Schleiß, Philipp

Filters

1 1
1
Reset filters

Settings
Now showing 1 - 1 of 1
  • Publication
    Trustworthy AI for Intelligent Traffic Systems (ITS)
    (Fraunhofer IKS, 2021)
    Bortoli, Stefano
    ;
    Grossi, Margherita
    ;
    Burton, Simon
    ;
    Grobelna, Marta
    ;
    Hagiwara, Yuki
    ;
    Schleiß, Philipp
    AI-enabled Intelligent Traffic Systems (ITS) offer the potential to greatly improve the efficiency of traffic flow in inner cities resulting in shorter travel times, increased fuel efficiency and reduction in harmful emissions. These systems make use of data collected in real-time across different locations in order to adapt signaling infrastructure (such as traffic lights and lane signals) based on a set of optimized algorithms. Consequences of failures in such systems can range from increased congestion and the associated rise in traffic accidents to increased vehicle emissions over time. This white paper summarizes the results of consultations between safety, mobility and smart city experts to explore the consequences of the application of AI methods in Intelligent Traffic Systems. The consultations were held as a roundtable event on the 1st July 2021, hosted by Fraunhofer IKS and addressed the following questions: How does the use of AI fundamentally change our understanding of safety and risk related to such systems? Which challenges are introduced when using AI for decision making functions in Smart Cities and Intelligent Traffic Systems? How should these challenges be addressed in future? Based on these discussions, the white paper summarizes current and future challenges of introducing AI into Intelligent Traffic Systems in a trustworthy manner. Here, special focus is laid on the complex, heterogeneous, multi-disciplinary nature of ITS in Smart Cities. In doing so, we motivate a combined consideration of the emerging complexity and inherent uncertainty related to such systems and the need for collaboration and communication between a broad range of disciplines.