nachhaltigkeit und die Steigerung der Wettbewerbsfähigkeit, wobei weiterer Forschungsbedarf besteht, um angemessene Haftungsregelungen sicherzustellen und Bedenken wie Akzeptanz, Ethik und soziale Inklusion der Nutzer anzugehen. Das Kapitel kommt zu dem Schluss, dass KI das Potenzial hat, den Transportsektor zu revolutionieren und ihn trotz bestehender Skepsis intelligenter, sicherer und effizienter zu machen.
KI-Generiert
Diese Zusammenfassung des Fachinhalts wurde mit Hilfe von KI generiert.
Abstract
This paper aims at defining future research priorities for artificial intelligence (AI) in transport systems. The point of the departure is the state of the art regarding the application of AI in transport combined with the EU policy needs and the assessment of the recent European projects. The paper presents an overview of the potential benefits that the deployment of AI has for transport. Special focus is put on results of European projects funded within Horizon 2020 Framework Programme. The main achievements of the research have shown that AI can help in the optimisation of applications within the transport means. It can also aid public authorities in improving the overall infrastructure thanks to data gathering and first screening. Further, the deployment of AI is a source of profitable opportunities for various sectors like automotive, software, waterborne, aviation, passenger and freight transport. The final aim of these projects is to boost efficiency, sustainability, and safety by having a human centric AI, aware of every situation it is facing and able of taking prompt decisions. The paper concludes by discussing selected cross-cutting concerns regarding the application of AI in the transport sector. They include definition of software updates for autonomous vehicles’ algorithms, the need for liability regimes and the issue of data scarcity.
1 Introduction
Artificial intelligence (AI) is pivotal for the modernization and optimisation of the transport sector. Its deployment shows improvements, from traffic management to enhancing vehicle safety and security. The Horizon Europe (HE) and Horizon 2020 (H2020) programmes are the EU’s flagship projects for research and innovation (R&I). They include several calls for actions related to the progress of the use of AI in the transport sector to boost efficiency, sustainability, and safety. In this context, the deployment of AI in transport is one of the main tools for achieving the targets set by the European Grean Deal and the Vision Zero. Hence, acknowledging both past and present R&I activities is key for the development of new technologies and strategies.
2 Background
The EU priorities regarding the application of AI technologies to transport modes have evolved throughout the past years. In 2021 the European Commission (EC) started the process for the enactment of a Regulation dealing with AI horizontally. In the specific case of transport, it tackles its critical role for citizens’ health [1]. R&I projects are supported by political, and legislatives aims and objectives. Thus, funding programmes for R&I are fundamental for reaching EC’s goals. H2020 had an overall budget of nearly €80 billion for the period of 2014 to 2020. A new round of projects has been launched by HE for the 2021–2027 period. Most of the calls from H2020 and HE deal with the application of AI on road transport. However, increasing considerations are given to aviation and waterborne projects.
Anzeige
Additionally, the Joint Research Centre (JRC) of the European Commission has also been active in assessment of the deployment of AI technologies in the transport sector. Most of the JRC works looked at AI applied to road transport, where it can potentially oversee vehicles’ safety, robustness, and security [2]. This includes, for instance, safety and security of AI technologies, particularly related to malicious action and cybersecurity risks in automated vehicles (AV) [3].
Moreover, the need emerged for the establishment of testing strategies accounting for the inherent flaws of AI systems [4]. Indeed, AI algorithms are ultimately responsible for the driving actions at high levels of automation [5]. Thus, a harmonised legal definition of software updates for AV algorithms is needed. However, some researchers believe that applying AI to AV could increase uncertainty and have undesirable consequences due to the complexity of the road transport system [6]. In essence, the review of the existing research studies carried out by JRC demonstrates the gap between technology and regulation and the overall need for furthering the existing knowledge for road transport and AI.
3 Methods and Data
In the next two sections we provide a review and assessment of the EU funded AI R&I projects with a focus on AI application to transport. Community Research and Development Information Service (CORDIS) (Fig. 1) contains a constantly updated database of H2020, and HE funded programmes and projects on transport R&I. This study focuses on 88 projects (38 for HE and 50 for H2020) that deal or dealt with AI in the transport sector. We reviewed identified projects to define main themes within AI transport research and to categorize projects according to these themes. The themes are related to application of AI for particular transport mode, and they include:
Road: research projects that investigate AI technologies employed for predictive maintenance, automated vehicles, traffic optimisation, fleet management and reduction of environmental impacts.
Waterborne: projects that research the improvement of shipbuilding and maintenance.
Aviation: research on AI technologies for enabling new digital aviation technologies for new aircraft business models and services, as well as minimise the risk from emerging threats to aviation such as extreme weather phenomena, cybersecurity, and communicable diseases.
Rail: methods to optimise automation and recognition of obstacle detection.
Cross modal: projects that investigate the application of AI holistically to the transport sector, regardless of the type of the transport in which the technology is applied to.
We categorised the relevant R&I projects into the macro categories by identifying the relevant keywords for each category, followed by a review of project objectives and results.
Anzeige
4 Results
4.1 Overview of the Projects
The data analysed show an increasing interest for R&I on the application of AI to road transport. Road transport projects on AI went from 42% of the overall projects under H2020 to 64% under HE. This anticipates an implied interest for automated vehicles and their implications. At the same time, some of these technologies are cross-cutting among transport sectors.
Fig. 1.
