In a recent publication in the journal Information, researchers conducted an in-depth analysis of artificial intelligence (AI) applications in urban sustainability. This offers recommendations for stakeholders and outlines future research directions.
Study: Leveraging Artificial Intelligence for Urban Sustainability and Mobility. Image credit: Generated using DALL.E.3
Background
In the past, various industries, including retail, finance, insurance, healthcare, and sports, have harnessed technology to address operational challenges, driving efficiency improvements and cost reductions. However, the transportation sector has experienced transformative change through cutting-edge technology adoption, which impacts both vehicle efficiency and overall system effectiveness. This profound transformation in mobility is underpinned by digital innovation. Emerging technologies applied to transportation enable personalized and dynamic mobility management, striking a balance between efficiency and sustainability in urban environments.
AI emerges as a pivotal tool for decision-making and continuous adjustment of transport supply to meet the demands of increasingly flexible and fluid mobility in the era of cooperative-intelligent transportation systems (ITSs). AI, combined with big data acquisition and analysis of traffic flows, serves to calibrate demand simulation models and interpret phenomena, even during exceptional or disruptive events.
AI-based solutions hold the potential to significantly advance urban mobility globally. They enhance data collection, storage, and analysis to improve urban transport systems.
Impact of AI paradigm shifting on transport
The concept of urban AI is defined as the operation of artifacts within cities capable of acquiring and interpreting information about the urban environment. These artifacts use their knowledge to make rational decisions, even in complex situations where information may be incomplete. The sustainable and intelligent mobility market is rapidly evolving, and various stakeholders are recognizing the potential benefits. To harness these opportunities and mitigate the risks associated with innovation, cities must adopt an integrated strategy with a system-wide approach.
In pursuit of enhanced user experiences and more sustainable, liveable cities, researchers examine the role of AI in supporting dynamic and personalized mobility solutions and its contribution to sustainable mobility planning.
AI for dynamic and personalized mobility
Mobility needs are continually evolving, and AI, paired with emerging technologies, is set to bring further transformation. Big data analytics, machine learning, and AI automation are enabling real-time information processing from various sources, including mobile devices, and enhancing intermodal transport options.
Many cities are committed to ambitious sustainability goals, including reducing motorized vehicles and promoting sustainable transportation modes. Shared mobility solutions and on-demand transportation companies have become reliable alternatives, especially in areas implementing demand management policies. The "mobility-as-a-service" (MaaS) concept aims to offer tailored mobility solutions for passengers and freight, promoting the integration of various transportation modes into a seamless travel experience.
The advancements in AI benefit both users and businesses but carry the risk of unguided innovation. Innovations require intelligent government and data-based planning to ensure equilibrium in the urban mobility system. Without proper governance, MaaS could lead to service disparities and disincentivize sustainable mobility.
AI for sustainable urban mobility planning
Sustainable Urban Mobility Plans (SUMPs) are vital in guiding cities toward sustainable and efficient urban mobility. The SUMP's 10-year planning horizon provides a vision for the urban mobility system, promoting environmental, social, and economic sustainability. Quantitative evidence forms the basis for defining objectives and monitoring their implementation. AI aligns with the Sustainable Development Goal of creating sustainable cities and communities. It aids in developing and monitoring SUMPs, offering insights into mobility's impact, and translating it into quality-of-life indicators. During the participatory process of SUMP design, AI applications facilitate communication and goal-sharing with citizens, fostering smart and community-friendly mobility.
To drive this positive transformation, cities must embrace digital innovations that support flexible, user-centric solutions and enable intelligent information management for urban and extra-urban mobility governance in a dynamic, interconnected ecosystem.
Intelligent transportation systems
The evolution of Intelligent Transportation Systems (ITS) into integrated digital platforms is a game-changer for smart cities. These digital platforms, particularly service-oriented ones, excel in data acquisition, rapid interpretation, and decision support for urban transport system management. They emphasize intermodality and multi-channel information. Creating AI-based MCCs is a trend in modern cities. These MCCs centralize data and control field systems, integrating elements such as IoT, ITS, big data, traffic simulation, AI, and MaaS. This integration optimizes services for collective goals, offering dynamic, intermodal journeys with real-time updates.
Application in a virtual district
Researchers proposed an IT framework for medium-large cities with fragmented ITS and C-ITS systems seeking to implement an AI-based MCC. This MCC centralizes data and services, capitalizing on previous investments and enhancing value through data management. The architecture includes several layers. Data source integration layer for acquiring data from sensors and external systems. High-performance data layer for ingesting, preprocessing, and storing data. Business Logic Layer to utilize transport models and AI for data processing. API management offers scalable API creation and management. Finally, the data consumption layer presents data to end users with customizable views, KPIs, and analytics.
The MCC operator interface includes modules for traffic status supervision, network and ITS monitoring, decision support, operational management, prediction, KPIs, analytics, and asset management. AI is crucial in automating and supporting these modules, facilitating quick decision-making and evidence-based mobility policies.
Conclusion
In summary, the current study introduces an AI-based MCC framework for urban sustainability. AI supports weather prediction, traffic management, and public transportation planning, making smart cities more efficient. However, cost distribution and policy fragmentation pose challenges. Local governments should adopt sustainable urban mobility plans, invest in AI-based MCCs, and prioritize regulatory and safety compliance. The digital transition with AI promises enhanced urban quality of life, but it requires integrated frameworks and skilled governance.
Control and Motion Planning of Fixed-wing UAVs Through Reinforcement Learning