Share it

The Centre of Innovation for Data Tech and Artificial Intelligence (CIDAI) invites you to the results presentation session of the project Intelligent Mobility Agent for ATM, an initiative aimed at exploring the potential of generative artificial intelligence applied to public mobility services in Catalonia.
The project has developed an intelligent conversational assistant capable of answering questions in natural language about public transport in Catalonia, integrating both static data and real-time operational information. The solution leverages the open standards GTFS and GTFS-RT to provide contextualized, reliable, and accessible information to citizens, public administrations, and operators.
The Intelligent Mobility Agent represents a new approach to semantic access to public mobility data, combining generative artificial intelligence technologies with traditional data querying and exploitation architectures. The system incorporates a language model integrated through the OpenAI API and implements the ReAct pattern (Reasoning + Acting), which enables the combination of reasoning capabilities with the execution of specific actions on tools and databases.
The developed architecture follows a modular and scalable approach, integrating a conversational interface, a FastAPI-based backend, a database optimized for large volumes of information, an interactive dashboard, and multimodal features such as Speech-to-Text through Whisper. The system allows users to query schedules, routes, connections, incidents, nearby stops, or operational alerts using natural language.
During the session, the main technical and functional results of the project will be presented, along with the challenges identified related to data quality, response latency, and service scalability.
From ATM’s perspective—particularly from the Mobility Information Management Center (CGIM)—this project represents a first structured approach to the use of generative artificial intelligence in the mobility domain, helping to identify both its potential and the technical and functional constraints of its application in real operational environments.

Programme

  • 11:00 am | Registration and welcome coffee

Event host: Marco Orellana, Manager of CIDAI

  • 11:30 am | Institutional welcome
    Manuel Valdés López, Director General of ATM
    Meritxell Granger, Head of the Digital Sector Promotion Area at the Secretariat for Digital Policies of the Government of Catalonia
  • 11:45 am | Project overview by ATM
    Guillem Vall, Head of Mobility Services at ATM
    He will present ATM Barcelona’s digitalization and standardization strategy and how we aim to deliver the outputs of this strategy to users. This joint pilot is part of the broader effort to improve how mobility information is communicated to users.
  • 11:55 am | Methodology and architecture for the intelligent mobility agent
    Ian Palacín and Oriol Alàs, Researchers at the Applied Artificial Intelligence (AAI) unit at Eurecat
    Presentation of the methodology, technical architecture, and functional description of the conversational assistant. Demonstration of the developed prototype and the main use cases implemented in public mobility. The technical solution will be presented, with a focus on decisions made to address common challenges in this type of technology, such as response reliability, integration with heterogeneous data sources, latency, and system scalability.
  • 12:35 pm | Solution evaluation and next steps
    Pol Carrera, Technology Lead at the Mobility Information Management Center of ATM
    The tests carried out at the Mobility Information Management Center will be presented, as well as the potential applications across various ATM Barcelona products, provided funding is available to continue the pilot.
  • 12:45 pm | Q&A
  • 01:00 pm | End of event

Venue

sede eurecat

EURECAT

72, Bilbao street | Complex Cornerstone | Innova room

08005 Barcelona

LIMITED SEATS AVAILABLE!

ATM-bus
El projecte ha desenvolupat un assistent conversacional intel·ligent capaç de respondre preguntes en llenguatge natural sobre el transport públic de Catalunya, integrant tant dades estàtiques com informació operativa en temps real.
CIDAI