R&I projects implementing AI in modes of transport in H2020 and HE
4.2 Key Achievements and Results of H2020 Projects
Road. The major concern for public safety is human error as it plays a significant role in 94% of accidents [7]. Although AI appears to be a promising technology for monitoring the driver’s state and behaviour [7], it lacks public acceptance of AVs [8]. One project suggested commercial campaigns as a mean to gain people’s trust [9]. Another project suggested for AI to be coupled with 5G and mobile edge computing for reaching the most efficient cross-modal communication [10].
Waterborne. The project BugWright2 is ongoing, however it showed promising initial results in using autonomous robotic solutions for underwater hull cleaning. This type of technologies can significantly decrease the consumption of fuels in merchant vessels.
Aviation. AI has effectively tackled disruptions to air communications networks by predicting and thus preventing hazards [11]. AI was also used to facilitate airlines commercial activities by ensuring a secure digital marketplace [12]. However, AICHAIN, SIMBAD and SlotMachine projects showed the most promising results for passengers as they seek to predict, avoid, and alleviate delays for users [12].
Rail. Collision with obstacles is still very relevant for rail transport. SMART2 has showed great results in designing a system that enhances the obstacle detection of the train.
Cross modal. Research demonstrated that the creation of cooperative transport ecosystems connecting users and infrastructures can aid in making road transport systems safer, more sustainable and efficient [13, 14].
4.3 Current and Future Research Priorities: HE Projects
The future HE calls mirror R&I priorities, focusing on Vision Zero1, environmental sustainability and boost of competitiveness. By looking at the background analysis of this paper and the topics of the HE calls it is possible to see a continuation between what should be done and what it is intended.
Road. The priorities shifted from safety to optimisation of the road recharging systems, advancing environmental sustainability, and improvement of connected, cooperative, and automated mobility. AVs’ systems must be technically robust and safe, resilient to attacks, respect privacy and data governance, be transparent in its operations, apply non-discriminative behaviours, ensuring societal and environmental well-being [15].
Waterborne. Most projects focus on improving safer navigation and detection of viruses on board.
Aviation. New projects will focus on AI application for reducing the environmental impact of aviation, facilitate business models and enhance aviation safety.
Overall, future priorities will require for further research as it is necessary for ensuring that the proper liability regimes are put in place [4]. The level of uncertainty given by human logical mechanisms can lead AI to behave unexpectedly [4]. AI technologies are key for the development of a new generation of vehicle safety systems that can better protect drivers and pedestrians by handling situations where human capabilities fail [4]. For instance, AI deployment is essential updating traffic management systems. Some of the papers reviewed by this study suggest further research on multimodality and transport infrastructure projects, sensors, and detection systems [16]. This would facilitate ongoing communication among 3 modes of transport and enable the transport system to reach and please as many users as possible. Moreover, future research should focus on the integration of such on shore automated systems with smart scheduling and potentially automated ships, integrating logistic chains and benefiting operational measures to reduce GHG emissions such as lower cruising speeds [17].
At a societal level, the application of AI technologies to transport could bring important safety and productivity gains. Nevertheless, some important concerns exist, such as users’ acceptance, ethics, social inclusion, and labour. AI applied to transport systems can provide profitable opportunities for many sectors, namely automotive, software and digital media [18]. On the other hand, sectors like insurance and maintenance and repair are identified as businesses that might experience important decreases in revenues in the future due to a decrease of accidents [18].
5 Conclusion
R&I projects are fundamental for highlighting the advantages that AI can bring and more importantly for individuating and preventing the risks associated to it. AI can potentially be the main solution to many transport challenges, despite people’s scepticism. The projects reviewed for this paper represent a step forward towards an optimised, sustainable and high-functioning transport environment. R&I is necessary for cost-effective smart mobility, safer infrastructures, and for increasing the deployment of AI in support of the operation of the network. Making more data available means more deployment of data-driven services and technologies such as AI. AVs have the potential of reducing energy consumption and emissions from transport. Although AVs can enhance road safety, they do not increase road capacity. Hence, AI technologies are making the transport sector smarter, with enormous advantages in relation to safety and efficiency. Overall, the existing projects focused on pre-empting disaster and enhancing safety of all modes of transport. Thus, the essence of AI is to increase efficiency in a secure and safe manner.
Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Llorca, F., Gomez, D., Gutierrez, E.: Artificial intelligence in autonomous vehicles: towards trustworthy systems, European Commission, no. JRC128170, pp. 1–6 (2022)
3.
Dede, G., Hamon, R., Junklewitz, H., Naydenov, R., Malatras, A., Sanchez, M.: Cybersecurity challenges in the uptake of Artificial Intelligence in Autonomous Driving. Publications Office of the European Union (2021)
4.
Hamon, R., et al.: Artificial Intelligence in automated driving: an analysis of safety and cybersecurity challenges, European Commission (2022)
5.
Baldini, G.: Testing and certification of automated vehicles including cybersecurity and artificial intelligence aspects, Publications Office of the European Union (2020)
6.
Ortega Hortelano, A., et al.: Research and innovation in car sharing in Europe, Publications Office of the European Union (2022)
Fernandez Llorca, D., Gomez Gutierrez, E.: Trustworthy Autonomous Vehicles, Publications Office of the European Union (2021)
16.
Van Balen, M., et al.: Research and innovation in network and traffic management systems in Europe, Publications Office of the European Union (2020)
17.
Grosso, M., et al.: Waterborne transport in Europe - the role of Research and Innovation in decarbonisation, Publications Office of the European Union (2021)
18.
Alonso Raposo, M., et al.: An analysis of possible socio-economic effects of a Cooperative, Connected and Automated Mobility (CCAM) in Europe, Publications Office of the European Union (2018)
