Adaptive System Architecture for Intelligent Multimodal Transport: Challenges and Fundamental Design Aspects

Multimodal Intelligent Transportation Systems (M-ITS) encompass a range of transportation services utilizing various modes of transport (e.g., buses, trains, ride-sharing) and incorporating intelligent technologies for enhanced efficiency and user experience. Traditional, non-adaptive system architectures struggle to respond to dynamic changes in real-time traffic conditions, user demands, and operational disruptions. These rigid systems lack flexibility in integrating new technologies, managing fluctuating demand, and ensuring seamless operation across multiple transport modes. Consequently, inefficiencies in data handling, scalability, and real-time decision-making emerge, hindering the potential of M-ITS. In this paper, we provide a conceptual layered architecture that can adapt to various needs of multimodal transportation systems. The proposed architecture focuses on aspects such as scalability, adaptability, seamless integration, and interoperability of various subcomponents that are owned and managed by different stakeholders (parties with an interest or role in the system, such as users, city planners, service operators, and technology providers). In addition to the component architecture, we propose a data architecture that emphasizes the crucial role of integrating multimodal, multisource data to enable intelligent decision-making. We illustrate the functionality of the proposed architecture through two use cases at a conceptual level: a traffic monitoring system and a traffic flow prediction system. These examples demonstrate how the data and system architecture can be fused and serve multimodal intelligent transport services, highlighting its ability to adapt to complex urban environments. Furthermore, we present results for an emergency vehicle approaching scenario, showcasing the architectures responsiveness and adaptability in critical situations.