CIDAI has shared the results of the Intelligent Mobility Agent for ATM project, 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 natural language queries about public transport in Catalonia, integrating both static data and real-time operational information. The solution leverages the open GTFS and GTFS-RT standards to provide contextualized, reliable, and accessible information to citizens, public administrations, and transport 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 analytics architectures. The system incorporates a language model integrated through the OpenAI API and implements the ReAct (Reasoning + Acting) pattern, enabling it to combine reasoning capabilities with the execution of specific actions on tools and databases.
The developed architecture adopts 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 functionalities such as Speech-to-Text through Whisper. The system allows users to make natural language queries about timetables, routes, connections, disruptions, nearby stops, and operational alerts.
During the session, the project’s main technical and functional results were presented, along with the key challenges identified regarding data quality, response latency, and service scalability. From the perspective of ATM, particularly the Mobility Information Management Centre (CGIM), this project represents a first structured approach to the use of generative artificial intelligence in the mobility sector and helps identify both its potential and the technical and functional constraints associated with its application in real-world operational environments.
